{"pageProps":{"id":"publications","content":{"id":"YskDMBAAACAAW0Np","uid":"publications","url":null,"type":"page","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YskDMBAAACAAW0Np%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-09T04:25:32+0000","last_publication_date":"2022-07-09T04:26:57+0000","slugs":["publications","anumana--publications"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"hideDefaultContactForm":null,"slices":[],"seoTitle":"Publications","seoDescription":"Our latest academic publications","socialImage":{},"slices1":[]}},"publications":[{"id":"YtquuxAAACEAHJWW","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtquuxAAACEAHJWW%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-22T14:07:07+0000","last_publication_date":"2024-09-20T17:41:25+0000","slugs":["ai-enhanced-ecg-enabled-rapid-non-invasive-exclusion-of-severe-acute-respiratory-syndrome-coronavirus-2-sars-cov-2-infection"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"AI Enhanced ECG Enabled Rapid Non-invasive Exclusion Of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) Infection","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Rapid identification of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is critical to management of the pandemic. We sought to investigate the use of artificial intelligence applied to the ECG to rule out acute COVID-19.","spans":[{"start":24,"end":69,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/sars-coronavirus","target":"_blank"}}],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"A global, volunteer consortium from 4 continents identified patients with ECGs obtained around the time of PCR confirmed COVID 19 diagnosis. Clinical characteristics and raw ECG data were collected. A convolutional neural network was trained using 26,153 ECGs (33.2% COVID positive), validated with 3,826 ECGS (33.3% positive) and tested on 7,870 ECGs not included in other sets (32.7% positive). Performance under different prevalence values was tested by adding control ECGs from a single high-volume site.","spans":[{"start":121,"end":129,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/covid-19","target":"_blank"}},{"start":215,"end":229,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/agricultural-and-biological-sciences/neural-network","target":"_blank"}}],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[],"direction":"ltr"},{"type":"paragraph","text":"The area under the curve (AUC) for detection of acute COVID 19 infection in the test group was 0.767 (95% CI: 0.756 to 0.778) (sensitivity 98%, specificity 10%, positive predictive value 37%, negative predictive value 91%). When 50,905 normal controls were added to adjust the COVID prevalence to approximately 5% (2,657/58,555), resulting in an AUC of 0.780 (95% CI: 0.771 to 0.790) with a specificity of 12.1% and a negative predictive value to 99.2%.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Infection with SARS-CoV-2 results in electrocardiographic changes that permit the AI-ECG to be utilized as a rapid screening test with a high negative predictive value (99.2%). This may permit the development of ECG-based tools to rapidly screen individuals for pandemic control.","spans":[{"start":115,"end":129,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/biochemistry-genetics-and-molecular-biology/screening-test","target":"_blank"}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"A global study used artificial intelligence applied to ECGs to detect acute COVID-19 infections, finding that the AI-ECG achieved a high negative predictive value of 99.2%. The convolutional neural network demonstrated an area under the curve (AUC) of 0.767 in initial testing, improving to 0.780 when adjusted for prevalence. This suggests AI-ECG could be a useful tool for rapid screening and pandemic control.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"69d93352-91f8-4bc0-a58c-c8d19994fd0f","url":"https://www.sciencedirect.com/science/article/pii/S0735109721045253?via%3Dihubhttps://"},"date":"2021-05-01T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Poster @ American College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi Itzhak Attia, Suraj Kapa, Jennifer Dugan, Naveen Pereira, Peter Noseworthy, Francisco Lopez-Jimenez, Rickey Carter, Jessica Cruz, Daniel DeSimone, John Signorino, John Halamka, Paul Friedman","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbi9RAAACEAC3ur","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbi9RAAACEAC3ur%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:59:37+0000","last_publication_date":"2024-09-20T17:37:29+0000","slugs":["artificial-intelligence-helps-identify-patients-with-graves-disease-at-risk-for-atrial-fibrillation"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence Helps Identify Patients With Graves' Disease At Risk For Atrial Fibrillation","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Graves' disease (GD) is known to be associated with atrial fibrillation (AF). Artificial intelligence (AI)-enabled ECGs using a convolutional neural network can identify the signature of silent AF. Whether the existing AI model is able to identify patients at highest risk of GD-related AF is unknown.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Patients with GD (2009-2019) at our institution were included. GD-associated AF was defined as AF diagnosed ≤30 days before or any time after GD. Probability of AF was obtained from the AI platform on ECGs in sinus rhythm done within 2 months before and up to 2 years after GD; when multiple ECGs were present, the earliest was considered. ECGs done at/after AF diagnosis were excluded. Risk factors were analyzed using cox proportional hazards. For multivariate analysis, all variables with p <0.2 at univariate analysis were entered into the model and a stepwise selection method was used to generate the final model.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"430 patients with GD were included; mean age 50±17, 78% female. AF was diagnosed in 43 (10%) patients with a median (IQR) of 11 (0-863) days after GD. ECGs used were obtained 27 (4-690) days before AF. Univariate risk factors included older age [HR 1.07 (1.04-1.09) p <.001], male gender [HR 1.9 (1.01-3.6) p =.047], hypertension (HR 4.4 (2.2-8.8), p<.001), hyperlipidemia [HR 2.8 (1.5-5.1), p = .001], history of coronary artery disease [HR 5.0 (2.4-10.5), p <.001], chronic kidney disease [HR 2.9 (1.4-6.3), p =.006], and probability of AF >5% [HR 5.9 (3.2-10.9). p<.001]. At multivariate analysis, risk factors for AF were AI ECG probability of AF>5% [HR 4.2 (2.1-8.1), p<.001], older age [HR 1.05 (1.03-1.07) per year, p=<.001] and overt hyperthyroidism (free T4>1.7) [HR 3.4 (1.04-11.1) p = .04]. Model AUC was 0.84 (compared to 0.79 without ECG-derived AF probability) and chi square was 61 (compared to 43 without ECG-derived AF probability, p <.001).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A clinical risk model based on AI-ECG, age and free T4 was strongly associated with developing GD-associated AF at follow-up. The AI-enabled ECG is available within the electronic medical record and could be easily incorporated in clinical-decision tools. Prospective validation of the model is currently underway.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"An AI-enabled ECG model effectively predicts the risk of atrial fibrillation (AF) in patients with Graves' disease (GD), identifying those at higher risk based on ECG probability, age, and free T4 levels. In a study of 430 GD patients, the model showed a strong association with AF development, with an AUC of 0.84. The AI-ECG could be integrated into clinical decision tools, with prospective validation ongoing.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"e4020d60-27c6-488b-967a-01d1e9e02760","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2901678-8"},"date":"2021-04-30T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Poster @ American College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jwan Naser, Zachi Itzhak Attia, Sorin Pislaru, Marius N. Stan, Peter Noseworthy, Paul Friedman, and Grace Lin","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuA1LxAAACYAoFtG","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuA1LxAAACYAoFtG%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:42:00+0000","last_publication_date":"2024-09-27T20:40:02+0000","slugs":["machine-learning-algorithms-to-predict-10-year-atherosclerotic-cardiovascular-risk-in-a-contemporary-community-based-historical-cohort"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Machine Learning Algorithms to Predict 10-Year Atherosclerotic Cardiovascular Risk in a Contemporary, Community-Based Historical Cohort","spans":[]}],"abstract":[{"type":"paragraph","text":"Background:\nThe ACC/AHA Pooled Cohort Equation (PCE) for Atherosclerotic cardiovascular disease (ASCVD) has shown modest accuracy. We assessed if machine learning algorithms (MLA) could improve PCE performance with traditional and selected enriched clinical features.","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Methods:\nWe tested MLA in a community cohort of patients >30 years, that sought primary care in Olmsted County, MN. Inclusion criteria was as of the PCE. ASCVD events were validated in duplicate and included fatal and non-fatal myocardial infarction and ischemic stroke at 10 years, analyzed as a composite and individual outcomes. A random sample of 70% of the dataset was used for training and optimal MLA were selected with grid search. Performance was evaluated in an independent testing set with the remaining observations.","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Results:\nWe included 34,831 adults, mean ± SD age 49.8 ± 23.2, 54% female, baseline PCE risk 6.54 ±11.5. There were 4,255 ASCVD events (12.2%) in 2,613 people: 1,850 non-fatal MI, 901 MI deaths, 1,299 ischemic strokes and 205 ischemic stroke deaths. MLA did not perform better than the PCE to predict ASCVD as whole or specific outcomes. Logistic regression provides modest improvement to predict ASCVD when adding enriched features (ROC 0.83361 vs 0.81843, p-value=0.03). Interestingly, all perform better when predicting fatal events vs. non-fatal events. See Table.","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Conclusion:\nMLA do not perform better than PCE when using the same variables and likely require additional features to enhance predictive capabilities.","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated whether machine learning algorithms (MLA) could improve the prediction of 10-year atherosclerotic cardiovascular disease (ASCVD) risk compared to the ACC/AHA Pooled Cohort Equation (PCE). Using a cohort of 34,831 adults, MLA did not outperform PCE in predicting ASCVD events, including myocardial infarction and ischemic stroke. Logistic regression showed a modest improvement when enriched clinical features were added, but overall, MLA provided no significant advantage. The results suggest that additional features may be needed to enhance the predictive capabilities of MLA.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"02d2f612-f010-4552-b54c-2090442ebe63","url":"https://www.jacc.org/doi/abs/10.1016/S0735-1097%2820%2932654-1"},"date":"2020-03-24T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Poster @ American College of Cardiology (ACC) 2020","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jose Medina-Inojosa, Michal Shelly, Zachi Itzhak Attia, Peter Noseworthy, Suraj Kapa, Paul Friedman, and Francisco Lopez-Jimenez","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZuANTxkAAEMAWOs8","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZuANTxkAAEMAWOs8%22%29+%5D%5D","tags":[],"first_publication_date":"2024-09-10T09:14:27+0000","last_publication_date":"2024-09-16T17:15:45+0000","slugs":["validation-of-noninvasive-detection-of-hyperkalemia-by-artificial-intelligenceenhanced-electrocardiography-in-high-acuity-settings"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Validation of Noninvasive Detection of Hyperkalemia by Artificial Intelligence–Enhanced Electrocardiography in High Acuity Settings","spans":[],"direction":"ltr"}],"abstract":[{"type":"heading2","text":"Abstract","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"heading3","text":"Key Points ","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"list-item","text":"Measuring blood potassium has always required access to blood. The surface electrocardiogram, analyzed using an artificial intelligence algorithm, can detect hyperkalemia bloodlessly.","spans":[],"direction":"ltr"},{"type":"list-item","text":"The artificial intelligence-analyzed electrocardiogram exhibited a high negative predictive value but substantially lower positive predictive value.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Background ","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Artificial intelligence (AI) electrocardiogram (ECG) analysis can enable detection of hyperkalemia. In this validation, we assessed the algorithm's performance in two high acuity settings.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods ","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"An emergency department (ED) cohort (February to August 2021) and a mixed intensive care unit (ICU) cohort (August 2017 to February 2018) were identified and analyzed separately. For each group, pairs of laboratory-collected potassium and 12 lead ECGs obtained within 4 hours of each other were identified. The previously developed AI ECG algorithm was subsequently applied to leads 1 and 2 of the 12 lead ECGs to screen for hyperkalemia (potassium >6.0 mEq/L).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results ","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The ED cohort (N=40,128) had a mean age of 60 years, 48% were male, and 1% (N=351) had hyperkalemia. The area under the curve (AUC) of the AI-enhanced ECG (AI-ECG) to detect hyperkalemia was 0.88, with sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive likelihood ratio (LR+) of 80%, 80%, 3%, 99.8%, and 4.0, respectively, in the ED cohort. Low-eGFR (<30 ml/min) subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.83, 86%, 60%, 15%, 98%, and 2.2, respectively, in the ED cohort. The ICU cohort (N=2636) had a mean age of 65 years, 60% were male, and 3% (N=87) had hyperkalemia. The AUC for the AI-ECG was 0.88 and yielded sensitivity, specificity, PPV, NPV, and LR+ of 82%, 82%, 14%, 99%, and 4.6, respectively in the ICU cohort. Low-eGFR subanalysis yielded AUC, sensitivity, specificity, PPV, NPV, and LR+ of 0.85, 88%, 67%, 29%, 97%, and 2.7, respectively in the ICU cohort.","spans":[{"start":15,"end":16,"type":"em"},{"start":76,"end":77,"type":"em"},{"start":572,"end":573,"type":"em"},{"start":631,"end":632,"type":"em"}],"direction":"ltr"},{"type":"heading3","text":"Conclusions ","spans":[{"start":0,"end":12,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The AI-ECG algorithm demonstrated a high NPV, suggesting that it is useful for ruling out hyperkalemia, but a low PPV, suggesting that it is insufficient for treating hyperkalemia.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study validated an AI-enhanced ECG algorithm for detecting hyperkalemia in emergency department (ED) and intensive care unit (ICU) settings. The algorithm showed a high negative predictive value (NPV) of 99-99.8%, making it highly effective for ruling out hyperkalemia, but a much lower positive predictive value (PPV). While useful for excluding the condition, the AI-ECG's low PPV limits its ability to confirm hyperkalemia, indicating it should not be relied on for treatment decisions.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"428aaf55-13fa-4be3-ad8c-28332d6047a6","url":"https://journals.lww.com/cjasn/abstract/2024/08000/validation_of_noninvasive_detection_of.6.aspx","target":"_blank"},"date":null,"algorithm":"Hyperkalemia","publishedIn":"journals","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"David M. Harmon, Kan Liu, Jennifer Dugan, Jacob C. Jentzer, Zachi I. Attia, Paul A. Friedman, John J. Dillon","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZalOaxIAACIAmr01","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZalOaxIAACIAmr01%22%29+%5D%5D","tags":[],"first_publication_date":"2024-01-18T16:19:27+0000","last_publication_date":"2024-09-16T17:35:54+0000","slugs":["artificial-intelligence-enabled-ecg-for-left-ventricular-diastolic-function-and-filling-pressure"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence-enabled ECG for left ventricular diastolic function and filling pressure","spans":[]}],"abstract":[{"type":"paragraph","text":"Assessment of left ventricular diastolic function plays a major role in the diagnosis and prognosis of cardiac diseases, including heart failure with preserved ejection fraction. We aimed to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify echocardiographically determined diastolic dysfunction and increased filling pressure. We trained, validated, and tested an AI-enabled ECG in 98,736, 21,963, and 98,763 patients, respectively, who had an ECG and echocardiographic diastolic function assessment within 14 days with no exclusion criteria. It was also tested in 55,248 patients with indeterminate diastolic function by echocardiography. The model was evaluated using the area under the curve (AUC) of the receiver operating characteristic curve, and its prognostic performance was compared to echocardiography. The AUC for detecting increased filling pressure was 0.911. The AUCs to identify diastolic dysfunction grades ≥1, ≥2, and 3 were 0.847, 0.911, and 0.943, respectively. During a median follow-up of 5.9 years, 20,223 (20.5%) died. Patients with increased filling pressure predicted by AI-ECG had higher mortality than those with normal filling pressure, after adjusting for age, sex, and comorbidities in the test group (hazard ratio (HR) 1.7, 95% CI 1.645–1.757) similar to echocardiography and in the indeterminate group (HR 1.34, 95% CI 1.298–1.383). An AI-enabled ECG identifies increased filling pressure and diastolic function grades with a good prognostic value similar to echocardiography. AI-ECG is a simple and promising tool to enhance the detection of diseases associated with diastolic dysfunction and increased diastolic filling pressure.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"We trained, validated, and tested an AI-enabled ECG in 98,736, 21,963, and 98,763 patients, respectively, who had an ECG and echocardiographic diastolic function assessment within 14 days with no exclusion criteria. It was also tested in 55,248 patients with indeterminate diastolic function by echocardiography. An AI-enabled ECG identifies increased filling pressure and diastolic function grades with a good prognostic value similar to echocardiography. AI-ECG is a simple and promising tool to enhance the detection of diseases associated with diastolic dysfunction and increased diastolic filling pressure.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"353518df-1f2b-4d04-bee5-590b7a790146","url":"https://www.nature.com/articles/s41746-023-00993-7"},"date":"2024-01-06T19:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Eunjung Lee, Saki Ito, William R. Miranda, Francisco Lopez-Jimenez, Garvan C. Kane, Samuel J. Asirvatham, Peter A. Noseworthy, Paul A. Friedman, Rickey E. Carter, Barry A. Borlaug, Zachi I. Attia & Jae K. Oh","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbk5RAAACEAC4SV","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbk5RAAACEAC4SV%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:07:52+0000","last_publication_date":"2024-09-20T17:33:22+0000","slugs":["batch-enrollment-for-an-artificial-intelligence-guided-intervention-to-lower-neurologic-events-in-patients-with-undiagnosed-atrial-fibrillation-rationale-and-design-of-a-digital-clinical-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Batch enrollment for an artificial intelligence-guided intervention to lower neurologic events in patients with undiagnosed atrial fibrillation: rationale and design of a digital clinical trial","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied to a single-lead ECG, recorded during ECG-enabled stethoscope examination, to validate a potential point-of-care screening tool for LVEF of 40% or lower.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We conducted an observational, prospective, multicentre study of a convolutional neural network (known as AI-ECG) that was previously validated for the detection of reduced LVEF using 12-lead ECG as input. We used AI-ECG retrained to interpret single-lead ECG input alone. Patients (aged ≥18 years) attending for transthoracic echocardiogram in London (UK) were recruited. All participants had 15 s of supine, single-lead ECG recorded at the four standard anatomical positions for cardiac auscultation, plus one handheld position, using an ECG-enabled stethoscope. Transthoracic echocardiogram-derived percentage LVEF was used as ground truth. The primary outcome was performance of AI-ECG at classifying reduced LVEF (LVEF ≤40%), measured using metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with two-sided 95% CIs. The primary outcome was reported for each position individually and with an optimal combination of AI-ECG outputs (interval range 0-1) from two positions using a rule-based approach and several classification models. This study is registered with ClinicalTrials.gov, NCT04601415.","spans":[{"start":1153,"end":1164,"type":"hyperlink","data":{"link_type":"Web","url":"http://clinicaltrials.gov/show/NCT04601415","target":"_blank"}}],"direction":"ltr"},{"type":"heading3","text":"Findings","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Between Feb 6 and May 27, 2021, we recruited 1050 patients (mean age 62 years [SD 17·4], 535 [51%] male, 432 [41%] non-White). 945 (90%) had an ejection fraction of at least 40%, and 105 (10%) had an ejection fraction of 40% or lower. Across all positions, ECGs were most frequently of adequate quality for AI-ECG interpretation at the pulmonary position (979 [93·3%] of 1050). Quality was lowest for the aortic position (846 [80·6%]). AI-ECG performed best at the pulmonary valve position (p=0·02), with an AUROC of 0·85 (95% CI 0·81-0·89), sensitivity of 84·8% (76·2-91·3), and specificity of 69·5% (66·4-72·6). Diagnostic odds ratios did not differ by age, sex, or non-White ethnicity. Taking the optimal combination of two positions (pulmonary and handheld positions), the rule-based approach resulted in an AUROC of 0·85 (0·81-0·89), sensitivity of 82·7% (72·7-90·2), and specificity of 79·9% (77·0-82·6). Using AI-ECG outputs from these two positions, a weighted logistic regression with l2 regularisation resulted in an AUROC of 0·91 (0·88-0·95), sensitivity of 91·9% (78·1-98·3), and specificity of 80·2% (75·5-84·3).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Interpretation","spans":[{"start":0,"end":14,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG-enabled stethoscope can detect LVEF of 40% or lower. These findings highlight the potential for inexpensive, non-invasive, workflow-adapted, point-of-care screening, for earlier diagnosis and prognostically beneficial treatment.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Funding","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"NHS Accelerated Access Collaborative, NHSX, and the National Institute for Health Research.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated an AI algorithm applied to single-lead ECGs recorded during stethoscope examinations for detecting left ventricular ejection fraction (LVEF) of 40% or lower. The AI-ECG performed best at the pulmonary valve position, achieving an AUROC of 0.85, with a sensitivity of 84.8% and specificity of 69.5%, improving to an AUROC of 0.91 with a weighted logistic regression using outputs from two positions. These findings suggest AI-ECG could serve as an inexpensive, non-invasive, point-of-care screening tool for early detection of heart failure with reduced LVEF.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"b3b2378f-3c56-467c-b1db-f778805ae82e","url":"https://pubmed.ncbi.nlm.nih.gov/34998740/"},"date":"2021-08-31T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"American Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Patrik Bachtiger, Camille F Petri, Francesca E Scott, Se Ri Park, Mihir A Kelshiker, Harpreet K Sahemey, Bianca Dumea, Regine Alquero, Pritpal S Padam, Isobel R Hatrick, Alfa Ali, Maria Ribeiro, Wing-See Cheung, Nina Bual, Bushra Rana, Matthew Shun-Shin, Daniel B Kramer, Alex Fragoyannis, Daniel Keene, Carla M Plymen, Nicholas S Peters","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZFo5thEAACMAgeOD","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZFo5thEAACMAgeOD%22%29+%5D%5D","tags":[],"first_publication_date":"2023-05-09T12:17:56+0000","last_publication_date":"2024-09-27T20:31:57+0000","slugs":["emerging-role-of-artificial-intelligence-in-cardiac-electrophysiology"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Emerging role of artificial intelligence in cardiac electrophysiology","spans":[]}],"abstract":[{"type":"heading2","text":"Key Findings","spans":[],"direction":"ltr"},{"type":"list-item","text":"Artificial Intelligence and machine learning have significantly impacted the field of cardiac electrophysiology.","spans":[],"direction":"ltr"},{"type":"list-item","text":"Application of AI to EKG, data from wearables and smart devices can provide information beyond human capabilities for risk stratification, disease screening, and detection of noncardiac conditions.","spans":[],"direction":"ltr"},{"type":"list-item","text":"AI can potentially be used to streamline workflow around remote monitoring of implantable cardiac devices, predict ICD therapies and response to CRT.","spans":[{"start":57,"end":74,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/remote-sensing","target":"_blank"}},{"start":115,"end":118,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/implantable-automatic-defibrillator","target":"_blank"}}],"direction":"ltr"},{"type":"list-item","text":"AI can be used to identify sites of successful ablation and predict response to ablative therapies.","spans":[{"start":80,"end":98,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/ablation-therapy","target":"_blank"}}],"direction":"ltr"},{"type":"list-item","text":"Personalized computation modelling provides an individualized non-invasive approach to determine targets of ablation in ventricular tachycardia and persistent AF and determine arrhythmia risk in patients with heart disease","spans":[{"start":148,"end":161,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/persistent-atrial-fibrillation","target":"_blank"}},{"start":209,"end":222,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/heart-disease","target":"_blank"}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"Artificial intelligence (AI) and machine learning (ML) have significantly impacted the field of cardiovascular medicine, especially cardiac electrophysiology (EP), on multiple fronts. The goal of this review is to familiarize readers with the field of AI and ML and their emerging role in EP. The current review is divided into 3 sections. In the first section, we discuss the definitions and basics of AI, ML, and big data. In the second section, we discuss their application to EP in the context of detection, prediction, and management of arrhythmias. Finally, we discuss the regulatory issues, challenges, and future directions of AI in EP.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"4417de67-9f4f-4174-bcaf-b7298c18bc8d","url":"https://www.sciencedirect.com/science/article/pii/S2666693622001530"},"date":"2022-09-27T18:30:00+0000","algorithm":"Electrophysiology","publishedIn":"Cardiovascular Digital Health Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Rajesh Kabra MD, FHRS, Sharat Israni PhD, Bharat Vijay MS, Chaitanya Baru PhD, Raghuveer Mendu BTech, Mark Fellman BS, Arun Sridhar MD, FHRS, Pamela Mason MD, FHRS, Jim W. Cheung MD, FHRS, Luigi DiBiase MD, PhD, FHRS, Srijoy Mahapatra MD, FHRS, Jerome Kalifa MD, PhD, Steven A. Lubitz MD, Peter A. Noseworthy MD, FHRS, Rachita Navara MD, David D. McManus MD, FHRS, Mitchell Cohen MD, Mina K. Chung MD, FHRS, Natalia Trayanova PhD, FHRS, Rakesh Gopinathannair MD, FHRS, Dhanunjaya Lakkireddy MD, FHRS","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbg4xAAACAAC3In","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbg4xAAACAAC3In%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:50:46+0000","last_publication_date":"2024-09-27T21:03:48+0000","slugs":["trastuzumab-cartiotoxicity-surveillance-by-artificial-intelligence-augmented-electrocardiography-in-a-multi-site-study"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Trastuzumab Cartiotoxicity Surveillance by Artificial Intelligence-Augmented Electrocardiography in a Multi Site Study","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Trastuzumab carries a black box warning for cardiotoxicity, and HER-2 positive breast cancer patients who are treated with trastuzumab are recommended to have an echocardiogram (TTE) every three month while on therapy and even every six months for the first two years after therapy based on the package insert. However, the need and cost-effectiveness of such practice is unclear. In the past we have shown that an artificial intelligence (AI) model can detect a low ejection fraction using 12-lead electrocardiography (ECG). The applicability of this technique for the detection of trastuzumab cardiotoxicity is unknown. ","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods ","spans":[],"direction":"ltr"},{"type":"paragraph","text":"We studied female patients (n=330) who received Trastuzumab at three Mayo Clinic campuses (Minnesota, Arizona, Florida) from 2001 and 2019 and has TTEs during or one year after Trastuzumab therapy as well as ECGs within 2 weeks of the echocardiograms. All ECGs that were recorded during and up to 1 year after Trastuzumab therapy were scored using the model and compared to echocardiography-derived ejection fraction values. ","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results ","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Overall, we had 515 TTE and ECG pairs ≤ 14 days apart or less from 330 unique patients. Of these, 24 TTEs from 18 patients showed an EF ≤ 40% and 15 TTEs from 11 patients showed an EF ≤ 35%. The AUC of the AI-ECG model for the detection of an EF ≤ 35% was 0.92 and for an EF ≤ 40% was 0.83. The sensitivity, specificity, and accuracy of the AI-ECG model to detect  an EF ≤ 40% were 79%, 77%, and 77.1%, respectively. Accordingly, using the AI-ECG algorithm for the screening of EFs ≤ 40% in trastuzumab-treated patients with a very sensitive threshold, 44% of screening TTEs could be avoided without missing a single patient. ","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion ","spans":[],"direction":"ltr"},{"type":"paragraph","text":"An AI-augmented ECG algorithm to detect an EF ≤ 40% in patients treated with trastuzumab is highly accurate. The AI ECG coupled with a smartphone may allow at home, inexpensive, self-administered long-term monitoring to enhance trastuzumab safety.","spans":[],"direction":"ltr"}],"body":[],"link":{"link_type":"Web","key":"dcb3c833-024a-445a-8c37-b8a68f946aa9","url":"https://www.jacc.org/doi/abs/10.1016/S0735-1097%2820%2931543-6"},"date":"2020-02-29T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Poster @ American College of Cardiology (ACC) 2020","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi Itzhak Attia, Suraj Kapa, Peter Noseworthy, Meir Tabi, Samuel Asirvatham, Patricia Pellikka, Gaurav Satam, Francisco Lopez-Jimemez, Paul Friedman, and Joerg Herrmann","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Zt_9EhkAAEYAWNHn","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Zt_9EhkAAEYAWNHn%22%29+%5D%5D","tags":["Low Ejection Fraction"],"first_publication_date":"2024-09-10T09:14:27+0000","last_publication_date":"2024-09-16T16:44:13+0000","slugs":["artificial-intelligenceenhanced-electrocardiography-identifies-patients-with-normal-ejection-fraction-at-riskofworse-outcomes"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence–Enhanced Electrocardiography Identifies Patients With Normal Ejection Fraction at Risk of Worse Outcomes","spans":[],"direction":"ltr"}],"abstract":[{"type":"heading2","text":"Abstract","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Background\nAn artificial intelligence (AI)-based electrocardiogram (ECG) model identifies patients with a higher likelihood of low ejection fraction (EF). Patients with an abnormal AI-ECG score but normal EF (false positives; FP) more often developed future low EF.\n\nObjective\nThe purpose of this study was to evaluate echocardiographic characteristics and all-cause mortality risk in FP patients.\n\nMethods\nPatients with transthoracic echocardiography and ECG were classified retrospectively into FP, true negatives (TN) (EF ≥50%, normal AI-ECG), true positives (TP) (EF <50%, abnormal AI-ECG), or false negatives (FN) (EF <50%, normal AI-ECG). Echocardiographic abnormalities included systolic and diastolic left ventricular function, valve disease, estimated pulmonary pressures, and right heart parameters. Cox regression was used to assess factors associated with all-cause mortality.\n\nResults\nOf 100,586 patients (median age 63 years; 45.5% females), 79% were TN, 7% FP, 5% FN, and 8% TP. FPs had more echocardiographic abnormalities than TN but less than FN or TP patients. An echocardiographic abnormality was present in 97% of FPs. Over median 2.7 years, FPs had increased mortality risk (age and sex-adjusted HR: 1.64 [95% CI: 1.55-1.73]) vs TN. Age and sex-adjusted mortality was higher in FP with abnormal echocardiography than FP with normal echocardiography and to TN regardless of echocardiography result; FP with normal echocardiography had comparable mortality risk to TN with abnormal echocardiography.\n\nConclusions\nFP patients were more likely than TNs to have echocardiographic abnormalities with 97% of exams showing an abnormality. FP patients had higher mortality rates, especially when their echocardiograms also had an abnormality; the concomitant use of AI ECG and echocardiography helps in stratifying risk in patients with normal LVEF.","spans":[{"start":0,"end":10,"type":"strong"},{"start":267,"end":276,"type":"strong"},{"start":399,"end":406,"type":"strong"},{"start":890,"end":897,"type":"strong"},{"start":1521,"end":1532,"type":"strong"}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated echocardiographic characteristics and mortality risk in patients with false positive (FP) results from an AI-based ECG model that detects low ejection fraction (EF). FP patients had more echocardiographic abnormalities than true negatives (TN), and 97% of them showed some abnormality. Over 2.7 years, FPs had a higher mortality risk compared to TNs, especially when their echocardiograms were also abnormal, highlighting the value of combining AI-ECG with echocardiography for risk stratification.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"13a072b2-ab33-4ed2-a856-7c524e445181","url":"https://www.sciencedirect.com/science/article/pii/S2772963X24004101","target":"_blank"},"date":"2024-09-27T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"ScienceDirect","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jwan A. Naser MBBS, Eunjung Lee PhD, Francisco Lopez-Jimenez MD, MBA, Peter A. Noseworthy MD, Omar S. Latif MD, Paul A. Friedman MD, Grace Lin MD, MBA, Jae K. Oh MD, Christopher G. Scott MS, Sorin V. Pislaru MD, PhD, Zachi I. Attia PhD, Patricia A. Pellikka MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbcuBAAACMAC16B","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbcuBAAACMAC16B%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:32:59+0000","last_publication_date":"2024-09-27T22:49:37+0000","slugs":["prospective-analysis-of-utility-of-signals-from-an-ecg-enabled-stethoscope-to-automatically-detect-a-low-ejection-fraction-using-neural-network-techniques-trained-from-the-standard-12-lead-ecg"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Prospective Analysis of Utility of Signals From an Ecg-Enabled Stethoscope to Automatically Detect a Low Ejection Fraction Using Neural Network Techniques Trained From the Standard 12-Lead Ecg","spans":[]}],"abstract":[{"type":"paragraph","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"ECG-enabled stethoscopes (ECG-steth) can acquire single lead ECGs during cardiac auscultation, and may facilitate real-time screening for pathologies not routinely identified during physical examination (eg, arrhythmias). We previously demonstrated an artificial intelligence (AI) algorithm applied to a 12-lead ECG (ECG-12) can identify low ejection fraction (EF) (defined as <=35%) with an accuracy of 87%. It is unknown if AI algorithms trained from ECG-12 can be applied to single lead ECGs acquired through devices such as ECG-steth.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Objective","spans":[{"start":0,"end":9,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"To demonstrate that an AI algorithm trained using ECG-12 can be applied to ECG-steth for detection of low EF.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"100 patients referred for echocardiography were included. In addition to transthoracic echocardiogram, ECG-steth with patient supine and/or sitting were obtained in standard positions where cardiac auscultation is done and via a hand-held lead I equivalent (Figure). An AI algorithm trained on 35,970 independent patients with pairs of ECG-12 and echocardiograms was retrained using a single lead from ECG-12 and validated against ECG-steth to determine accuracy for low EF detection (<=35% or <50%).","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Amongst 100 patients (age 70.6±13.8; 61% male), 7 had EF <=35% and 7 had EF 35-50%. The best single recording position was V2 with patient supine (area under the curve [AUC] 0.88 [CI:0.80-0.94] for EF<=35% and 0.81 [CI:0.72-0.88] for EF<50%). When considering best overall lead of all recordings (selected automatically), AUC was 0.906 [CI:0.831-0.955] for EF<=35%; 0.841[CI:0.754-0.906] for EF<50%. (Figure)","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"In a prospective study, an AI algorithm reliably detected low EF from single lead ECGs acquired using a novel ECG-enabled stethoscope in standard auscultation positions. The ability to identify patients with a possible low EF during routine physical examination may facilitate rapid clinical recognition of patients requiring further testing such as echocardiography.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated whether an AI algorithm trained on 12-lead ECGs (ECG-12) could be applied to single-lead ECGs obtained from ECG-enabled stethoscopes (ECG-steth) to detect low ejection fraction (EF). The algorithm was tested on 100 patients and demonstrated high accuracy, with an AUC of 0.906 for detecting EF ≤35% and 0.841 for EF <50%. The best single lead was V2 with the patient supine. The findings suggest that using AI with ECG-steth can effectively identify low EF during routine physical exams, potentially facilitating early detection and further testing.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"c05d6fdd-7a0f-4268-bb44-1bf2b6d285f5","url":"https://www.ahajournals.org/doi/abs/10.1161/circ.140.suppl_1.13447"},"date":"2019-11-11T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Abstract @ American Heart Association (AHA) 2019","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi I Attia, Jennifer Dugan, John Maidens, Adam Rideout, Francisco Lopez-Jimenez, Peter A Noseworthy, Samuel Asirvatham, Patricia A Pellikka, Dorothy J Ladewig, Gaurav Satam, Steve Pham, Subramaniam Venkatraman, Paul Friedman, and Suraj Kapa","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbkGxAAACEAC4D3","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbkGxAAACEAC4D3%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:04:30+0000","last_publication_date":"2024-09-27T20:41:47+0000","slugs":["understanding-spectrum-bias-in-algorithms-derived-by-artificial-intelligence-a-case-study-in-detecting-aortic-stenosis-using-electrocardiograms"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Understanding Spectrum Bias In Algorithms Derived By Artificial Intelligence A Case Study In Detecting Aortic Stenosis Using Electrocardiograms","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"There are an increasing number of diagnostic tests derived from artificial intelligence (AI) and machine learning algorithms. Spectrum bias can arise when a diagnostic test is derived from study populations with different disease spectra than the target population. This bias is well described studies of test performance, has not been previously evaluated in AI-derived algorithms. We used a real-world AI-derived electrocardiogram (AI-ECG) algorithm to detect severe aortic stenosis (AS) to demonstrate spectrum bias across the range of aortic value disease severity.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"All adult patients at the Mayo Clinic Minnesota, Arizona and Florida campuses between January 1st, 1989 to September 30th, 2019 with transthoracic echocardiograms within 180 days after ECG were identified. Two patient cohorts were derived based on the composition of the comparator group: a general cohort comparing severe AS to any non-severe AS and a limited cohort comparing severe AS to no AS. We developed two AI-ECG models using the two cohorts separately. Model performance was assessed by each respective holdout test group.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Overall, 258,607 patients had valid ECG and echocardiograms pairs. Using optimal decision threshold, the area under the receiver operator curve was 0.87 and 0.91 for the general and limited models respectively. Sensitivity and specificity for the general model was 80% and 81% respectively, while for the limited model it was 84% and 84% respectively. When applying the AI-ECG derived from the limited cohort to patients in the general cohort, the sensitivity, specificity and AUC were 83%, 73% and 0.86 respectively. In general, models should be applied to classification tasks that are similar to their initial training and exposure.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"While AI-ECG in both general and limited models performed robustly in identifying severe AS, there is evidence that spectrum bias may exist based on disease-severity selection. While the effect of the bias may be modest in this example, clinicians should be aware of the existence of such a bias in AI-derived algorithms and methods to ensure proper interpretation of test performance and generalizability in clinical practice.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study investigated spectrum bias in AI-derived electrocardiogram (AI-ECG) algorithms for detecting severe aortic stenosis (AS) by comparing general and limited patient cohorts. The AI-ECG models achieved an area under the curve (AUC) of 0.87 and 0.91, respectively, with sensitivities of 80% and 84% and specificities of 81% and 84%. Applying the limited cohort model to a general cohort resulted in a sensitivity of 83%, specificity of 73%, and AUC of 0.86. The findings suggest that while AI-ECG models perform well, spectrum bias based on disease severity can affect their generalizability, highlighting the need for careful interpretation of AI test performance.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"034ac085-6660-4157-bc16-763018701a14","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2904595-2"},"date":"2021-05-16T18:30:00+0000","algorithm":"Aortic Stenosis","publishedIn":"Poster @ American College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Andrew S. Tseng, Michal Shelly-Cohen, Zachi Itzhak Attia, Peter Noseworthy, Paul Friedman, and Francisco Lopez-Jimenez","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZRqmjRAAACcAxqjA","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZRqmjRAAACcAxqjA%22%29+%5D%5D","tags":[],"first_publication_date":"2023-10-02T11:18:06+0000","last_publication_date":"2024-09-20T15:53:40+0000","slugs":["machine-learning-derived-heart-and-brain-age-are-independently-associated-with-cognition"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Machine-learning-derived heart and brain age are independently associated with cognition","spans":[]}],"abstract":[{"type":"heading4","text":"Background and purpose","spans":[{"start":0,"end":22,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated.","spans":[],"direction":"ltr"},{"type":"heading4","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Using 12-lead electrocardiograms, heart age was estimated for a population-based sample (N = 7779, age 40-85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis.","spans":[],"direction":"ltr"},{"type":"heading4","text":"Results","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3-36) of the HDA effect on the tapping test score was mediated through BDA.","spans":[],"direction":"ltr"},{"type":"heading4","text":"Discussion","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Heart delta age, representing the cumulative effects of life-long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study investigated the relationship between a heart age biomarker, estimated from electrocardiograms, and cognitive function in a population-based sample of 7,779 individuals aged 40-85 years. Significant associations were found between heart delta age (HDA) and cognitive test scores, with HDA also correlating modestly with brain delta age (BDA). Mediation analysis showed that 13% of the HDA effect on tapping test scores was mediated by BDA, suggesting that HDA, reflecting lifelong exposures, is linked to both brain aging and cognitive performance.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"3a8770bc-2e7d-428f-8330-2500b57f3d60","url":"https://europepmc.org/article/med/37254942"},"date":"2023-06-12T18:30:00+0000","algorithm":"Other Programs","publishedIn":"European Journal of Neurology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Iakunchykova O, Schirmer H, Vangberg T, Wang Y, Benavente ED, van Es R, van de Leur RR, Lindekleiv H, Attia ZI, Lopez-Jimenez F, Leon DA, Wilsgaard T","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbhkBAAACEAC3VA","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbhkBAAACEAC3VA%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:53:39+0000","last_publication_date":"2024-09-27T20:42:41+0000","slugs":["detection-of-aortic-stenosis-using-an-artificial-intelligence-enabled-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Detection Of Aortic Stenosis Using An Artificial Intelligence-Enabled Electrocardiogram","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Patients with moderate to severe aortic stenosis (AS) have increased mortality even when asymptomatic. We hypothesized, that artificial intelligence - (AI) enabled electrocardiogram (ECG) - an inexpensive, ubiquitous, 10 second test - could detect patients with moderate/severe AS.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"263,570 Patients with an echocardiogram (Echo) and ECG performed within 180 days of each other were included. Patients with past cardiac surgery, or pacemaker implantation prior to the echo were excluded. We trained a convolutional neural network (CNN) to detect AS of at least moderate severity (aortic valve velocity ≥ 3 m/sec and/or area ≤ 1.5 cm2), using a 12 lead ECG. The model that achieved the highest AUC on an internal validation set was selected, and the final performance was assessed on third independent dataset.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Of the total cohort, 50% were used for training, 10% for internal validation and 40% for testing the network. Of 105,461 testing patients, 5,088 (4.8%) patients had at least moderate AS and were labeled as “positive”. The area under the receiver operating characteristic curve of the classifier was 0.85 (Fig. 1A). The overall sensitivity, specificity and accuracy were 78%, 75% and 75%, respectively. The predicted probabilities for moderate to severe AS by AI track well with AS progression determined by Echo (Fig. 1B).","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Adding AI to the 12 lead ECG can permit early detection of AS. The ECG may serve as a powerful tool to screen for asymptomatic aortic stenosis in the community.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study explored using an AI-enabled electrocardiogram (ECG) to detect moderate to severe aortic stenosis (AS). A convolutional neural network was trained on 263,570 patients to identify AS from 12-lead ECGs, achieving an area under the curve (AUC) of 0.85. The AI model showed 78% sensitivity, 75% specificity, and 75% accuracy in detecting moderate to severe AS. The results suggest that AI-enhanced ECG could be an effective tool for early screening of asymptomatic aortic stenosis in community settings.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"56a9f5d9-1127-4b9d-9236-c05a10464a37","url":"https://www.jacc.org/doi/full/10.1016/s0735-1097%2820%2932742-x"},"date":"2020-02-29T18:30:00+0000","algorithm":"Aortic Stenosis","publishedIn":"Poster @ American College of Cardiology (ACC) 2020","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Michal Shelly, Zachi Itzhak Attia, Wei-Yin Ko, Saki Ito, Benjamin Essayagh, Hector I. Michelena, Rickey Carter, Maurice Sarano, Paul Friedman, and Jae K. Oh","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuA0JRAAACYAoFae","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuA0JRAAACYAoFae%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:37:24+0000","last_publication_date":"2024-09-27T20:35:29+0000","slugs":["deep-learning-enabled-electrocardiographic-prediction-of-computer-tomography-based-high-coronary-calcium-score-cac"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Deep Learning Enabled Electrocardiographic Prediction of Computer Tomography-Based High Coronary Calcium Score (CAC)","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Coronary artery calcium (CAC) scoring is recommended in adults with unclear cardiovascular (CV) risk to inform preventative strategies and has major limitations. We developed a deep learning (DL) algorithm to predict CAC from 12-lead electrocardiograms (ECG-AI).","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Historical cohort of 43,210 consecutive patients that from 1997-2020 underwent clinically indicated CAC and ECG within 1 year. Age, sex and major modifiable CV risk factors were collected during medical visits. We excluded those on statins, paced rhythm, history of myocardial infarction or missing data. We trained a convolutional neural network based on ECG-AI output +/- CV risk factors to predict a high CAC score (≥ 300) on a random sample of 60% of the dataset, validated in 20%. We evaluated model performance with thresholds that yielded 90% sensitivity, in the remaining 20%.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Mean ± SD age 55 ± 9.8, 31% women, 1,857 (20%) had CAC ≥ 300. Algorithm's AUC of the ROC, specificity, and accuracy was 77%, 38%, 44%, for ECG-AI only; and 83%, 56%, 60% for ECG-AI + age and sex; and 83%, 57%, 61% for ECG-AI, age, sex + CV risk factors, see Figure. The ECG-AI + age and sex algorithm displayed equivalent performance when compared to the one including CV risk factors (p>0.05). Subgroup performance was constant, including those with no CV risk factors. ","spans":[{"start":258,"end":265,"type":"strong"}],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The DL-enabled ECG can help predict a high CAC score, even without information on CV risk. This algorithm could improve selection of subjects with higher likelihood of CAC.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study developed a deep learning (DL) algorithm to predict high coronary artery calcium (CAC) scores using ECG data from 43,210 patients. The algorithm, based on ECG data alone, achieved an AUC of 77%, which improved to 83% when age and sex were included. Adding cardiovascular (CV) risk factors did not significantly enhance performance. The DL-enabled ECG can effectively predict high CAC scores, potentially improving patient selection for preventative strategies.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"a47a8705-7e28-4066-92fc-0b4b2edc9af9","url":"https://www.jacc.org/doi/10.1016/S0735-1097%2821%2904624-6"},"date":"2021-05-03T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Poster @ American College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jose Medina-Inojosa, Michal Shelly, Zachi Itzhak Attia, Peter Noseworthy, Paul Friedman, Rickey Carter, and Francisco Lopez-Jimenez","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbiLxAAACAAC3gZ","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbiLxAAACAAC3gZ%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:56:18+0000","last_publication_date":"2024-09-20T17:35:34+0000","slugs":["recurrent-cryptogenic-stroke-a-potential-role-for-an-artificial-intelligence-enabled-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Recurrent cryptogenic stroke: A potential role for an artificial intelligence-enabled electrocardiogram?","spans":[]}],"abstract":[{"type":"paragraph","text":"Key Teaching Points","spans":[{"start":0,"end":19,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Many patients with cryptogenic stroke are suspected to have underlying paroxysmal atrial fibrillation (AF). However, in the absence of proven AF, anticoagulation of these patients has not been shown to prevent recurrent ischemic strokes and may result in excess bleeding compared with aspirin.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"The artificial intelligence–enabled electrocardiogram (AI-ECG) may identify patients with a particularly high likelihood of concomitant AF in the setting of sinus rhythm.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"AI-ECG may serve as an AF/atrial myopathy risk marker and could influence management of patients with cryptogenic stroke. Further study will be required to evaluate and validate the clinical utility of AI-ECG in patient care.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This case report demonstrates that AI-enabled ECGs can detect high-risk atrial fibrillation (AF) in patients with cryptogenic stroke, even when standard ECGs show sinus rhythm. Retrospective analysis revealed increasing AF risk before a patient’s recurrent strokes, which was later confirmed with atrial flutter. AI-ECG may aid in identifying undiagnosed AF and guide treatment, but further validation is needed.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"083d297b-21e8-4077-9ed9-777fc94dca09","url":"https://www.heartrhythmcasereports.com/article/S2214-0271(19)30194-0/fulltext"},"date":"2020-01-08T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"HeartRhythm Case Reports","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Anthony H. Kashou, MD, Alejandro A. Rabinstein, MD, Itzhak Zachi Attia, MS, Samuel J. Asirvatham, MD, Bernard J. Gersh, MBChB, DPhil, Paul A. Friedman, MD, Peter A. Noseworthy, MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YzcD2RMAALxVX00s","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YzcD2RMAALxVX00s%22%29+%5D%5D","tags":[],"first_publication_date":"2022-09-30T15:02:17+0000","last_publication_date":"2024-09-20T17:40:26+0000","slugs":["artificial-intelligence-guided-screening-for-atrial-fibrillation-using-electrocardiogram-during-sinus-rhythm-a-prospective-non-randomised-interventional-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence-guided screening for atrial fibrillation using electrocardiogram during sinus rhythm: a prospective non-randomised interventional trial","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Previous atrial fibrillation screening trials have highlighted the need for more targeted approaches. We did a pragmatic study to evaluate the effectiveness of an artificial intelligence (AI) algorithm-guided targeted screening approach for identifying previously unrecognised atrial fibrillation.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"For this non-randomised interventional trial, we prospectively recruited patients with stroke risk factors but with no known atrial fibrillation who had an electrocardiogram (ECG) done in routine practice. Participants wore a continuous ambulatory heart rhythm monitor for up to 30 days, with the data transmitted in near real time through a cellular connection. The AI algorithm was applied to the ECGs to divide patients into high-risk or low-risk groups. The primary outcome was newly diagnosed atrial fibrillation. In a secondary analysis, trial participants were propensity-score matched (1:1) to individuals from the eligible but unenrolled population who served as real-world controls. This study is registered with ClinicalTrials.gov, NCT04208971.","spans":[{"start":723,"end":741,"type":"hyperlink","data":{"id":"interrefs10","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}},{"start":743,"end":754,"type":"hyperlink","data":{"id":"interrefs20","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}}],"direction":"ltr"},{"type":"heading3","text":"Findings","spans":[],"direction":"ltr"},{"type":"paragraph","text":"1003 patients with a mean age of 74 years (SD 8·8) from 40 US states completed the study. Over a mean 22·3 days of continuous monitoring, atrial fibrillation was detected in six (1·6%) of 370 patients with low risk and 48 (7·6%) of 633 with high risk (odds ratio 4·98, 95% CI 2·11–11·75, p=0·0002). Compared with usual care, AI-guided screening was associated with increased detection of atrial fibrillation (high-risk group: 3·6% [95% CI 2·3–5·4] with usual care vs 10·6% [8·3–13·2] with AI-guided screening, p<0·0001; low-risk group: 0·9% vs 2·4%, p=0·12) over a median follow-up of 9·9 months (IQR 7·1–11·0).","spans":[{"start":464,"end":466,"type":"em"},{"start":541,"end":543,"type":"em"}],"direction":"ltr"},{"type":"heading3","text":"Interpretation","spans":[],"direction":"ltr"},{"type":"paragraph","text":"An AI-guided targeted screening approach that leverages existing clinical data increased the yield for atrial fibrillation detection and could improve the effectiveness of atrial fibrillation screening.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"A study evaluated an AI-guided targeted screening approach for detecting previously unrecognized atrial fibrillation (AF) among patients with stroke risk factors. The AI algorithm stratified patients into high-risk or low-risk groups, leading to significantly higher detection rates of AF in the high-risk group compared to usual care (10.6% vs 3.6%). This approach improved AF detection rates and could enhance the effectiveness of screening strategies.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"eb7841e7-9585-458e-9707-4c7f685747da","url":"https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(22)01637-3/fulltext"},"date":"2022-09-27T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"The Lancet","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Prof Peter A Noseworthy, MD, Zachi I Attia, PhD, Emma M Behnken, BA, Rachel E Giblon, MS, Katherine A Bews, BA, Sijia Liu, PhD, Tara A Gosse, MS, Zachery D Linn, MS, Yihong Deng, PhD, Jun Yin, PhD, Prof Bernard J Gersh, MBChB, DPhil, Jonathan Graff-Radford, MD, Prof Alejandro A Rabinstein, MD, Konstantinos C Siontis, MD, Prof Paul A Friedman, MD, Xiaoxi Yao, PhD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZxnenxoAAEUAyczL","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZxnenxoAAEUAyczL%22%29+%5D%5D","tags":[],"first_publication_date":"2024-10-24T05:51:22+0000","last_publication_date":"2024-10-24T05:51:22+0000","slugs":["artificial-intelligence-evaluation-of-electrocardiographic-characteristics-and-interval-changes-in-transgender-patients-on-gender-affirming-hormone-therapy"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence Evaluation of Electrocardiographic Characteristics and Interval Changes in Transgender Patients on Gender-Affirming Hormone Therapy","spans":[],"direction":"ltr"}],"abstract":[{"type":"paragraph","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Gender-affirming hormone therapy (GAHT) is used by some transgender individuals (TG), who comprise 1.4% of US population. However, the effects of GAHT on ECG remain unknown.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Objective","spans":[{"start":0,"end":9,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"To assess the effects of GAHT on ECG changes in TG.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Twelve-lead ECGs of TG on GAHT at the Mayo Clinic were inspected using a validated artificial intelligence algorithm. The algorithm assigns a patient’s ECG male pattern probability on a scale of 0 (female) to 1 (male). In the primary analysis, done separately for transgender women (TGW) and transgender men (TGM), 12-lead ECGs were used to estimate the male pattern probability before and after GAHT. In a subanalysis, only patients with both pre- & post-GAHT EGCs were included. Further, the autopopulated PR, QRS and QTc intervals were compared before and after GAHT.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Among TGW (n=86), the probability (mean ±SD) of an ECG male pattern was 0.84 ±0.25 in the pre-GAHT group, and it was lowered to 0.59 ±0.36 in the post-GAHT group (n=173, p < 7 .8 x 10-10). Conversely, among TGM, male pattern probability was 0.16 ±0.28 (n =47) in the pre-GAHT group, and it was higher at 0.41±0.38 in the post-GAHT group (n=53, p<2.4 X 10-4). The trend persisted in the subanalysis. Furthermore, both the PR (p = 5.68x10-4) and QTc intervals (p= 6.65 x10-6) prolonged among TGW. Among TGM, the QTc interval shortened (p= 4.8x10-2).","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Among TG, GAHT is associated with ECG changes trending towards gender congruence, as determined by the AI algorithm and ECG intervals. Prospective studies are warranted to understand GAHT effects on cardiac structure and function.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study assessed the effects of gender-affirming hormone therapy (GAHT) on ECG patterns in transgender individuals using an AI algorithm. Among transgender women (TGW), GAHT significantly lowered the probability of a male ECG pattern, while among transgender men (TGM), it increased the probability of a male ECG pattern. ECG intervals, including PR and QTc, were prolonged in TGW and shortened in TGM. These findings suggest that GAHT induces ECG changes consistent with gender congruence, though further research is needed to understand its impact on cardiac structure and function.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"5108576c-cfa7-4751-984b-13d3493f20a5","url":"https://www.ahajournals.org/doi/abs/10.1161/circ.140.suppl_1.13447"},"date":"2024-10-14T18:29:00+0000","algorithm":"Other Programs","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Fadi W Adel, MD, Philip Sang, MD, MS, Connor Walsh, MS, Arvind Maheshwari, MBBS, Paige Cummings, Zachi Attia, PhD, Kathryn Mangold, PhD, Caroline Davidge-Pitts, MBBCh, Francisco Lopez-Jimenez, MD, MBA, Paul Friedman, MD, Peter A Noseworthy, MD, Rekha Mankad, MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbccxAAACAAC11C","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbccxAAACAAC11C%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:31:50+0000","last_publication_date":"2024-10-25T13:04:04+0000","slugs":["screening-for-cardiac-contractile-dysfunction-using-an-artificial-intelligenceenabled-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram","spans":[]}],"abstract":[{"type":"paragraph","text":"Asymptomatic left ventricular dysfunction (ALVD) is present in 3–6% of the general population, is associated with reduced quality of life and longevity, and is treatable when found1,2,3,4. An inexpensive, noninvasive screening tool for ALVD in the doctor’s office is not available. We tested the hypothesis that application of artificial intelligence (AI) to the electrocardiogram (ECG), a routine method of measuring the heart’s electrical activity, could identify ALVD. Using paired 12-lead ECG and echocardiogram data, including the left ventricular ejection fraction (a measure of contractile function), from 44,959 patients at the Mayo Clinic, we trained a convolutional neural network to identify patients with ventricular dysfunction, defined as ejection fraction ≤35%, using the ECG data alone. When tested on an independent set of 52,870 patients, the network model yielded values for the area under the curve, sensitivity, specificity, and accuracy of 0.93, 86.3%, 85.7%, and 85.7%, respectively. In patients without ventricular dysfunction, those with a positive AI screen were at 4 times the risk (hazard ratio, 4.1; 95% confidence interval, 3.3 to 5.0) of developing future ventricular dysfunction compared with those with a negative screen. Application of AI to the ECG—a ubiquitous, low-cost test—permits the ECG to serve as a powerful screening tool in asymptomatic individuals to identify ALVD.","spans":[{"start":180,"end":181,"type":"hyperlink","data":{"id":"ref-link-section-d106511862e505","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}},{"start":182,"end":183,"type":"hyperlink","data":{"id":"ref-link-section-d106511862e505_1","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}},{"start":184,"end":185,"type":"hyperlink","data":{"id":"ref-link-section-d106511862e505_2","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}},{"start":186,"end":187,"type":"hyperlink","data":{"id":"ref-link-section-d106511862e508","type":"broken_type","tags":[],"lang":null,"slug":"-","first_publication_date":null,"last_publication_date":null,"link_type":"Document","isBroken":true}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study demonstrates that AI applied to routine ECGs can identify asymptomatic left ventricular dysfunction (ALVD) with high accuracy, achieving an AUC of 0.93, sensitivity of 86.3%, and specificity of 85.7%. In patients without current dysfunction, a positive AI screen indicated a fourfold increased risk of future ventricular dysfunction. This suggests that AI-enhanced ECGs could serve as an effective, low-cost screening tool for early detection of ALVD.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"33690664-1387-45f0-b8de-782c253b481e","url":"https://www.nature.com/articles/s41591-018-0240-2"},"date":"2019-01-07T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi I. Attia, Suraj Kapa, Francisco Lopez-Jimenez, Paul M. McKie, Dorothy J. Ladewig, Gaurav Satam, Patricia A. Pellikka, Maurice Enriquez-Sarano, Peter A. Noseworthy, Thomas M. Munger, Samuel J. Asirvatham, Christopher G. Scott, Rickey E. Carter & Paul A. Friedman","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbgmBAAACIAC3DM","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbgmBAAACIAC3DM%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:49:31+0000","last_publication_date":"2024-10-25T05:02:29+0000","slugs":["external-validation-of-a-deep-learning-electrocardiogram-algorithm-to-detect-ventricular-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction","spans":[]}],"abstract":[{"type":"heading3","text":"Objective","spans":[{"start":0,"end":9,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"To validate a novel artificial-intelligence electrocardiogram algorithm (AI-ECG) to detect left ventricular systolic dysfunction (LVSD) in an external population.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"LVSD, even when asymptomatic, confers increased morbidity and mortality. We recently derived AI-ECG to detect LVSD using ECGs based on a large sample of patients treated at the Mayo Clinic.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We performed an external validation study with subjects from the Know Your Heart Study, a cross-sectional study of adults aged 35-69 years residing in two cities in Russia, who had undergone both ECG and transthoracic echocardiography. LVSD was defined as left ventricular ejection fraction ≤ 35%. We assessed the performance of the AI-ECG to identify LVSD in this distinct patient population.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Among 4277 subjects in this external population-based validation study, 0.6% had LVSD (compared to 7.8% of the original clinical derivation study). The overall performance of the AI-ECG to detect LVSD was robust with an area under the receiver operating curve of 0.82. When using the LVSD probability cut-off of 0.256 from the original derivation study, the sensitivity, specificity, and accuracy in this population were 26.9%, 97.4%, 97.0%, respectively. Other probability cut-offs were analysed for different sensitivity values.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Conclusions","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The AI-ECG detected LVSD with robust test performance in a population that was very different from that used to develop the algorithm. Population-specific cut-offs may be necessary for clinical implementation. Differences in population characteristics, ECG and echocardiographic data quality may affect test performance.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study aimed to validate an AI-enabled electrocardiogram algorithm (AI-ECG) for detecting left ventricular systolic dysfunction (LVSD) in an external population from the Know Your Heart Study in Russia. Among 4,277 subjects, 0.6% had LVSD, compared to 7.8% in the original Mayo Clinic derivation study. The AI-ECG showed strong performance, with an area under the receiver operating curve (AUC) of 0.82. While the algorithm was accurate, population-specific cut-offs may be necessary for clinical use, as differences in population characteristics and data quality affected test sensitivity and performance.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"74883e08-2b67-422b-9062-42d455da8732","url":"https://pubmed.ncbi.nlm.nih.gov/33400971/"},"date":"2021-01-02T19:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"International Journal of Cardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Itzhak Zachi Attia, Andrew S Tseng, Ernest Diez Benavente, Jose R Medina-Inojosa, Taane G Clark, Sofia Malyutina, Suraj Kapa, Henrik Schirmer, Alexander V Kudryavtsev, Peter A Noseworthy, Rickey E Carter, Andrew Ryabikov, Pablo Perel, Paul A Friedman, David A Leon, Francisco Lopez-Jimenez","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbdGBAAACIAC2BI","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbdGBAAACIAC2BI%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:34:35+0000","last_publication_date":"2024-10-25T05:03:46+0000","slugs":["ecg-ai-guided-screening-for-low-ejection-fraction-eagle-rationale-and-design-of-a-pragmatic-cluster-randomized-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[],"direction":"ltr"},{"type":"paragraph","text":"A deep learning algorithm to detect low ejection fraction (EF) using routine 12-lead electrocardiogram (ECG) has recently been developed and validated. The algorithm was incorporated into the electronic health record (EHR) to automatically screen for low EF, encouraging clinicians to obtain a confirmatory transthoracic echocardiogram (TTE) for previously undiagnosed patients, thereby facilitating early diagnosis and treatment.","spans":[{"start":40,"end":57,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/ejection-fraction","target":"_blank"}},{"start":192,"end":216,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/nursing-and-health-professions/electronic-health-record","target":"_blank"}},{"start":321,"end":335,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/echocardiography","target":"_blank"}},{"start":400,"end":415,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/nursing-and-health-professions/early-diagnosis","target":"_blank"}}],"direction":"ltr"},{"type":"heading3","text":"Objectives","spans":[],"direction":"ltr"},{"type":"paragraph","text":"To prospectively evaluate a novel artificial intelligence (AI) screening tool for detecting low EF in primary care practices.","spans":[{"start":102,"end":114,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/nursing-and-health-professions/primary-medical-care","target":"_blank"}}],"direction":"ltr"},{"type":"heading3","text":"Design","spans":[],"direction":"ltr"},{"type":"paragraph","text":"The EAGLE trial is a pragmatic two-arm cluster randomized trial (NCT04000087) that will randomize >100 clinical teams (i.e., clusters) to either intervention (access to the new AI screening tool) or control (usual care) at 48 primary care practices across Minnesota and Wisconsin. The trial is expected to involve approximately 400 clinicians and 20,000 patients. The primary endpoint is newly discovered EF ≤50%. Eligible patients will include adults who undergo ECG for any reason and have not been previously diagnosed with low EF. Data will be pulled from the EHR, and no contact will be made with patients. A positive deviance qualitative study and a post-implementation survey will be conducted among select clinicians to identify facilitators and barriers to using the new screening report.","spans":[{"start":39,"end":63,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/cluster-randomized-trial","target":"_blank"}},{"start":65,"end":76,"type":"hyperlink","data":{"link_type":"Web","url":"https://clinicaltrials.gov/show/NCT04000087","target":"_blank"}},{"start":226,"end":238,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/medicine-and-dentistry/primary-health-care","target":"_blank"}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This trial will examine the effectiveness of the AI-enabled ECG for detection of asymptomatic low EF in routine primary care practices and will be among the first to prospectively evaluate the value of AI in real-world practice. Its findings will inform future implementation strategies for the translation of other AI-enabled algorithms.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"af820298-be99-4784-bd0b-99de38786f32","url":"https://doi.org/10.1016/j.ahj.2019.10.007"},"date":"2019-10-25T17:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"American Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Xiaoxi Yao, PhD; Rozalina G. McCoy, MD, MS; Paul A. Friedman, MD; Nilay D. Shah, PhD; Barbara A. Barry, PhD; Emma M. Behnken; Jonathan W. Inselman, MS; Zachi I. Attia, MS; Peter A. Noseworthy, MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbjRxAAACAAC30b","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbjRxAAACAAC30b%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:00:58+0000","last_publication_date":"2024-09-20T17:39:04+0000","slugs":["artificial-intelligence-enabled-electrocardiography-for-the-detection-of-cerebral-infarcts-in-patients-with-atrial-fibrillation"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence Enabled-Electrocardiography for the Detection of Cerebral Infarcts in Patients With Atrial Fibrillation","spans":[]}],"abstract":[{"type":"paragraph","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Atrial fibrillation (AF) is an established risk factor for ischemic stroke but can be paroxysmal and go undiagnosed. An artificial intelligence (AI)-enabled ECG acquired during normal sinus rhythm was recently shown to detect silent AF. The objective of this study was to determine if AI-ECG AF score is associated with the presence of cerebral infarcts.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Participants from a population-based study aged 30 to 95 years with T2 fluid attenuation inversion recovery (FLAIR) MRI obtained between October 10, 2011, and November 2, 2017 were considered for inclusion. Participants without ECG were excluded. AI-ECG score was calculated using the most recent ECG with normal sinus rhythm at the time of MRI. Presence of infarcts was determined on FLAIR MRI scans. Logistic regression was run to evaluate the relationship between AI-ECG AF score and presence of cerebral infarcts. Similar analyses were performed using history of AF rather than AI-ECG AF score as a predictor. Age and sex were included as covariates. We also examined whether a high-threshold AI-ECG score was associated with infarcts. In a prior study, an AI-ECG AF score > 0.5 was associated with a cumulative incidence of AF of 21.5% at 2 years and 52.2% at 10 years.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"This study included 1,373 individuals. Average age was 69.6 years and 53% of participants were male. There were 136 (10%) individuals with ECG-confirmed AF; 1237 (90%) participants had no AF history. Of participants with AF, 23% (n=31) were on anticoagulation, 47% (n=64) were on antiplatelet, and 18% (n=24) were on dual therapy. Only 1.3% (n=16) of patients without AF were on anticoagulation and 47% (n=578) were on antiplatelet therapy. Ischemic infarcts were detected in 214 (15.6%) patients. As a continuous measure, AI-ECG was associated with infarcts but not after adjusting for age and sex (p=0.46). AI-ECG AF score > 0.5 was associated with infarcts (p < 0.001); even after adjusting for age and sex (p=0.03). History of AF was also associated with infarcts after adjusting for age and sex (p=0.018).","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"AI-ECG AF score and history of AF were associated with the presence of cerebral infarcts after adjusting for age and sex. This tool could be useful in select patients with cryptogenic stroke but further investigation would be required.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"The study investigated whether an artificial intelligence (AI)-enabled ECG score could predict cerebral infarcts in patients with and without atrial fibrillation (AF). Results showed that an AI-ECG AF score greater than 0.5 and a history of AF were both associated with a higher likelihood of cerebral infarcts, even after adjusting for age and sex. This suggests that AI-ECG could be a valuable tool in identifying patients at risk of infarcts, particularly in those with cryptogenic stroke, though further research is needed.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"b4aba02e-9eed-4c20-aa68-93e706c8ca52","url":"https://www.ahajournals.org/doi/abs/10.1161/str.52.suppl_1.P708"},"date":"2021-03-10T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Poster Abstract @ International Stroke Conference 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Erika Weil, Peter Noseworthy, Alejandro Rabinstein, Paul Friedman, Camden Lopez, Itzhak Attia, Xiaoxi Yao, Konstantino Siontis, Walter Kremers, Georgios Christopoulos, Michelle Mielke, Prashanthi Vemuri, Clifford Jack, David Knopman, Ronald Petersen, Jonathan Graff-Radford","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbidxAAACAAC3lm","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbidxAAACAAC3lm%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:57:31+0000","last_publication_date":"2024-09-20T17:30:59+0000","slugs":["how-will-machine-learning-inform-the-clinical-care-of-atrial-fibrillation"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"How Will Machine Learning Inform the Clinical Care of Atrial Fibrillation?","spans":[]}],"abstract":[{"type":"paragraph","text":"Machine learning applications in cardiology have rapidly evolved in the past decade. With the availability of machine learning tools coupled with vast data sources, the management of atrial fibrillation (AF), a common chronic disease with significant associated morbidity and socioeconomic impact, is undergoing a knowledge and practice transformation in the increasingly complex healthcare environment. Among other advances, deep-learning machine learning methods, including convolutional neural networks, have enabled the development of AF screening pathways using the ubiquitous 12-lead ECG to detect asymptomatic paroxysmal AF in at-risk populations (such as those with cryptogenic stroke), the refinement of AF and stroke prediction schemes through comprehensive digital phenotyping using structured and unstructured data abstraction from the electronic health record or wearable monitoring technologies, and the optimization of treatment strategies, ranging from stroke prophylaxis to monitoring of antiarrhythmic drug (AAD) therapy. Although the clinical and population-wide impact of these tools continues to be elucidated, such transformative progress does not come without challenges, such as the concerns about adopting black box technologies, assessing input data quality for training such models, and the risk of perpetuating rather than alleviating health disparities. This review critically appraises the advances of machine learning related to the care of AF thus far, their potential future directions, and its potential limitations and challenges.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"Machine learning has rapidly transformed atrial fibrillation (AF) management, enabling advances like AF screening through 12-lead ECGs and optimizing treatment strategies such as stroke prevention and antiarrhythmic therapy monitoring. Deep learning methods, including convolutional neural networks, are refining AF and stroke prediction by utilizing structured and unstructured data from electronic health records and wearable technologies. However, the adoption of these tools faces challenges, including concerns over \"black box\" technologies, data quality for model training, and potential to exacerbate health disparities.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"003bbb56-1c4a-4923-9027-c860175a74b4","url":"https://doi.org/10.1161/CIRCRESAHA.120.316401"},"date":"2020-05-31T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Circulation Research","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Konstantinos C. Siontis, Xiaoxi Yao, James P. Pirruccello, Anthony A. Philippakis, Peter A. Noseworthy","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Zx_sHxoAAEQA0oPZ","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Zx_sHxoAAEQA0oPZ%22%29+%5D%5D","tags":[],"first_publication_date":"2024-10-28T19:57:20+0000","last_publication_date":"2024-10-28T19:57:20+0000","slugs":["cost-effectiveness-of-ai-enabled-electrocardiograms-for-early-detection-of-low-ejection-fraction-a-secondary-analysis-of-the-eagle-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Cost-Effectiveness of AI-Enabled Electrocardiograms for Early Detection of Low Ejection Fraction: A Secondary Analysis of the EAGLE Trial","spans":[],"direction":"ltr"}],"abstract":[{"type":"heading3","text":"Objective","spans":[],"direction":"ltr"},{"type":"paragraph","text":"To investigate the cost-effectiveness of using artificial intelligence (AI) to screen for low ejection fraction (EF) in routine clinical practice using a pragmatic randomized controlled trial (RCT).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Participants & Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"In a post-hoc analysis of the electrocardiogram (ECG) AI-Guided Screening for Low Ejection Fraction (EAGLE) trial, we developed a decision analytic model for patients 18 years and older without previously diagnosed heart failure (HF) and underwent a clinically indicated ECG between August 5, 2019 and March 31, 2020. In the previously published RCT, the intervention arm underwent an AI-guided targeted screening program for low EF with a workflow embedded into routine clinical practice – AI was applied to the ECG to identify patients at high risk and recommended clinicians to order an echocardiogram; and the control arm received usual care without the screening program. We used results from the RCT for rates of low EF diagnosis and a lifetime Markov model to project the long-term outcomes. Quality-adjusted life-years (QALY), costs of intervention and treatment, disease event costs, incremental cost-effectiveness ratio (ICER), and cost for the number needed to screen. Multiple scenario and sensitivity analyses were performed.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Compared with usual care, AI-ECG was cost-effective, with an incremental cost-effectiveness ratio of $27,858/QALY. The program remained cost-effective even with a change in patient age and follow-up time duration, although the specific ICER values varied for these parameters. The program was more cost-effective in outpatient settings (ICER $1,651/QALY) than in inpatient or emergency room settings.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Conclusion","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Implementing AI-guided targeted screening for low EF in routine clinical practice was cost-effective.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study demonstrates that AI applied to routine ECGs can identify asymptomatic left ventricular dysfunction (ALVD) with high accuracy, achieving an AUC of 0.93, sensitivity of 86.3%, and specificity of 85.7%. In patients without current dysfunction, a positive AI screen indicated a fourfold increased risk of future ventricular dysfunction. This suggests that AI-enhanced ECGs could serve as an effective, low-cost screening tool for early detection of ALVD.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"35ac2c64-d0a4-49fc-b85a-bb63137aba96","url":"https://www.mcpdigitalhealth.org/article/S2949-7612(24)00104-4/fulltext"},"date":"2024-10-25T17:29:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings: Digital Healt","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Viengneesee Thao, PhD, MS, Ye Zhu, MD, MPH, PhD, Andrew S. Tseng, MD, MPH, Jonathan W. Inselman, MS, Bijan J. Borah, PhD, Rozalina G. McCoy, MD, MS, Zachi I. Attia, PhD, Francisco Lopez-Jimenez, MD, MBA, Patricia A. Pellikka, MD, David R. Rushlow, MD, MBOE, Paul A. Friedman, MD, Peter A. Noseworthy, MD, MBA, Xiaoxi Yao, PhD, MPH, MS","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZAJg2RAAACoApMEI","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZAJg2RAAACoApMEI%22%29+%5D%5D","tags":[],"first_publication_date":"2023-03-03T21:05:07+0000","last_publication_date":"2024-09-20T17:28:02+0000","slugs":["an-artificial-intelligence-enabled-ecg-algorithm-for-the-identification-of-patients-with-atrial-fibrillation-during-sinus-rhythm-a-retrospective-analysis-of-outcome-prediction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Atrial fibrillation is frequently asymptomatic and thus underdetected but is associated with stroke, heart failure, and death. Existing screening methods require prolonged monitoring and are limited by cost and low yield. We aimed to develop a rapid, inexpensive, point-of-care means of identifying patients with atrial fibrillation using machine learning.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"We developed an artificial intelligence (AI)-enabled electrocardiograph (ECG) using a convolutional neural network to detect the electrocardiographic signature of atrial fibrillation present during normal sinus rhythm using standard 10-second, 12-lead ECGs. We included all patients aged 18 years or older with at least one digital, normal sinus rhythm, standard 10-second, 12-lead ECG acquired in the supine position at the Mayo Clinic ECG laboratory between Dec 31, 1993, and July 21, 2017, with rhythm labels validated by trained personnel under cardiologist supervision. We classified patients with at least one ECG with a rhythm of atrial fibrillation or atrial flutter as positive for atrial fibrillation. We allocated ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. We calculated the area under the curve (AUC) of the receiver operatoring characteristic curve for the internal validation dataset to select a probability threshold, which we applied to the testing dataset. We evaluated model performance on the testing dataset by calculating the AUC and the accuracy, sensitivity, specificity, and F1 score with two-sided 95% CIs.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Findings","spans":[],"direction":"ltr"},{"type":"paragraph","text":"We included 180 922 patients with 649 931 normal sinus rhythm ECGs for analysis: 454 789 ECGs recorded from 126 526 patients in the training dataset, 64 340 ECGs from 18 116 patients in the internal validation dataset, and 130 802 ECGs from 36 280 patients in the testing dataset. 3051 (8·4%) patients in the testing dataset had verified atrial fibrillation before the normal sinus rhythm ECG tested by the model. A single AI-enabled ECG identified atrial fibrillation with an AUC of 0·87 (95% CI 0·86–0·88), sensitivity of 79·0% (77·5–80·4), specificity of 79·5% (79·0–79·9), F1 score of 39·2% (38·1–40·3), and overall accuracy of 79·4% (79·0–79·9). Including all ECGs acquired during the first month of each patient's window of interest (ie, the study start date or 31 days before the first recorded atrial fibrillation ECG) increased the AUC to 0·90 (0·90–0·91), sensitivity to 82·3% (80·9–83·6), specificity to 83·4% (83·0–83·8), F1 score to 45·4% (44·2–46·5), and overall accuracy to 83·3% (83·0–83·7).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Interpretation","spans":[],"direction":"ltr"},{"type":"paragraph","text":"An AI-enabled ECG acquired during normal sinus rhythm permits identification at point of care of individuals with atrial fibrillation.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study developed an AI-enabled ECG to detect atrial fibrillation (AF) during normal sinus rhythm using 10-second, 12-lead ECGs. The model demonstrated strong performance, with an AUC of 0.87, 79.0% sensitivity, and 79.4% accuracy in identifying AF, improving to an AUC of 0.90 with additional ECGs. The findings suggest this AI-ECG could provide a rapid, cost-effective, point-of-care screening tool for detecting asymptomatic AF, potentially improving early diagnosis and intervention.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"a316ea6a-6c7a-4b0b-87cc-b9cac07c792a","url":"https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(19)31721-0/fulltext#%20"},"date":"2019-08-01T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"The Lancet","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi I Attia, Peter A Noseworthy, Francisco Lopez-Jimenez, Samuel J Asirvatham, Abhishek J Deshmukh, Bernard J Gersh, Rickey E Carter, Xiaoxi Yao, Alejandro A Rabinstein, Brad J Erickson, Suraj Kapa, Paul A Friedman","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Zt_98xkAAE4AWNNR","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Zt_98xkAAE4AWNNR%22%29+%5D%5D","tags":["Low Ejection Fraction"],"first_publication_date":"2024-09-10T09:14:26+0000","last_publication_date":"2024-09-16T16:49:12+0000","slugs":["artificial-intelligence-guided-screening-for-cardiomyopathies-in-an-obstetric-population-a-pragmatic-randomized-clinical-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence guided screening for cardiomyopathies in an obstetric population: a pragmatic randomized clinical trial","spans":[],"direction":"ltr"}],"abstract":[{"type":"paragraph","text":"Nigeria has the highest reported incidence of peripartum cardiomyopathy worldwide. This open-label, pragmatic clinical trial randomized pregnant and postpartum women to usual care or artificial intelligence (AI)-guided screening to assess its impact on the diagnosis left ventricular systolic dysfunction (LVSD) in the perinatal period. The study intervention included digital stethoscope recordings with point of-care AI predictions and a 12-lead electrocardiogram with asynchronous AI predictions for LVSD. ","spans":[],"direction":"ltr"},{"type":"paragraph","text":"The primary end point was identification of LVSD during the study period. In the intervention arm, the primary end point was defined as the number of identified participants with LVSD as determined by a positive AI screen, confirmed by echocardiography. In the control arm, this was the number of participants with clinical recognition and documentation of LVSD on echocardiography in keeping with current standard of care. Participants in the intervention arm had a confirmatory echocardiogram at baseline for AI model validation. A total of 1,232 (616 in each arm) participants were randomized and 1,195 participants (587 intervention arm and 608 control arm) completed the baseline visit at 6 hospitals in Nigeria between August 2022 and September 2023 with follow-up through May 2024. ","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Using the AI-enabled digital stethoscope, the primary study end point was met with detection of 24 out of 587 (4.1%) versus 12 out of 608 (2.0%) patients with LVSD (intervention versus control odds ratio 2.12, 95% CI 1.05–4.27; P = 0.032). With the 12-lead AI-electrocardiogram model, the primary end point was detected in 20 out of 587 (3.4%) versus 12 out of 608 (2.0%) patients (odds ratio 1.75, 95% CI 0.85–3.62; P = 0.125). A similar direction of effect was observed in prespecified subgroup analysis. There were no serious adverse events related to study participation. In pregnant and postpartum women, AI-guided screening using a digital stethoscope improved the diagnosis of pregnancy-related cardiomyopathy. ClinicalTrials.gov registration: NCT05438576","spans":[{"start":228,"end":229,"type":"em"},{"start":417,"end":418,"type":"em"},{"start":751,"end":762,"type":"hyperlink","data":{"link_type":"Web","url":"https://clinicaltrials.gov/study/NCT05438576","target":"_blank"}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study in Nigeria investigated AI-guided screening for diagnosing left ventricular systolic dysfunction (LVSD) in pregnant and postpartum women. Participants were randomized to either AI screening using digital stethoscopes and ECGs or usual care, with 3.4% in the AI group and 2.0% in the control group diagnosed with LVSD using the AI-enabled 12-lead ECG. AI-guided screening was shown to improve the detection of peripartum cardiomyopathy, with no serious adverse events reported.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"9fe424a6-ad3c-4da9-ba69-0f61d8f3fa69","url":"https://www.nature.com/articles/s41591-024-03243-9","target":"_blank"},"date":"2024-09-01T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Demilade A. Adedinsewo, Andrea Carolina Morales-Lara, Bosede B. Afolabi, Oyewole A. Kushimo, Amam C. Mbakwem, Kehinde F. Ibiyemi, James Ayodele Ogunmodede, Hadijat Olaide Raji, Sadiq H. Ringim, Abdullahi A. Habib, Sabiu M. Hamza, Okechukwu S. Ogah, Gbolahan Obajimi, Olugbenga Oluseun Saanu, Olusoji E. Jagun, Francisca O. Inofomoh, Temitope Adeolu, Kamilu M. Karaye, Sule A. Gaya, Isiaka Alfa, Cynthia Yohanna, K. L. Venkatachalam, Jennifer Dugan, Xiaoxi Yao, on behalf of the SPEC-AI Nigeria Investigators","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZRqniRAAACYAxqpf","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZRqniRAAACYAxqpf%22%29+%5D%5D","tags":[],"first_publication_date":"2023-10-02T11:21:38+0000","last_publication_date":"2024-09-16T17:38:02+0000","slugs":["abstract-42-artificial-intelligence-electrocardiogram-to-detect-coronary-calcification-and-to-predict-atherosclerotic-cardiovascular-events-in-the-community"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Abstract 42: Artificial Intelligence Electrocardiogram to Detect Coronary Calcification and to Predict Atherosclerotic Cardiovascular Events in the Community","spans":[]}],"abstract":[{"type":"paragraph","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We developed a deep learning algorithm that detects coronary artery calcium (CAC) score using 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that the output from the CAC-ECG algorithm would be associated with incident atherosclerotic cardiovascular disease (ASCVD) events and that the CAC- ECG would refine the AHA/ACC Pooled Cohort Equation’s (PCE) predictive capabilities.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A community-based cohort of consecutive patients seeking primary care in Olmsted County, MN, between 1998-2000 with passive follow-up via record linkage. Inclusion was identical to the PCE. The original CAC-ECG was developed in 43,210 subjects yielding an AUC of 0.83. Herein, we used the CAC-ECG output to predict a high CAC (≥ 300). Primary outcome was ASCVD defined as fatal and non-fatal myocardial infarction and ischemic stroke, secondary outcome was Major Adverse Cardiovascular Events (MACE) further including PCI, CABG, and mortality. Events were validated in duplicate. Cox proportional hazard models adjusted for variables included in the PCE and were stratified to evaluate the effect of the CAC-ECG on PCE-predicted risk. Follow-up was truncated at 10 years for PCE analyses.","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We included 24,793 subjects, mean ± SD age 53.9 ± 12.1, 52% women, 95% white. After 16.7±3.7 yrs follow-up, 2,366 (9.5%) had ASCVD and 3,401 (13.7%) had MACE. Risk of ASCVD and MACE increased with CAC-ECG probability quintiles, independent of risk factors, p for trend <0.001 (Fig. A-B). The CAC-ECG enhanced the predicted capabilities of the PCE across all ASCVD risk groups (Fig. C). Net reclassification improved 13.7% with comparable C-statistic from 0.77 vs. 0.78 for PCE and CAC-ECG.","spans":[{"start":257,"end":258,"type":"em"},{"start":277,"end":285,"type":"strong"},{"start":377,"end":383,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Conclusions","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"CAC-ECG was associated with ASCVD and MACE and improved PCE predicted risk. The CAC-ECG algorithm could identify individuals at risk in primary prevention; Unlike the PCE, the CAC-ECG can be applied without chart review or performing a computer tomography and may be reliably used retrospectively in cohorts with digitally stored ECGs.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"We developed a deep learning algorithm that detects coronary artery calcium (CAC) score using 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that the output from the CAC-ECG algorithm would be associated with incident atherosclerotic cardiovascular disease (ASCVD) events and that the CAC- ECG would refine the AHA/ACC Pooled Cohort Equation’s (PCE) predictive capabilities.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"d311d2cc-535a-4b81-aa24-3bb00ff3c6a5","url":"https://www.ahajournals.org/doi/abs/10.1161/circ.147.suppl_1.42"},"date":"2023-03-14T18:30:00+0000","algorithm":"ASCVD","publishedIn":"Circulation","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jose R Medina-Inojosa, Betsy J Medina-Inojosa, Zachi Attia, Michal Shelly, Abraham Baez Suarez, Paul Friedman, Rickey Carter, and Francisco Lopez-Jimenez","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbf0BAAACMAC20x","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbf0BAAACMAC20x%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:46:11+0000","last_publication_date":"2024-10-24T12:03:06+0000","slugs":["validation-of-an-artificial-intelligence-electrocardiogram-based-algorithm-for-the-detection-of-left-ventricular-systolic-dysfunction-in-subjects-with-chagas-disease"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Validation Of An Artificial Intelligence Electrocardiogram Based Algorithm For The Detection Of Left Ventricular Systolic Dysfunction In Subjects With Chagas Disease","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Chagas cardiomyopathy is a frequent and severe manifestation of Chagas disease (CD) and it is a leading cause of morbidity and death in South America. The dilated cardiomyopathy in CD is often discovered only when patients present with symptomatic heart failure. We developed an artificial intelligence electrocardiogram (AI-ECG) based algorithm for the detection of left ventricular systolic dysfunction (LVSD) using a deep convolutional neural network that may be an important tool to screen for LVSD in patients with CD, especially in limited-resource settings. In this study, we validated the AI-ECG algorithm for the first time in a sample of subjects with CD in Brazil.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We studied a sample of CD patients from the second visit of the Sami-Trop longitudinal study, NIH sponsored cohort that aims to study the natural history of Chagas cardiomyopathy in an endemic region of Brazil. Chagas cardiomyopathy was defined by the presence of major ECG abnormalities using the Minnesota code. ECGs were resampled to 500Hz and were evaluated using the algorithm; as each patient had 3 ECG recordings the average score was used for analysis. We used the area under the receiver operating curve (AUC) to evaluate the algorithm and estimated sensitivity, specificity, and accuracy for the detection of EF<=40% and EF<=35%.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We included 1,437 subjects who had an ECG and echocardiogram, 1330 with CD. 958 were female (66.7%%), the mean age was 60.6 years, 839 (58.4%) had Chagas cardiomyopathy, and 99 patients (6.9%) had EF<=40%. For the detection of EF<=40%, the AI-ECG had an AUC of 0.813, with sensitivity 83.8%, specificity 54.3%, and a negative predictive value of 97.8% using the originally calculated threshold. The sensitivity was 72.7%, specificity 78.9%, negative predictive value 97.5%, positive predictive value 13%, and accuracy 77.3 using an optimal threshold based on the ROC. The AUC was 0.818 for detection of ejection fraction <=35% and 0.805 for the detection of EF<50%.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The AI-augmented ECG can facilitate the screening and monitoring of patients with Chagas disease for early detection of LVSD to enable early treatment and to optimize the use of other resources like echocardiography.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study validated an AI-ECG algorithm for detecting left ventricular systolic dysfunction (LVSD) in patients with Chagas disease (CD) in Brazil. Among 1,437 subjects, including 1,330 with CD, the AI algorithm showed good performance, with an AUC of 0.813 for detecting ejection fraction (EF) ≤40%. The sensitivity was 83.8%, and the negative predictive value was high at 97.8%. The algorithm also performed well for detecting EF ≤35%, with an AUC of 0.818. These findings suggest the AI-ECG can be a valuable tool for early screening of LVSD in CD patients, particularly in resource-limited settings.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"c47e2df7-8637-45c9-903f-eb0dc6040d76","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2904608-8"},"date":"2021-04-30T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Poster @ American College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv5qxIAACEAq34Y","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv5qxIAACEAq34Y%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:14:10+0000","last_publication_date":"2024-09-27T20:30:28+0000","slugs":["rapid-exclusion-of-covid-infection-with-the-artificial-intelligence-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Rapid Exclusion of COVID Infection With the Artificial Intelligence Electrocardiogram","spans":[]}],"abstract":[{"type":"heading3","text":"Objective","spans":[],"direction":"ltr"},{"type":"paragraph","text":"To rapidly exclude severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection using artificial intelligence applied to the electrocardiogram (ECG).","spans":[{"start":19,"end":64,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/pharmacology-toxicology-and-pharmaceutical-science/sars-coronavirus","target":"_blank"}}],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"A global, volunteer consortium from 4 continents identified patients with ECGs obtained around the time of polymerase chain reaction–confirmed COVID-19 diagnosis and age- and sex-matched controls from the same sites. Clinical characteristics, polymerase chain reaction results, and raw electrocardiographic data were collected. A convolutional neural network was trained using 26,153 ECGs (33.2% COVID positive), validated with 3826 ECGs (33.3% positive), and tested on 7870 ECGs not included in other sets (32.7% positive). Performance under different prevalence values was tested by adding control ECGs from a single high-volume site.","spans":[{"start":243,"end":268,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/biochemistry-genetics-and-molecular-biology/polymerase-chain-reaction","target":"_blank"}}],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[],"direction":"ltr"},{"type":"paragraph","text":"The area under the curve for detection of acute COVID-19 infection in the test group was 0.767 (95% CI, 0.756 to 0.778; sensitivity, 98%; specificity, 10%; positive predictive value, 37%; negative predictive value, 91%). To more accurately reflect a real-world population, 50,905 normal controls were added to adjust the COVID prevalence to approximately 5% (2657/58,555), resulting in an area under the curve of 0.780 (95% CI, 0.771 to 0.790) with a specificity of 12.1% and a negative predictive value of 99.2%.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Conclusion","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Infection with SARS-CoV-2 results in electrocardiographic changes that permit the artificial intelligence–enhanced ECG to be used as a rapid screening test with a high negative predictive value (99.2%). This may permit the development of electrocardiography-based tools to rapidly screen individuals for pandemic control.","spans":[{"start":141,"end":155,"type":"hyperlink","data":{"link_type":"Web","url":"https://www.sciencedirect.com/topics/biochemistry-genetics-and-molecular-biology/screening-test","target":"_blank"}}],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study aimed to rapidly exclude SARS-CoV-2 infection using artificial intelligence applied to electrocardiograms (ECGs). A convolutional neural network was trained on ECG data from COVID-19 positive patients and matched controls, yielding an area under the curve (AUC) of 0.767 in the test group. When adjusted to a real-world prevalence of 5%, the model's AUC improved to 0.780, with a high negative predictive value (99.2%). These results suggest that AI-enhanced ECGs can be used as a rapid screening tool for COVID-19 with strong potential for pandemic control.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"38a506c4-526f-4db9-895b-6dbb49822522","url":"https://www.sciencedirect.com/science/article/pii/S0025619621004699"},"date":"2021-08-01T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Zachi I. Attia PhD, Suraj Kapa MD, Jennifer Dugan BA, Naveen Pereira MD, Peter A. Noseworthy MD, Francisco Lopez Jimenez MD, Jessica Cruz MBA, Rickey E. Carter PhD, Daniel C. DeSimone MD, John Signorino MHSA, John Halamka MD, Nikhita R. Chennaiah Gari MBBS, Raja Sekhar Madathala MBBS, Pyotr G. Platonov MD, Fahad Gul MD, Stefan P. Janssens MD, Sanjiv Narayan MD, Gaurav A. Upadhyay MD, Francis J. Alenghat MD, Marc K. Lahiri MD, Paul A. Friedman MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZRqksBAAACgAxqXM","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZRqksBAAACgAxqXM%22%29+%5D%5D","tags":[],"first_publication_date":"2023-10-02T11:15:51+0000","last_publication_date":"2024-09-20T16:31:09+0000","slugs":["patient-level-artificial-intelligenceenhanced-electrocardiography-in-hypertrophic-cardiomyopathylongitudinal-treatment-and-clinical-biomarker-correlations"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Patient-Level Artificial Intelligence–Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations","spans":[]}],"abstract":[{"type":"heading3","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Artificial intelligence (AI) applied to 12-lead electrocardiographs (ECGs) can detect hypertrophic cardiomyopathy (HCM).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Objectives","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"The purpose of this study was to determine if AI-enhanced ECG (AI-ECG) can track longitudinal therapeutic response and changes in cardiac structure, function, or hemodynamics in obstructive HCM during mavacamten treatment.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We applied 2 independently developed AI-ECG algorithms (University of California-San Francisco and Mayo Clinic) to serial ECGs (n = 216) from the phase 2 PIONEER-OLE trial of mavacamten for symptomatic obstructive HCM (n = 13 patients, mean age 57.8 years, 69.2% male). Control ECGs from 2,600 age- and sex-matched individuals without HCM were obtained. AI-ECG output was correlated longitudinally to echocardiographic and laboratory metrics of mavacamten treatment response.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"In the validation cohorts, both algorithms exhibited similar performance for HCM diagnosis, and exhibited mean HCM score decreases during mavacamten treatment: patient-level score reduction ranged from approximately 0.80 to 0.45 for Mayo and 0.70 to 0.35 for USCF algorithms; 11 of 13 patients demonstrated absolute score reduction from start to end of follow-up for both algorithms. HCM scores were significantly associated with other HCM-relevant parameters, including left ventricular outflow tract gradient at rest, postexercise, and with Valsalva, and NT-proBNP level, independent of age and sex (all P < 0.01). For both algorithms, the strongest longitudinal correlation was between AI-ECG HCM score and left ventricular outflow tract gradient postexercise (slope estimate: University of California-San Francisco 0.70 [95% CI: 0.45-0.96], P < 0.0001; Mayo 0.40 [95% CI: 0.11-0.68], P = 0.007).","spans":[{"start":606,"end":607,"type":"em"},{"start":845,"end":846,"type":"em"},{"start":888,"end":889,"type":"em"}],"direction":"ltr"},{"type":"heading3","text":"Conclusions","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"AI-ECG analysis longitudinally correlated with changes in echocardiographic and laboratory markers during mavacamten treatment in obstructive HCM. These results provide early evidence for a potential paradigm for monitoring HCM therapeutic response.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated the ability of AI-enhanced ECG (AI-ECG) to track therapeutic response and cardiac changes in patients with obstructive hypertrophic cardiomyopathy (HCM) during mavacamten treatment. Both AI-ECG algorithms (from UCSF and Mayo Clinic) showed significant reductions in HCM scores and were strongly correlated with echocardiographic and laboratory markers, particularly left ventricular outflow tract gradient postexercise. The findings suggest AI-ECG could be a promising tool for monitoring treatment response in HCM.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"147755cc-55e0-4228-a2b0-9c995e1f70a6","url":"https://www.jacc.org/doi/full/10.1016/j.jacadv.2023.100582"},"date":"2023-10-02T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"JACC","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Konstantinos C. Siontis, Sean Abreau, Zachi I. Attia, Joshua P. Barrios, Thomas A. Dewland, Priyanka Agarwal, Aarthi Balasubramanyam, Yunfan Li, Steven J. Lester, Ahmad Masri, Andrew Wang, Amy J. Sehnert, Jay M. Edelberg, Theodore P. Abraham, Paul A. Friedman, Jeffrey E. Olgin, Peter A. Noseworthy, and Geoffrey H. Tison","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbhVRAAACMAC3Qz","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbhVRAAACMAC3Qz%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:52:40+0000","last_publication_date":"2024-09-27T20:33:55+0000","slugs":["an-automated-screening-algorithm-using-electrocardiograms-for-pulmonary-hypertension"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"An Automated Screening Algorithm Using Electrocardiograms for Pulmonary Hypertension","spans":[]}],"abstract":[{"type":"paragraph","text":"Pulmonary hypertension (PH) is a life-threatening disease that is typically detected after significant pulmonary vascular remodeling has occurred. Longer diagnostic delays are associated with higher mortality and there is a need for a simple, fast, non-invasive PH screening tool. Currently, electrocardiograms often only identify abnormalities in severe PH. However, deep learning-based algorithms may enable detection of early, subtle, disease-specific changes, and could allow this inexpensive and ubiquitous test to serve as a powerful screening tool for PH. We used convolutional neural networks (CNN) to develop an algorithm for PH using retrospective electrocardiogram voltage-time data from Mayo Clinic. Each standard 12-lead electrocardiogram was paired with right heart catheterization to define patients as PH or non-PH, and the non- PH group was supplemented with patients in whom PH was excluded by echocardiogram. PH was defined as mean pulmonary arterial pressure (mPAP) ≥25 mmHg (at rest or during drug or exercise challenge), and non-PH was defined as mPAP <21 mmHg or tricuspid regurgitation velocity ≤2.8 m/s, if mPAP was not available. All patients were then randomly partitioned into training (48%), validation (12%) and test sets (40%) for building, optimizing and testing the models, respectively. Models were trained using electrocardiograms performed within 1 month of PH diagnosis (diagnostic dataset) and performance was tested on the diagnostic dataset and on electrocardiograms from 6-18 months (pre-emptive dataset) and 36-60 months before diagnosis. Model performance was evaluated by calculating the area under the curve (AUC) of the receiver operating characteristic curve, sensitivity, specificity, and diagnostic odds ratios. In total, 56,612 unique patients were identified: 11,138 PH and 45,474 non-PH patients. Several model structures were tested, and the best performing were CNNs with residual connections incorporating the 12-lead voltage-time electrocardiogram data. The final model yielded an AUC, sensitivity and specificity, respectively, of 0.91, 83.5%, and 83.6% in the diagnostic test set and 0.86, 77.8% and 78.3% in the pre-emptive dataset (Table). AUC remained above 0.81 for detection of PH using electrocardiograms from 6-monthly intervals up to 5 years before diagnosis. Among the PH patients, 2,134 patients had pre-capillary PH, which includes some progressive but potentially treatable forms of PH, and AUC was 0.95 for detection of PH in this diagnostic dataset. The electrocardiogram algorithm was able to detect PH up to 5 years prior to diagnosis. This type of algorithm has the potential to accelerate diagnosis and management of PH.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"A deep learning algorithm using ECG data was developed to detect pulmonary hypertension (PH) earlier. Trained on data from 56,612 patients, the model achieved an AUC of 0.91 with 83.5% sensitivity and 83.6% specificity for PH detection near diagnosis. It also maintained strong performance (AUC 0.86) for ECGs taken up to 5 years prior, showing potential for earlier PH diagnosis and improved outcomes.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"45fae4a4-bebf-4450-a24e-abd85e542f47","url":"https://www.atsjournals.org/doi/pdf/10.1164/ajrccm-conference.2021.203.1_MeetingAbstracts.A1179"},"date":"2020-10-31T18:30:00+0000","algorithm":"Pulmonary Hypertension","publishedIn":"American Thoracic Society (ATS) 2021 International Conference","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"H.M. Dubrock, T. Wagner, Z.I. Attia, S.J. Asirvatham, S. Awasthi, M. Babu, R. Barve, K. Carlson, C.L. Carpenter, R.P. Frantz, P.A. Friedman, A. Prasad, C. Chehoud, E. Kogan, A. Nnewihe, D. Quinn, C. Bridges, S. Kapa, V. Soundararajan","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtfLDBAAACIAD4UF","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtfLDBAAACIAD4UF%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-20T09:29:51+0000","last_publication_date":"2024-09-27T20:45:11+0000","slugs":["detection-of-hypertrophic-cardiomyopathy-by-artificial-intelligence-enabled-electrocardiography-in-children-and-adolescents"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Detection Of Hypertrophic Cardiomyopathy By Artificial Intelligence-Enabled Electrocardiography In Children And Adolescents","spans":[]}],"abstract":[{"type":"heading2","text":"Background","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"Hypertrophic cardiomyopathy (HCM) is a cause of morbidity and sudden cardiac death in children and adolescents. There is currently no established screening approach for HCM. We recently developed an artificial intelligence (AI) convolutional neural network (CNN) for the detection of HCM based on the 12-lead electrocardiogram (ECG) in an adult population. We aimed to validate this approach of ECG-based HCM detection in pediatric patients.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Methods","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We identified a cohort of children and adolescents with HCM who had an ECG and echocardiogram at our institution. These patients were age and sex-matched to a control population without HCM. Diagnostic performance of the AI-ECG model for the detection of HCM was estimated using the previously identified optimal diagnostic threshold of 11% (the probability output derived by the AI-ECG model above which an ECG is considered to belong to an HCM patient).","spans":[],"direction":"ltr"},{"type":"heading2","text":"Results","spans":[{"start":0,"end":7,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We included 318 HCM patients (mean age 12±4.8 years, male 68%) and 22,996 age- and sex-matched non-HCM controls. AI-ECG probability for HCM was >11% in 91% of cases and 3% of controls. The AUC of the AI-ECG model for HCM detection was 0.98 (95% CI 0.97-0.99) with corresponding sensitivity 97% and specificity 91%. The model performed similarly in subgroups defined by gender and HCM genotype status. Model performance was best in the oldest subgroup (15-18 years) in both males and females.","spans":[],"direction":"ltr"},{"type":"heading2","text":"Conclusion","spans":[{"start":0,"end":10,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12-lead ECG.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study validated an AI convolutional neural network for detecting hypertrophic cardiomyopathy (HCM) in pediatric patients using 12-lead ECGs. The model, previously developed for adults, showed high performance in a cohort of 318 HCM patients and 22,996 controls, achieving an AUC of 0.98 with 97% sensitivity and 91% specificity. The AI-ECG detected HCM with 91% probability in affected cases and 3% in controls. The model was particularly effective in older adolescents (15-18 years), demonstrating strong potential for HCM screening in children and adolescents.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"6791789b-2984-4baf-ba82-8b630ac7930b","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2904601-5"},"date":"2021-04-30T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Poster @ Americal College of Cardiology (ACC) 2021","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Konstantinos Siontis, Kan Liu, J. Martijn Bos, Zachi Itzhak Attia, Adelaide Arruda-Olson, Nasibeh Z. Farahani, Paul Friedman, Peter Noseworthy, and Michael Ackerman","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbiuBAAACAAC3qL","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbiuBAAACAAC3qL%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:58:35+0000","last_publication_date":"2024-09-20T17:29:37+0000","slugs":["artificial-intelligenceelectrocardiography-to-predict-incident-atrial-fibrillation"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence–Electrocardiography to Predict Incident Atrial Fibrillation","spans":[]}],"abstract":[{"type":"heading3","text":"Background:","spans":[{"start":0,"end":11,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"An artificial intelligence (AI) algorithm applied to electrocardiography during sinus rhythm has recently been shown to detect concurrent episodic atrial fibrillation (AF). We sought to characterize the value of AI–enabled electrocardiography (AI-ECG) as a predictor of future AF and assess its performance compared with the CHARGE-AF score (Cohorts for Aging and Research in Genomic Epidemiology–AF) in a population-based sample.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods:","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"We calculated the probability of AF using AI-ECG, among participants in the population-based Mayo Clinic Study of Aging who had no history of AF at the time of the baseline study visit. Cox proportional hazards models were fit to assess the independent prognostic value and interaction between AI-ECG AF model output and CHARGE-AF score. C statistics were calculated for AI-ECG AF model output, CHARGE-AF score, and combined AI-ECG and CHARGE-AF score.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results:","spans":[{"start":0,"end":8,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"A total of 1936 participants with median age 75.8 (interquartile range, 70.4–81.8) years and median CHARGE-AF score 14.0 (IQR, 13.2–14.7) were included in the analysis. Participants with AI-ECG AF model output of >0.5 at the baseline visit had cumulative incidence of AF 21.5% at 2 years and 52.2% at 10 years. When included in the same model, both AI-ECG AF model output (hazard ratio, 1.76 per SD after logit transformation [95% CI, 1.51–2.04]) and CHARGE-AF score (hazard ratio, 1.90 per SD [95% CI, 1.58–2.28]) independently predicted future AF without significant interaction (P=0.54). C statistics were 0.69 (95% CI, 0.66–0.72) for AI-ECG AF model output, 0.69 (95% CI, 0.66–0.71) for CHARGE-AF, and 0.72 (95% CI, 0.69–0.75) for combined AI-ECG and CHARGE-AF score.","spans":[{"start":582,"end":583,"type":"em"}],"direction":"ltr"},{"type":"heading3","text":"Conclusions:","spans":[{"start":0,"end":12,"type":"strong"}],"direction":"ltr"},{"type":"paragraph","text":"In the present study, both the AI-ECG AF model output and CHARGE-AF score independently predicted incident AF. The AI-ECG may offer a means to assess risk with a single test and without requiring manual or automated clinical data abstraction.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study evaluated the predictive value of an AI-enabled ECG algorithm for future atrial fibrillation (AF) in a population-based sample, comparing it to the CHARGE-AF score. Both AI-ECG and CHARGE-AF independently predicted AF, with participants showing a 21.5% cumulative AF incidence at 2 years and 52.2% at 10 years when AI-ECG output exceeded 0.5. The combined AI-ECG and CHARGE-AF score improved predictive accuracy, suggesting AI-ECG could serve as a quick, single-test method for assessing AF risk.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"c160abaa-e467-43ca-a36c-024ab07a4114","url":"https://doi.org/10.1161/CIRCEP.120.009355"},"date":"2020-11-12T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Circulation: Arrhythmia and Electrophysiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Georgios Christopoulos, MD, Jonathan Graff-Radford, MD, Camden L. Lopez, MS, Xiaoxi Yao, PhD, Zachi I. Attia, PhD, Alejandro A. Rabinstein, MD, Ronald C. Petersen, MD, PhD, David S. Knopman, MD, Michelle M. Mielke, PhD, Walter Kremers, PhD, Prashanthi Vemuri, PhD, Konstantinos C. Siontis, MD, Paul A. Friedman, MD, Peter A. Noseworthy, MD","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZuAK9BkAAE4AWOei","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZuAK9BkAAE4AWOei%22%29+%5D%5D","tags":[],"first_publication_date":"2024-09-10T09:14:26+0000","last_publication_date":"2024-09-16T17:34:44+0000","slugs":["predictors-of-mortality-by-an-artificial-intelligence-enhanced-electrocardiogram-model-for-cardiac-amyloidosis"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Predictors of mortality by an artificial intelligence enhanced electrocardiogram model for cardiac amyloidosis","spans":[],"direction":"ltr"}],"abstract":[{"type":"heading3","text":"Aims","spans":[],"direction":"ltr"},{"type":"paragraph","text":"We aim to determine if our previously validated, diagnostic artificial intelligence (AI) electrocardiogram (ECG) model is prognostic for survival among patients with cardiac amyloidosis (CA).","spans":[],"direction":"ltr"},{"type":"heading3","text":"Methods","spans":[],"direction":"ltr"},{"type":"paragraph","text":"A total of 2533 patients with CA (1834 with light chain amyloidosis (AL), 530 with wild-type transthyretin amyloid protein (ATTRwt) and 169 with hereditary transthyretin amyloid (ATTRv)] were included. An amyloid AI ECG (A2E) score was calculated for each patient reflecting the likelihood of CA. CA stage was calculated using the European modification of the Mayo 2004 criteria for AL and Mayo stage for transthyretin amyloid (ATTR). Risk of death was modelled using Cox proportional hazards, and Kaplan–Meier was used to estimate survival.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Results","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Median age of the cohort was 67 [inter-quartile ratio (IQR) 59, 74], and 71.6% were male. The median overall survival for the cohort was 35.6 months [95% confidence interval (CI) 32.3, 39.5]. For AL, ATTRwt and ATTRv, respectively, median survival was 22.9 (95% CI 19.2, 28.2), 47.2 (95% CI 43.4, 52.3) and 61.4 (95% CI 48.7, 75.9) months. On univariate analysis, an increasing A2E score was associated with more than a two-fold risk of all-cause death. On multivariable analysis, the A2E score retained its importance with a risk ratio of 2.0 (95% CI 1.58, 2.55) in the AL group and 2.7 (95% CI 1.81, 4.24) in the ATTR group.","spans":[],"direction":"ltr"},{"type":"heading3","text":"Conclusions","spans":[],"direction":"ltr"},{"type":"paragraph","text":"Among patients with AL and ATTR amyloidosis, the A2E model helps to stratify risk of CA and adds another dimension of prognostication.","spans":[],"direction":"ltr"}],"body":[{"type":"paragraph","text":"This study aimed to assess if a previously validated AI-enhanced ECG model (A2E) could predict survival in patients with cardiac amyloidosis (CA). Among 2,533 patients with different types of CA, the A2E score was significantly associated with increased risk of death, with a more than two-fold risk in both light chain amyloidosis (AL) and transthyretin amyloidosis (ATTR) groups. The A2E model proved valuable for risk stratification and prognostication in CA patients, supplementing existing staging systems.","spans":[],"direction":"ltr"}],"link":{"link_type":"Web","key":"cf1710fd-7ed8-4c75-bfbf-5a1be5bec526","url":"https://onlinelibrary.wiley.com/doi/10.1002/ehf2.15061","target":"_blank"},"date":"2024-08-30T18:30:00+0000","algorithm":"Cardiac Amyloidosis","publishedIn":"Wiley Online Library","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":"Jennifer M. Amadio, Martha Grogan, Eli Muchtar, Francisco Lopez-Jimenez, Zachi I. Attia, Omar AbouEzzeddine, Grace Lin, Surendra Dasari, Suraj Kapa, Daniel D. Borgeson, Paul A. Friedman, Morie A. Gertz, Dennis H. Murphree Jr, Angela Dispenzieri","authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y3J6DRQAACUA3rDI","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y3J6DRQAACUA3rDI%22%29+%5D%5D","tags":[],"first_publication_date":"2022-11-14T17:26:19+0000","last_publication_date":"2022-11-14T17:26:19+0000","slugs":["prospective-evaluation-of-smartwatch-enabled-detection-of-left-ventricular-dysfunction","clinician-adoption-of-an-artificial-intelligence-algorithm-to-detect-left-ventricular-systolic-dysfunction-in-primary-care."],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Prospective evaluation of smartwatch-enabled detection of left ventricular dysfunction","spans":[]}],"abstract":[{"type":"paragraph","text":"Although artificial intelligence (AI) algorithms have been shown to be capable of identifying cardiac dysfunction, defined as ejection fraction (EF) ≤ 40%, from 12-lead electrocardiograms (ECGs), identification of cardiac dysfunction using the single-lead ECG of a smartwatch has yet to be tested. In the present study, a prospective study in which patients of Mayo Clinic were invited by email to download a Mayo Clinic iPhone application that sends watch ECGs to a secure data platform, we examined patient engagement with the study app and the diagnostic utility of the ECGs. The AI algorithm detected patients with low EF with an area under the curve of 0.885 (95% confidence interval 0.823–0.946) and 0.881 (0.815–0.947), using the mean prediction within a 30-d window or the closest ECG relative to the echocardiogram that determined the EF, respectively. These findings indicate that consumer watch ECGs, acquired in nonclinical environments, can be used to identify patients with cardiac dysfunction, a potentially life-threatening and often asymptomatic condition.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"01a9c237-8db3-48d3-8b09-50c24ee561ce","url":"https://www.nature.com/articles/s41591-022-02053-1"},"date":"2022-11-14T19:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y_TvORAAACUAPZXf","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y_TvORAAACUAPZXf%22%29+%5D%5D","tags":[],"first_publication_date":"2023-02-21T16:21:45+0000","last_publication_date":"2023-02-21T16:21:45+0000","slugs":["physiological-age-by-artificial-intelligenceenhanced-electrocardiograms-as-a-novel-risk-factor-of-mortality-in-kidney-transplant-candidates","digitizing-paper-based-ecg-files-to-foster-deep-learning-based-analysis-of-existing-clinical-datasets-an-exploratory-analysis"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Physiological Age by Artificial Intelligence–Enhanced Electrocardiograms as a Novel Risk Factor of Mortality in Kidney Transplant Candidates","spans":[]}],"abstract":[{"type":"paragraph","text":"Mortality risk assessment before kidney transplantation (KT) is imperfect. An emerging risk factor for death in nontransplant populations is physiological age as determined by the application of artificial intelligence to the electrocardiogram (ECG). The aim of this study was to examine the relationship between ECG age and KT waitlist mortality. We applied a previously developed convolutional neural network to the ECGs of KT candidates evaluated 2014 to 2019 to determine ECG age. We used a Cox proportional hazard model to examine whether ECG age was associated with waitlist mortality. In this study, we found that ECG age is a risk factor for KT waitlist mortality. Determining ECG age through artificial intelligence may help guide risk-benefit assessment when evaluating candidates for KT. ","spans":[]}],"body":[],"link":{"link_type":"Web","key":"f48f13a4-bf16-4115-8bc3-202ded30d641","url":"https://journals.lww.com/transplantjournal/Fulltext/9900/Physiological_Age_by_Artificial.333.aspx"},"date":"2023-02-13T19:30:00+0000","algorithm":"Other Programs","publishedIn":"Transplantation","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y3ZStRAAACgAuFa6","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y3ZStRAAACgAuFa6%22%29+%5D%5D","tags":[],"first_publication_date":"2022-11-17T15:27:38+0000","last_publication_date":"2022-11-17T15:45:17+0000","slugs":["community-based-participatory-research-application-of-an-artificial-intelligence-enhanced-electrocardiogram-for-cardiovascular-disease-screening-a-faith-trial-ancillary-study","prospective-evaluation-of-smartwatch-enabled-detection-of-left-ventricular-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Community-based participatory research application of an artificial intelligence-enhanced electrocardiogram for cardiovascular disease screening: A FAITH! Trial ancillary study","spans":[]}],"abstract":[{"type":"paragraph","text":"We conducted this study to evaluate the potential utility of an AI-based cardiovascular diseases (CVD) screening tool in an under-resourced African-American cohort, we reviewed the AI-enhanced electrocardiogram (ECG) data of participants enrolled in a community-based clinical trial as a proof-of-concept ancillary study for community-based screening. The AI-ECG for decreased LVEF demonstrated excellent performance with an AUC of 0.892 (95% confidence interval [CI] 0.708-1); sensitivity=50% (95% CI 9.5-90.5%; n=1/2) and specificity=96% (95% CI 86.8-98.9%; n=49/51). This novel, community-centric delivery of AI could provide valuable screening resources and appropriate referrals for early detection of highly-morbid CVD for under-resourced patient populations.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"bee921ce-9197-44f8-aaba-4984b4171880","url":"https://www.sciencedirect.com/science/article/pii/S2666667722001155"},"date":"2022-11-13T19:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"American Journal of Preventive Cardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y5eOqxcAACgAeDmY","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y5eOqxcAACgAeDmY%22%29+%5D%5D","tags":[],"first_publication_date":"2022-12-12T20:28:49+0000","last_publication_date":"2022-12-12T20:28:49+0000","slugs":["digitizing-paper-based-ecg-files-to-foster-deep-learning-based-analysis-of-existing-clinical-datasets-an-exploratory-analysis","tandem-deep-learning-and-logistic-regression-models-to-optimize-hypertrophic-cardiomyopathy-detection-in-routine-clinical-practice"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Digitizing paper based ECG files to foster deep learning based analysis of existing clinical datasets: An exploratory analysis","spans":[]}],"abstract":[{"type":"paragraph","text":"Recently, we developed and validated a deep learning model for detecting left ventricular dysfunction based on a standard 12-lead ECG. However, this model largely depends on the availability of digital ECG data: 10s for all 12 leads sampled at 500 Hz stored as a numeric array. This limits the ability to validate or scale this technology to institutions that store ECGs as PDF or image files (“paper” ECGs). Methods do exist to create digital signals from the archived paper copies of the ECGs. The primary objective of this study was to evaluate how well the AI-ECG model output obtained using digitized paper ECGs agreed with the predictions from the native digital ECGs for the detection of low ejection fraction. Our study demonstrates an agreement between deep learning model predictions obtained from digitized paper-based ECGs and native digital ECGs and provides some insight into potential expandability of ECG-based deep learning models including the importance of captured duration (10-s vs. 2-5-s recordings) and ECG vectors (precordial leads vs. limb leads).","spans":[]}],"body":[],"link":{"link_type":"Web","key":"ad32a233-5bc2-400f-804e-887bb2ce1ef0","url":"https://www.sciencedirect.com/science/article/pii/S2666521222000230"},"date":"2022-08-08T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Intelligence-Based Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv8KBIAACAAq4mo","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv8KBIAACAAq4mo%22%29+%5D%5D","tags":[],"first_publication_date":"2023-03-08T15:59:34+0000","last_publication_date":"2023-03-08T15:59:34+0000","slugs":["artificial-intelligence-enhanced-electrocardiography-in-cardiovascular-disease-management"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","spans":[]}],"abstract":[{"type":"paragraph","text":"The application of artificial intelligence (AI) to the electrocardiogram (ECG), a ubiquitous and standardized test, is an example of the ongoing transformative effect of AI on cardiovascular medicine. Although the ECG has long offered valuable insights into cardiac and non-cardiac health and disease, its interpretation requires considerable human expertise. Advanced AI methods, such as deep-learning convolutional neural networks, have enabled rapid, human-like interpretation of the ECG, while signals and patterns largely unrecognizable to human interpreters can be detected by multilayer AI networks with precision, making the ECG a powerful, non-invasive biomarker. Large sets of digital ECGs linked to rich clinical data have been used to develop AI models for the detection of left ventricular dysfunction, silent (previously undocumented and asymptomatic) atrial fibrillation and hypertrophic cardiomyopathy, as well as the determination of a person’s age, sex and race, among other phenotypes. In this Review, we summarize the current and future state of the AI-enhanced ECG in the detection of cardiovascular disease in at-risk populations, discuss its implications for clinical decision-making in patients with cardiovascular disease and critically appraise potential limitations and unknowns.\t\t","spans":[]},{"type":"paragraph","text":"","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"01351d73-f57f-4af1-971e-9e9468c9b99c","url":"https://www.sciencedirect.com/science/article/abs/pii/S0025619620301385"},"date":"2021-02-01T19:30:00+0000","algorithm":"Other Programs","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbkpBAAACIAC4Nn","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbkpBAAACIAC4Nn%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:06:47+0000","last_publication_date":"2023-03-07T17:41:53+0000","slugs":["artificial-intelligenceenhanced-electrocardiogram-for-the-early-detection-of-cardiac-amyloidosis"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence–Enhanced Electrocardiogram for the Early Detection of Cardiac Amyloidosis","spans":[]}],"abstract":[{"type":"paragraph","text":"The objective of this study was to develop an artificial intelligence (AI)–based tool to detect cardiac amyloidosis (CA) from a standard 12-lead electrocardiogram (ECG). 12-lead ECG data from 2541 patients with light chain or transthyretin CA seen at Mayo Clinic between 2000 and 2019 was collected. Cases were nearest neighbor matched for age and sex, with 2454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with an internal validation set (n=999; 20%) and a randomly selected holdout testing set (n=999; 20%). Experiments using single-lead and 6-lead ECG subsets were performed. The area under the receiver operating characteristic curve (AUC) was 0.91 (CI, 0.90 to 0.93), with a positive predictive value for detecting either type of CA of 0.86. By use of a cutoff probability of 0.485 determined by the Youden index, 426 (84%) of the holdout patients with CA were detected by the model. Of the patients with CA and prediagnosis electrocardiographic studies, the AI model successfully predicted the presence of CA more than 6 months before the clinical diagnosis in 59%. The best single-lead model was V5 with an AUC of 0.86 and a precision of 0.78, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.90 and a precision of 0.85. An AI-driven ECG model effectively detects CA and may promote early diagnosis of this life-threatening disease.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"2b33e57c-f7de-4d10-b350-f65609bc6d4a","url":"https://www.mayoclinicproceedings.org/article/S0025-6196(21)00353-0/abstract"},"date":"2021-07-02T18:30:00+0000","algorithm":"Amyloidosis","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbeSxAAACMAC2XW","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbeSxAAACMAC2XW%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:39:43+0000","last_publication_date":"2023-03-03T17:31:10+0000","slugs":["artificial-intelligence-enabled-ecg-algorithm-to-identify-patients-with-left-ventricular-systolic-dysfunction-presenting-to-the-emergency-department-with-dyspnea"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea","spans":[]}],"abstract":[{"type":"paragraph","text":"Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD). A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86-0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83-0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76-0.84). The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"ee21d460-e641-4f11-924f-c0e07eeea117","url":"https://pubmed.ncbi.nlm.nih.gov/32986471/"},"date":"2020-08-04T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Circulation: Arrhythmia and Electrophysiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbd2BAAACEAC2PF","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbd2BAAACEAC2PF%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:37:47+0000","last_publication_date":"2023-03-03T17:27:47+0000","slugs":["assessing-and-mitigating-bias-in-medical-artificial-intelligence---the-effects-of-race-and-ethnicity-on-a-deep-learning-model-for-ecg-analysis"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Assessing and Mitigating Bias in Medical Artificial Intelligence - The Effects of Race and Ethnicity on a Deep Learning Model for ECG Analysis","spans":[]}],"abstract":[{"type":"paragraph","text":"Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG. Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"c9331e4c-6566-4752-a9c5-f779fec14940","url":"https://doi.org/10.1161/circep.119.007988"},"date":"2020-02-16T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Circulation: Arrhythmia and Electrophysiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbX4RAAACAAC0ha","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbX4RAAACAAC0ha%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:12:24+0000","last_publication_date":"2023-03-08T16:15:12+0000","slugs":["artificial-intelligenceaugmented-electrocardiogram-detection-of-left-ventricular-systolic-dysfunction-in-the-general-population"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence–Augmented Electrocardiogram Detection of Left Ventricular Systolic Dysfunction in the General Population","spans":[]}],"abstract":[{"type":"paragraph","text":"The goal of this study was to validate an AI-enabled ECG algorithm for the detection of preclinical left ventricular systolic dysfunction (LVSD) in a large community-based cohort. We found that for detection of LVSD in the total population, the area under the curve (AUC) for the AI-ECG was 0.97, and in the high-risk subgroup, the AUC was 0.97 as well. Overall, the study showed that AI-enabled ECGs can identify preclinical LVSD in the community and requires further study as a screening tool for preclinical LVSD.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"dd46fc0f-cc93-44cb-9c1b-277cd0bf0c21","url":"https://www.mayoclinicproceedings.org/article/S0025-6196(21)00258-5/fulltext"},"date":"2021-06-09T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y1gM0RQAACUAaGQT","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y1gM0RQAACUAaGQT%22%29+%5D%5D","tags":[],"first_publication_date":"2022-10-25T16:21:30+0000","last_publication_date":"2023-03-03T18:50:51+0000","slugs":["tandem-deep-learning-and-logistic-regression-models-to-optimize-hypertrophic-cardiomyopathy-detection-in-routine-clinical-practice","artificial-intelligence-guided-screening-for-atrial-fibrillation-using-electrocardiogram-during-sinus-rhythm-a-prospective-non-randomised-interventional-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Tandem deep learning and logistic regression models to optimize hypertrophic cardiomyopathy detection in routine clinical practice","spans":[]}],"abstract":[{"type":"paragraph","text":"An electrocardiogram (ECG)-based artificial intelligence (AI) algorithm has shown good performance in detecting hypertrophic cardiomyopathy (HCM). However, its application in routine clinical practice may be challenging due to the low disease prevalence and potentially high false-positive rates. This study was conducted to identify clinical characteristics associated with true and false positive HCM AI-ECG results to improve its clinical application.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"6d086357-e05c-48bc-8829-6357d317cf73","url":"https://www.cvdigitalhealthjournal.com/article/S2666-6936(22)00167-0/fulltext"},"date":"2022-10-21T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Cardiovascular Digital Health Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yxi_-xMAACIA17vb","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yxi_-xMAACIA17vb%22%29+%5D%5D","tags":[],"first_publication_date":"2022-09-07T16:18:05+0000","last_publication_date":"2023-03-06T18:25:46+0000","slugs":["deep-learning-derived-cardiovascular-age-shares-a-genetic-basis-with-other-cardiac-phenotypes","artificial-intelligence-applied-to-cardiomyopathies-is-it-time-for-clinical-application"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":" Deep learning-derived cardiovascular age shares a genetic basis with other cardiac phenotypes","spans":[]}],"abstract":[{"type":"paragraph","text":"Artificial Intelligence (AI) based approaches can now use electrocardiograms (ECGs) to provide expert-level performance in detecting heart abnormalities and diagnosing disease. Additionally, patient age predicted from ECGs by AI models has shown great potential as a biomarker for cardiovascular age as recent work has found differences from chronological age (\"delta age\") to be associated with mortality and co-morbidities. However, the genetic underpinning of delta age is unknown, but crucial for understanding underlying individual risk. By performing a genome-wide association study using UK Biobank data (n=34,432), we identified eight loci associated with delta age (p ≤ 5 × 10^−8), including genes linked to cardiovascular disease (CVD) (e.g. SCN5A) and (heart) muscle development (e.g. TTN). Our results indicate that the genetic basis of cardiovascular aging is predominantly determined by genes directly involved with the cardiovascular system rather than those connected to more general mechanisms of aging. Our insights inform the epidemiology of CVD, with implications for preventative and precision medicine.","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"68d2635d-38fc-4360-8b6a-754512654503","url":"https://www.nature.com/articles/s41598-022-27254-z"},"date":"2022-08-29T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Nature","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"ZAiyLxAAACgAwDjG","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22ZAiyLxAAACgAwDjG%22%29+%5D%5D","tags":[],"first_publication_date":"2023-03-08T16:07:24+0000","last_publication_date":"2023-03-08T16:07:24+0000","slugs":["provider-perspectives-on-artificial-intelligenceguided-screening-for-low-ejection-fraction-in-primary-care-qualitative-study","artificial-intelligence-enhanced-electrocardiography-in-cardiovascular-disease-management"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Provider Perspectives on Artificial Intelligence–Guided Screening for Low Ejection Fraction in Primary Care: Qualitative Study","spans":[]}],"abstract":[{"type":"paragraph","text":"In this study, we aimed to describe provider perspectives on the adoption of an AI-enabled screening tool in primary care to inform effective integration and sustained use. A qualitative study was conducted between December 2019 and February 2020 as part of a pragmatic randomized controlled trial at a large academic medical center in the United States. In all, 29 primary care providers were purposively sampled using a positive deviance approach for participation in semistructured focus groups after their use of the AI tool in the randomized controlled trial was complete. Focus group data were analyzed using a grounded theory approach; iterative analysis was conducted to identify codes and themes, which were synthesized into findings. Our findings revealed that providers understood the purpose and functionality of the AI tool and saw potential value for more accurate and faster diagnoses. However, successful adoption into routine patient care requires the smooth integration of the tool with clinical decision-making and existing workflow to address provider needs and preferences during implementation. The implementation of AI-enabled tools in medicine can benefit from sensitivity to the nuanced context of care and provider needs to enable the useful adoption of AI tools at the point of care.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"193615de-e38b-4fed-9c8c-4c8f0b1d044a","url":"https://ai.jmir.org/2022/1/e41940"},"date":"2022-10-14T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"JMIR AI","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbejxAAACMAC2cT","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbejxAAACMAC2cT%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:40:49+0000","last_publication_date":"2023-03-03T17:34:48+0000","slugs":["mortality-risk-stratification-using-artificial-intelligence-augmented-electrocardiogram-in-cardiac-intensive-care-unit-patients"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Mortality risk stratification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients","spans":[]}],"abstract":[{"type":"paragraph","text":"An artificial intelligence-augmented electrocardiogram (AI-ECG) algorithm can identify left ventricular systolic dysfunction (LVSD). We sought to determine whether this AI-ECG algorithm could stratify mortality risk in cardiac intensive care unit (CICU) patients, independent of the presence of LVSD by transthoracic echocardiography (TTE). We included 11 266 unique Mayo Clinic CICU patients admitted from 2007 to 2018 who underwent AI-ECG after CICU admission. Left ventricular ejection fraction (LVEF) data were extracted for patients with a TTE during hospitalization. Patients with available LVEF data (n = 8242) were divided based on the presence of predicted (by AI-ECG) vs. observed (by TTE) LVSD (defined as LVEF ≤ 35%), using TTE as the gold standard. A stepwise increase in hospital mortality was observed for patients with a true negative, false positive, false negative, and true positive AI-ECG. The AI-ECG prediction of LVSD is associated with hospital mortality in CICU patients, affording risk stratification in addition to that provided by echocardiographic LVEF. Our results emphasize the prognostic value of electrocardiographic patterns reflecting underlying myocardial disease that are recognized by the AI-ECG.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"61e099b4-88c6-42f9-9b0a-72e712e24e88","url":"https://pubmed.ncbi.nlm.nih.gov/33620440/"},"date":"2020-10-16T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"European Heart Journal - Acute Cardiovascular Care","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbjlxAAACIAC36O","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbjlxAAACIAC36O%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:02:18+0000","last_publication_date":"2023-03-03T19:07:17+0000","slugs":["detection-of-hypertrophic-cardiomyopathy-using-a-convolutional-neural-network-enabled-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Detection of Hypertrophic Cardiomyopathy Using a Convolutional Neural Network-Enabled Electrocardiogram","spans":[]}],"abstract":[{"type":"paragraph","text":"Hypertrophic cardiomyopathy (HCM) is an uncommon but important cause of sudden cardiac death. This study sought to develop an artificial intelligence approach for the detection of HCM based on 12-lead electrocardiography (ECG). In the combined datasets, mean age was 54.8 ± 15.9 years for the HCM group and 57.5 ± 15.5 years for the control group. After training and validation, the area under the curve (AUC) of the CNN in the validation dataset was 0.95 (95% confidence interval [CI]: 0.94 to 0.97) at the optimal probability threshold of 11% for having HCM. When applying this probability threshold to the testing dataset, the CNN’s AUC was 0.96 (95% CI: 0.95 to 0.96) with sensitivity 87% and specificity 90%. In subgroup analyses, the AUC was 0.95 (95% CI: 0.94 to 0.97) among patients with left ventricular hypertrophy by ECG criteria and 0.95 (95% CI: 0.90 to 1.00) among patients with a normal ECG. The model performed particularly well in younger patients (sensitivity 95%, specificity 92%). In patients with HCM with and without sarcomeric mutations, the model-derived median probabilities for having HCM were 97% and 96%, respectively. ECG-based detection of HCM by an artificial intelligence algorithm can be achieved with high diagnostic performance, particularly in younger patients. This model requires further refinement and external validation, but it may hold promise for HCM screening.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"b7fe8c77-9fd0-4c59-bf3e-ee8cf13ca4a4","url":"https://www.jacc.org/doi/full/10.1016/j.jacc.2019.12.030"},"date":"2020-02-25T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Journal of the Americal College of Cardiology (JACC)","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbXnBAAACEAC0cA","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbXnBAAACEAC0cA%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:11:11+0000","last_publication_date":"2023-03-07T19:31:57+0000","slugs":["development-and-validation-of-a-deep-learning-model-to-screen-for-hyperkalemia-from-the-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Development and Validation of a Deep-Learning Model to Screen for Hyperkalemia From the Electrocardiogram","spans":[]}],"abstract":[{"type":"paragraph","text":"For patients with chronic kidney disease (CKD), hyperkalemia is common, associated with fatal arrhythmias, and often asymptomatic, while guideline-directed monitoring of serum potassium is underused. A deep-learning model that enables noninvasive hyperkalemia screening from the electrocardiogram (ECG) may improve detection of this life-threatening condition. A deep convolutional neural network (DNN) was trained using 1 576 581 ECGs from 449 380 patients seen at Mayo Clinic, Rochester, Minnesota, from 1994 to 2017. The DNN was trained using 2 (leads I and II) or 4 (leads I, II, V3, and V5) ECG leads to detect serum potassium levels of 5.5 mEq/L or less (to convert to millimoles per liter, multiply by 1) and was validated using retrospective data from the Mayo Clinic in Minnesota, Florida, and Arizona. The validation included 61 965 patients with stage 3 or greater CKD. Each patient had a serum potassium count drawn within 4 hours after their ECG was recorded. Data were analyzed between April 12, 2018, and June 25, 2018. Area under the receiver operating characteristic curve (AUC) and sensitivity and specificity, with serum potassium level as the reference standard. The model was evaluated at 2 operating points, 1 for equal specificity and sensitivity and another for high (90%) sensitivity. Of the total 1 638 546 ECGs, 908 000 (55%) were from men. The prevalence of hyperkalemia in the 3 validation data sets ranged from 2.6% (n = 1282 of 50 099; Minnesota) to 4.8% (n = 287 of 6011; Florida). Using ECG leads I and II, the AUC of the deep-learning model was 0.883 (95% CI, 0.873-0.893) for Minnesota, 0.860 (95% CI, 0.837-0.883) for Florida, and 0.853 (95% CI, 0.830-0.877) for Arizona. Using a 90% sensitivity operating point, the sensitivity was 90.2% (95% CI, 88.4%-91.7%) and specificity was 63.2% (95% CI, 62.7%-63.6%) for Minnesota; the sensitivity was 91.3% (95% CI, 87.4%-94.3%) and specificity was 54.7% (95% CI, 53.4%-56.0%) for Florida; and the sensitivity was 88.9% (95% CI, 84.5%-92.4%) and specificity was 55.0% (95% CI, 53.7%-56.3%) for Arizona. In this study, using only 2 ECG leads, a deep-learning model detected hyperkalemia in patients with renal disease with an AUC of 0.853 to 0.883. The application of artificial intelligence to the ECG may enable screening for hyperkalemia. Prospective studies are warranted.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"81948951-0c9a-4d52-9a67-07bb1aecfc3b","url":"https://jamanetwork.com/journals/jamacardiology/fullarticle/2729582"},"date":"2019-04-03T18:30:00+0000","algorithm":"Hyperkalemia","publishedIn":"JAMA Cardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yxi_gxMAACMA17md","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yxi_gxMAACMA17md%22%29+%5D%5D","tags":[],"first_publication_date":"2022-09-07T15:59:45+0000","last_publication_date":"2022-09-07T16:23:32+0000","slugs":["artificial-intelligence-applied-to-cardiomyopathies-is-it-time-for-clinical-application","artificial-intelligence-enhanced-electrocardiography-in-cardiovascular-disease-management"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence Applied to Cardiomyopathies: Is It Time for Clinical Application?","spans":[]}],"abstract":[{"type":"paragraph","text":"Many studies have been undertaken in recent years on cardiomyopathy screening especially using AI-enhanced electrocardiography (ECG). While the implementation of AI in the diagnosis and treatment of cardiomyopathies is still in its infancy, an ever-growing clinical research strategy will ascertain the clinical utility of these AI tools to help improve the diagnosis of and outcomes in cardiomyopathies. We also need to standardize the tools used to monitor the performance of AI-based systems which can then be used to expedite decision-making and rectify any hidden biases. Given its potentially important role in clinical practice, healthcare providers need to familiarize themselves with the promise and limitations of this technology.","spans":[]},{"type":"paragraph","text":"","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"f45d6874-e938-492f-999e-5018b4a6e6ff","url":"https://link.springer.com/article/10.1007/s11886-022-01776-4"},"date":"2022-09-01T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Current Cardiology Reports","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YynImBMAACUAI655","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YynImBMAACUAI655%22%29+%5D%5D","tags":[],"first_publication_date":"2022-09-20T14:09:49+0000","last_publication_date":"2022-09-20T14:09:49+0000","slugs":["electrocardiogram-artificial-intelligence-and-immune-mediated-necrotizing-myopathy-predicting-left-ventricular-dysfunction-and-clinical-outcomes","artificial-intelligence-applied-to-cardiomyopathies-is-it-time-for-clinical-application"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Electrocardiogram-Artificial Intelligence and Immune-Mediated Necrotizing Myopathy: Predicting Left Ventricular Dysfunction and Clinical Outcomes","spans":[]}],"abstract":[{"type":"paragraph","text":"This study was conducted to characterize the utility of an existing electrocardiogram (ECG)-artificial intelligence (AI) algorithm of left ventricular dysfunction (LVD) in immune-mediated necrotizing myopathy (IMNM). A retrospective cohort observational study was conducted within the Mayo Clinic's tertiary-care neuromuscular clinic for patients with IMNM meeting European Neuromuscular Centre diagnostic criteria. A validated AI algorithm using 12-lead standard ECGs to detect LVD, licensed to Anumana was applied. The output was presented as a percent probability of LVD. Electrocardiograms before and while on immunotherapy were reviewed. The LVD-predicted probability scores were compared with echocardiograms, immunotherapy treatment response, and mortality. The ECG-AI algorithm had acceptable accuracy in LVD prediction in 74% (68 of 89) of patients with IMNM with available echocardiograms (discrimination threshold, 0.74; 95% CI, 0.6-0.87). In IMNM, an AI-ECG algorithm assists detection of LVD, enhancing the decision to advance to echocardiogram testing, while also informing on mortality risk, which is important in the decision of immunotherapy escalation and monitoring.","spans":[]},{"type":"paragraph","text":"","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"b8e53aa3-c875-40ce-abc7-2098eee81473","url":"https://www.sciencedirect.com/science/article/pii/S2542454822000558"},"date":"2022-09-16T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv7hBIAACAAq4aa","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv7hBIAACAAq4aa%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:18:54+0000","last_publication_date":"2022-08-16T20:18:54+0000","slugs":["age-and-sex-estimation-using-artificial-intelligence-from-standard-12-lead-ecgs","application-of-artificial-intelligence-to-the-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Age and Sex Estimation Using Artificial Intelligence From Standard 12-Lead ECGs","spans":[]}],"abstract":[{"type":"paragraph","text":"Sex and age have long been known to affect the ECG. Several biologic variables and anatomic factors may contribute to sex and age-related differences on the ECG. We hypothesized that a convolutional neural network (CNN) could be trained through a process called deep learning to predict a person’s age and self-reported sex using only 12-lead ECG signals, and that discrepancies between CNN-predicted age and chronological age may serve as a physiological measure of health. Upon training CNNs using 10-second samples of 499727 12-lead ECGs, we found that the model was 90.4% accurate in sex classification and age was estimated as a continuous variable with an average error of 6.9+/-5.6 years. The study found that the major factors seen among patients with a CNN-predicted age that exceeded chronological age by >7 years included: low ejection fraction, hypertension, and coronary disease. We found that applying AI to the ECG allows prediction of patient sex, and estimation of age. The ability of an AI algorithm to determine psychological age, with further validation, may serve as a measure of overall health.","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"3c71e27f-054a-4aee-8efa-f208a20348a2","url":"https://www.ahajournals.org/doi/full/10.1161/CIRCEP.119.007284"},"date":"2019-08-27T18:30:00+0000","algorithm":"Other Programs","publishedIn":"American Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuA1fRAAACcAoFym","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuA1fRAAACcAoFym%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:43:22+0000","last_publication_date":"2022-07-26T18:43:22+0000","slugs":["a-comprehensive-artificial-intelligence-enabled-electrocardiogram-interpretation-program","machine-learning-algorithms-to-predict-10-year-atherosclerotic-cardiovascular-risk-in-a-contemporary-community-based-historical-cohort"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"A comprehensive artificial intelligence-enabled electrocardiogram interpretation program","spans":[]}],"abstract":[{"type":"paragraph","text":"Automated computerized electrocardiogram (ECG) interpretation algorithms are designed to enhance physician ECG interpretation, minimize medical error, and expedite clinical workflow. However, the performance of current computer algorithms is notoriously inconsistent. We aimed to develop and validate an artificial intelligence–enabled ECG (AI-ECG) algorithm capable of comprehensive 12-lead ECG interpretation with accuracy comparable to practicing cardiologists. We developed an AI-ECG algorithm using a convolutional neural network as a multilabel classifier capable of assessing 66 discrete, structured diagnostic ECG codes using the cardiologist’s final annotation as the gold-standard interpretation. We included 2,499,522 ECGs from 720,978 patients ≥18 years of age with a standard 12-lead ECG obtained at the Mayo Clinic ECG laboratory between 1993 and 2017. The total sample was randomly divided into training (n = 1,749,654), validation (n = 249,951), and testing (n = 499,917) datasets with a similar distribution of codes. We compared the AI-ECG algorithm’s performance to the cardiologist’s interpretation in the testing dataset using receiver operating characteristic (ROC) and precision recall (PR) curves. The model performed well for various rhythm, conduction, ischemia, waveform morphology, and secondary diagnoses codes with an area under the ROC curve of ≥0.98 for 62 of the 66 codes. PR metrics were used to assess model performance accounting for category imbalance and demonstrated a sensitivity ≥95% for all codes. An AI-ECG algorithm demonstrates high diagnostic performance in comparison to reference cardiologist interpretation of a standard 12-lead ECG. The use of AI-ECG reading tools may permit scalability as ECG acquisition becomes more ubiquitous.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"9d2c8e73-ea9e-4649-9ad1-93c84b0a6c23","url":"https://www.sciencedirect.com/science/article/pii/S2666693620300323"},"date":"2020-09-01T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Cardiovascular Digital Health Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv2mxIAACIAq3C3","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv2mxIAACIAq3C3%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T19:59:07+0000","last_publication_date":"2022-08-16T19:59:07+0000","slugs":["artificial-intelligenceelectrocardiography-to-detect-atrial-fibrillation-trend-of-probability-before-and-after-the-first-episode","a-comprehensive-artificial-intelligence-enabled-electrocardiogram-interpretation-program"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence—electrocardiography to detect atrial fibrillation: trend of probability before and after the first episode ","spans":[]}],"abstract":[{"type":"paragraph","text":"Artificial intelligence (AI) enabled electrocardiography (ECG) can detect latent atrial fibrillation (AF) in patients with sinus rhythm (SR). However, the change of AI-ECG probability before and after the first AF episode is not well characterized. We sought to characterize the temporal trend of AI-ECG AF probability around the first episode of AF. We found that the AI-ECG probability progressively increases with time prior to the first AF episode, transiently decreases 1–2 years following AF and continues to increase thereafter.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"3a582ad1-7ed0-4225-bf25-59f5985ffd32","url":"https://academic.oup.com/ehjdh/article/3/2/228/6582473https://"},"date":"2022-05-09T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuA10xAAACcAoF4-","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuA10xAAACcAoF4-%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:44:23+0000","last_publication_date":"2022-07-26T18:44:23+0000","slugs":["an-artificial-intelligenceenabled-ecg-algorithm-for-comprehensive-ecg-interpretation-can-it-pass-the-turing-test","a-comprehensive-artificial-intelligence-enabled-electrocardiogram-interpretation-program"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"An artificial intelligence–enabled ECG algorithm for comprehensive ECG interpretation: Can it pass the ‘Turing test’?","spans":[]}],"abstract":[{"type":"paragraph","text":"We developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, no changes needed), (2) acceptable (ie, minor edits needed), or (3) unacceptable (ie, major edits needed). Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as ideal from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as acceptable from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"e2d957e8-c26c-434c-b095-178bc57030ad","url":"https://www.sciencedirect.com/science/article/pii/S2666693621000463"},"date":"2021-05-05T18:30:00+0000","algorithm":"Other Programs","publishedIn":"Cardiovascular Digital Health Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuA01RAAACQAoFm0","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuA01RAAACQAoFm0%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:40:42+0000","last_publication_date":"2022-07-26T18:40:42+0000","slugs":["the-association-of-artificial-intelligence-enabled-electrocardiogram-derived-age-physiologic-age-with-atherosclerotic-cardiovascular-events-in-the-community","deep-learning-enabled-electrocardiographic-prediction-of-computer-tomography-based-high-coronary-calcium-score-cac"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"The association of artificial intelligence-enabled electrocardiogram-derived age (physiologic age) with atherosclerotic cardiovascular events in the community","spans":[]}],"abstract":[{"type":"paragraph","text":"This study demonstrates that artificial intelligence interpretation of ECGs (AI-ECG) can estimate an individual's physiologic age and that the gap between AI-ECG and chronologic age (Age-Gap) is associated with increased mortality. We hypothesized that Age-Gap would predict long-term atherosclerotic cardiovascular disease (ASCVD) and that Age-Gap would refine the ACC/AHA Pooled Cohort Equations' (PCE) predictive abilities. Using the Rochester Epidemiology Project (REP) we evaluated a community-based cohort of consecutive patients seeking primary care between 1998–2000 and followed through March 2016. Inclusion criteria were age 40–79 and complete data to calculate PCE. A neural network, trained, validated, and tested in an independent cohort of ∼ 500,000 independent patients, using 10-second digital samples of raw, 12 lead ECGs. PCE was categorized as low<5%, intermediate 5–9.9%, high 10–19.9%, and very high≥20%. The primary endpoint was ASCVD and included fatal and non-fatal myocardial infarction and ischemic stroke; the secondary endpoint also included coronary revascularization [Percutaneous Coronary Intervention (PCI) or Coronary Artery Bypass Graft (CABG)], TIA and Cardiovascular mortality. Events were validated in duplicate. Follow-up was truncated at 10 years for PCE analysis. The association between Age-Gap with ASCVD and expanded ASCVD was assessed with cox proportional hazard models that adjusted for chronological age, sex and risk factors. Models were stratified by PCE risk categories to evaluate the effect of PCE predicted risk. We included 24,793 patients (54% women, 95% Caucasian) with mean follow up of 12.6±5.1 years. 2,366 (9.5%) developed ASCVD events and 3,401 (13.7%) the expanded ASCVD.After adjusting for age and sex, those considered older by ECG, compared to their chronologic age had a higher risk for ASCVD when compared to those with <−2 SD age gap (considered younger by ECG) with similar results when using the expanded definition of ASCVD (data not shown). Age-Gap enhanced predicted capabilities of the PCE among those with low 10-year predicted risk (<5%). The difference between physiologic AI-ECG age and chronologic age is associated with long-term ASCVD, and enhances current risk calculators (PCE) ability to identify high and low risk individuals. This may help identify individuals who should or should not be treated with newer, expensive risk-reducing therapies.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"aa8eaa3e-5af3-4751-89cf-be7eec1fdbe2","url":"https://www.researchgate.net/publication/347222687_The_association_of_artificial_intelligence-enabled_electrocardiogram-derived_age_physiologic_age_with_atherosclerotic_cardiovascular_events_in_the_community"},"date":"2020-11-25T19:30:00+0000","algorithm":"Other Programs","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv5PhIAACMAq3y7","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv5PhIAACMAq3y7%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:09:55+0000","last_publication_date":"2022-08-16T20:09:55+0000","slugs":["the-12-lead-electrocardiogram-as-a-biomarker-of-biological-age","migraine-with-aura-associates-with-a-higher-artificial-intelligence-ecg-atrial-fibrillation-prediction-model-output-compared-to-migraine-without-aura-in-both-women-and-men"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"The 12-lead electrocardiogram as a biomarker\n of biological age","spans":[]}],"abstract":[{"type":"paragraph","text":"In a previous study, we demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG). However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. The study found that the difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological aging.","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"e9cb451b-a485-4cca-9483-4ddec48a1a2e","url":"https://academic.oup.com/ehjdh/article/2/3/379/6248088"},"date":"2021-04-23T18:30:00+0000","algorithm":"Other Programs","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv69BIAACIAq4P3","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv69BIAACIAq4P3%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:17:32+0000","last_publication_date":"2022-08-16T20:17:32+0000","slugs":["application-of-artificial-intelligence-to-the-electrocardiogram","left-ventricular-systolic-dysfunction-predicted-by-artificial-intelligence-using-the-electrocardiogram-in-chagas-disease-patientsthe-sami-trop-cohort"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Application of artificial intelligence to the electrocardiogram","spans":[]}],"abstract":[{"type":"paragraph","text":"Artificial intelligence (AI) has given the electrocardiogram (ECG) and clinicians reading them super-human diagnostic abilities. Trained without hard-coded rules by finding often subclinical patterns in huge datasets, AI transforms the ECG, a ubiquitous, non-invasive cardiac test that is integrated into practice workflows, into a screening tool and predictor of cardiac and non-cardiac diseases, often in asymptomatic individuals. This review describes the mathematical background behind supervised AI algorithms, and discusses selected AI ECG cardiac screening algorithms including those for the detection of left ventricular dysfunction, episodic atrial fibrillation from a tracing recorded during normal sinus rhythm, and other structural and valvular diseases. The ability to learn from big data sets, without the need to understand the biological mechanism, has created opportunities for detecting non-cardiac diseases as COVID-19 and introduced challenges with regards to data privacy. Like all medical tests, the AI ECG must be carefully vetted and validated in real-world clinical environments. Finally, with mobile form factors that allow acquisition of medical-grade ECGs from smartphones and wearables, the use of AI may enable massive scalability to democratize healthcare.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"f0cde0d7-5347-444a-907a-e435080f6a4b","url":"https://pubmed.ncbi.nlm.nih.gov/34534279/"},"date":"2021-06-18T18:30:00+0000","algorithm":"Other Programs","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YuAzsxAAACUAoFSe","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YuAzsxAAACUAoFSe%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-26T18:36:18+0000","last_publication_date":"2022-07-26T18:36:18+0000","slugs":["artificial-intelligence-enabled-electrocardiography-to-screen-patients-with-dilated-cardiomyopathy","conceptual-and-literature-basis-for-wide-complex-tachycardia-and-baseline-ecg-comparison"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence-Enabled Electrocardiography to Screen Patients with Dilated Cardiomyopathy","spans":[]}],"abstract":[{"type":"paragraph","text":"Undiagnosed dilated cardiomyopathy (DC) can be asymptomatic or present as sudden cardiac death, therefore pre-emptively identifying and treating patients may be beneficial. Screening for DC with echocardiography is expensive and labor intensive and standard electrocardiography (ECG) is insensitive and non-specific. The performance and applicability of artificial intelligence-enabled electrocardiography (AI-ECG) for detection of DC is unknown. Diagnostic performance of an AI algorithm in determining reduced left ventricular ejection fraction (LVEF) was evaluated in a cohort that comprised of DC and normal LVEF control patients. DC patients and controls with 12-lead ECGs and a reference LVEF measured by echocardiography performed within 30 and 180 days of the ECG respectively were enrolled. The model was tested for its sensitivity, specificity, negative predictive (NPV) and positive predictive values (PPV) based on the prevalence of DC at 1% and 5%. The cohort consisted of 421 DC cases (60% males, 57±15 years, LVEF 28±11%) and 16,025 controls (49% males, age 69 ±16 years, LVEF 62±5%). For detection of LVEF≤45%, the area under the curve (AUC) was 0.955 with a sensitivity of 98.8% and specificity 44.8%. The NPV and PPV were 100% and 1.8% at a DC prevalence of 1% and 99.9% and 8.6% at a prevalence of 5%, respectively. In conclusion AI-ECG demonstrated high sensitivity and negative predictive value for detection of DC and could be used as a simple and cost-effective screening tool with implications for screening first degree relatives of DC patients.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"629fd277-c93a-4cea-98bb-7708dd4c8948","url":"https://www.ajconline.org/article/S0002-9149(21)00579-8/fulltext"},"date":"2021-07-24T18:30:00+0000","algorithm":"Other Programs","publishedIn":"The American Journal of Cardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Y2P92BQAAMDendXe","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Y2P92BQAAMDendXe%22%29+%5D%5D","tags":[],"first_publication_date":"2022-11-03T17:44:39+0000","last_publication_date":"2022-11-03T17:44:39+0000","slugs":["clinician-adoption-of-an-artificial-intelligence-algorithm-to-detect-left-ventricular-systolic-dysfunction-in-primary-care.","tandem-deep-learning-and-logistic-regression-models-to-optimize-hypertrophic-cardiomyopathy-detection-in-routine-clinical-practice"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Clinician Adoption of an Artificial Intelligence Algorithm to Detect Left Ventricular Systolic Dysfunction in Primary Care.","spans":[]}],"abstract":[{"type":"paragraph","text":"In this study, we aimed to compare the clinicians’ characteristics of “high adopters” and “low adopters” of an artificial intelligence (AI)–enabled electrocardiogram (ECG) algorithm that alerted for possible low left ventricular ejection fraction (EF) and the subsequent effectiveness of detecting patients with low EF. The study found that clinicians who most frequently followed the recommendations of an AI tool were twice as likely to diagnose low EF. Those clinicians with less complex patients were more likely to be high adopters.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"381a9a22-5810-4ad5-83fa-dbd4e60c84df","url":"https://www.mayoclinicproceedings.org/article/S0025-6196(22)00247-6/fulltext"},"date":"2022-11-01T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv73hIAACAAq4hK","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv73hIAACAAq4hK%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:20:49+0000","last_publication_date":"2022-08-16T20:20:49+0000","slugs":["artificial-intelligence-enhanced-electrocardiography-in-cardiovascular-disease-management","age-and-sex-estimation-using-artificial-intelligence-from-standard-12-lead-ecgs"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","spans":[]}],"abstract":[{"type":"paragraph","text":"The application of artificial intelligence (AI) to the electrocardiogram (ECG), a ubiquitous and standardized test, is an example of the ongoing transformative effect of AI on cardiovascular medicine. Although the ECG has long offered valuable insights into cardiac and non-cardiac health and disease, its interpretation requires considerable human expertise. Advanced AI methods, such as deep-learning convolutional neural networks, have enabled rapid, human-like interpretation of the ECG, while signals and patterns largely unrecognizable to human interpreters can be detected by multilayer AI networks with precision, making the ECG a powerful, non-invasive biomarker. Large sets of digital ECGs linked to rich clinical data have been used to develop AI models for the detection of left ventricular dysfunction, silent (previously undocumented and asymptomatic) atrial fibrillation and hypertrophic cardiomyopathy, as well as the determination of a person’s age, sex and race, among other phenotypes. In this Review, we summarize the current and future state of the AI-enhanced ECG in the detection of cardiovascular disease in at-risk populations, discuss its implications for clinical decision-making in patients with cardiovascular disease and critically appraise potential limitations and unknowns.\t\t","spans":[]},{"type":"paragraph","text":"","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"2946fbf8-3a72-4ef6-8b5e-874017c1e1b2","url":"https://www.nature.com/articles/s41569-020-00503-2"},"date":"2021-02-01T19:30:00+0000","algorithm":"Other Programs","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv49RIAACEAq3uN","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv49RIAACEAq3uN%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:08:13+0000","last_publication_date":"2022-08-16T20:08:13+0000","slugs":["migraine-with-aura-associates-with-a-higher-artificial-intelligence-ecg-atrial-fibrillation-prediction-model-output-compared-to-migraine-without-aura-in-both-women-and-men","real-world-performance-long-term-efficacy-and-absence-of-bias-in-the-artificial-intelligence-enhanced-electrocardiogram-to-detect-left-ventricular-systolic-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Migraine with aura associates with a higher artificial intelligence: ECG atrial fibrillation prediction model output compared to migraine without aura in both women and men","spans":[]}],"abstract":[{"type":"paragraph","text":"MwA is associated with an approximately twofold risk of ischemic stroke. Longitudinal cohort studies showed that patients with MwA have a higher incidence of developing AF compared to those with MwoA. The Mayo Clinic Cardiology team developed an AI-ECG algorithm that calculates the probability of concurrent paroxysmal or impending AF in ECGs with normal sinus rhythm (NSR). In this study, we found that utilizing a novel AI-ECG algorithm on a large group of patients, we demonstrated that patients with MwA have a significantly higher AF prediction model output, implying a higher probability of concurrent paroxysmal or impending AF, compared to MwoA in both women and men.","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"28739513-651c-4495-809c-4cfbd2593eec","url":"https://academic.oup.com/ehjdh/advance-article/doi/10.1093/ehjdh/ztac030/6590492"},"date":"2022-06-08T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Headache","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv6nBIAACAAq4Ja","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv6nBIAACAAq4Ja%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:15:33+0000","last_publication_date":"2022-08-16T20:15:33+0000","slugs":["left-ventricular-systolic-dysfunction-predicted-by-artificial-intelligence-using-the-electrocardiogram-in-chagas-disease-patientsthe-sami-trop-cohort","rapid-exclusion-of-covid-infection-with-the-artificial-intelligence-electrocardiogram"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Left ventricular systolic dysfunction predicted by artificial intelligence using the electrocardiogram in Chagas disease patients–The SaMi-Trop cohort","spans":[]}],"abstract":[{"type":"paragraph","text":"Left ventricular systolic dysfunction (LVSD) in Chagas disease (ChD) is relatively common and its treatment using low-cost drugs can improve symptoms and reduce mortality. Recently, an artificial intelligence (AI)-enabled ECG algorithm showed excellent accuracy to detect LVSD in a general population, but its accuracy in ChD has not been tested. We conducted this study to analyze the ability of AI to recognize LVSD in patients with ChD, defined as a left ventricular ejection fraction determined by the Echocardiogram ≤ 40%. The AI analysis of the ECG of Chagas disease patients can be transformed into a powerful tool for the recognition of LVSD.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"f0744e95-d3f8-422f-af0d-2a7d4ff28e0a","url":"https://journals.plos.org/plosntds/article?id=10.1371/journal.pntd.0009974"},"date":"2021-12-06T19:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"PLOS","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Yvv3URIAACIAq3QV","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Yvv3URIAACIAq3QV%22%29+%5D%5D","tags":[],"first_publication_date":"2022-08-16T20:01:10+0000","last_publication_date":"2022-08-16T20:01:10+0000","slugs":["real-world-performance-long-term-efficacy-and-absence-of-bias-in-the-artificial-intelligence-enhanced-electrocardiogram-to-detect-left-ventricular-systolic-dysfunction","artificial-intelligenceelectrocardiography-to-detect-atrial-fibrillation-trend-of-probability-before-and-after-the-first-episode"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Real-world performance, long-term efficacy, and absence of bias in the artificial intelligence enhanced electrocardiogram to detect left ventricular systolic dysfunction ","spans":[]}],"abstract":[{"type":"paragraph","text":"We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm’s long-term efficacy and potential bias in the absence of retraining. Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.","spans":[]},{"type":"paragraph","text":"","spans":[]}],"body":[],"link":{"link_type":"Web","key":"b750e471-0e95-43fe-9ea2-e2d7608f2353","url":"https://academic.oup.com/ehjdh/article/3/2/238/6586624"},"date":"2022-05-17T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbXVRAAACEAC0Wl","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbXVRAAACEAC0Wl%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:10:07+0000","last_publication_date":"2022-07-20T07:56:59+0000","slugs":["novel-bloodless-potassium-determination-using-a-signal-processed-single-lead-ecg"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Novel Bloodless Potassium Determination Using a Signal-Processed Single-Lead ECG","spans":[]}],"abstract":[{"type":"paragraph","text":"Hyper- and hypokalemia are clinically silent, common in patients with renal or cardiac disease, and are life threatening. A noninvasive, unobtrusive, blood-free method for tracking potassium would be an important clinical advance. Two groups of hemodialysis patients (development group, n=26; validation group, n=19) underwent high-resolution digital ECG recordings and had 2 to 3 blood tests during dialysis. Using advanced signal processing, we developed a personalized regression model for each patient to noninvasively calculate potassium values during the second and third dialysis sessions using only the processed single-channel ECG. In addition, by analyzing the entire development group's first-visit data, we created a global model for all patients that was validated against subsequent sessions in the development group and in a separate validation group. This global model sought to predict potassium, based on the T wave characteristics, with no blood tests required. For the personalized model, we successfully calculated potassium values with an absolute error of 0.36±0.34 mmol/L (or 10% of the measured blood potassium). For the global model, potassium prediction was also accurate, with an absolute error of 0.44±0.47 mmol/L for the training group (or 11% of the measured blood potassium) and 0.5±0.42 for the validation set (or 12% of the measured blood potassium). The signal-processed ECG derived from a single lead can be used to calculate potassium values with clinically meaningful resolution using a strategy that requires no blood tests. This enables a cost-effective, noninvasive, unobtrusive strategy for potassium assessment that can be used during remote monitoring.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"e9cd2df2-acd9-4a75-bba0-96db1612ea07","url":"https://www.ahajournals.org/doi/10.1161/JAHA.115.002746"},"date":"2016-01-24T18:30:00+0000","algorithm":"Hyperkalemia","publishedIn":"Journal of the American Heart Association","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbh0RAAACMAC3Zx","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbh0RAAACMAC3Zx%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:54:44+0000","last_publication_date":"2022-07-20T09:15:20+0000","slugs":["detection-of-hypertrophic-cardiomyopathy-by-artificial-intelligence-enabled-electrocardiography-in-children-and-adolescents"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Detection Of Hypertrophic Cardiomyopathy By Artificial Intelligence-Enabled Electrocardiography In Children And Adolescents","spans":[]}],"abstract":[{"type":"paragraph","text":"Hypertrophic cardiomyopathy (HCM) is a cause of morbidity and sudden cardiac death in children and adolescents. There is currently no established screening approach for HCM. We recently developed an artificial intelligence (AI) convolutional neural network (CNN) for the detection of HCM based on the 12-lead electrocardiogram (ECG) in an adult population. We aimed to validate this approach of ECG-based HCM detection in pediatric patients. We included 318 HCM patients (mean age 12±4.8 years, male 68%) and 22,996 age- and sex-matched non-HCM controls. AI-ECG probability for HCM was >11% in 91% of cases and 3% of controls. The AUC of the AI-ECG model for HCM detection was 0.98 (95% CI 0.97-0.99) with corresponding sensitivity 97% and specificity 91%. The model performed similarly in subgroups defined by gender and HCM genotype status. Model performance was best in the oldest subgroup (15-18 years) in both males and females. A deep-learning, AI model can detect pediatric HCM with high accuracy from the standard 12-lead ECG.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"84568f8c-ee52-4a08-ad23-47ad2efc493f","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2904601-5"},"date":"2021-01-31T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Journal of the Americal College of Cardiology (JACC) / ACC.21","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbldxAAACMAC4cv","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbldxAAACMAC4cv%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:10:18+0000","last_publication_date":"2022-07-20T09:34:28+0000","slugs":["cost-effectiveness-of-an-electrocardiographic-deep-learning-algorithm-to-detect-asymptomatic-left-ventricular-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Cost Effectiveness of an Electrocardiographic Deep Learning Algorithm to Detect Asymptomatic Left Ventricular Dysfunction","spans":[]}],"abstract":[{"type":"paragraph","text":"We used decision analytic modeling to perform a cost-effectiveness analysis of the use of AI-ECG to screen for asymptomatic left ventricular dysfunction (ALVD) once at age 65 compared with no screening. This screening consisted of an initial screening decision tree and subsequent construction of a Markov model. One-way sensitivity analysis on various disease and cost parameters to evaluate cost-effectiveness at both $50,000 per quality-adjusted life year (QALY) and $100,000 per QALY willingness-to-pay threshold. We found that for universal screening at age 65, the novel AI-ECG algorithm would cost $43,351 per QALY gained, test performance, disease characteristics, and testing cost parameters significantly affect cost-effectiveness, and screening at ages 55 and 75 would cost $48,649 and $52,072 per QALY gained, respectively. Overall, under most of the clinical scenarios modeled, coupled with its robust test performance in both testing and validation cohorts, screening with the novel AI-ECG algorithm appears to be cost-effective at a willingness-to-pay threshold of $50,000. Universal screening for ALVD with the novel AI-ECG appears to be cost-effective under most clinical scenarios with a cost of <$50,000 per QALY. Cost-effectiveness is particularly sensitive to both the probability of disease progression and the cost of screening and downstream testing. To improve cost-effectiveness modeling, further study of the natural progression and treatment of ALVD and external validation of AI-ECG should be undertaken.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"d07582cb-ad75-4613-b8b3-05e8ad734562","url":"https://www.sciencedirect.com/science/article/pii/S0025619620314737?via%3Dihub"},"date":"2021-06-08T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbZMxAAACEAC045","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbZMxAAACEAC045%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:17:59+0000","last_publication_date":"2022-07-20T08:01:31+0000","slugs":["artificial-intelligence-enabled-electrocardiogram-for-atrial-fibrillation-identifies-cognitive-decline-risk-and-cerebral-infarcts"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence-Enabled Electrocardiogram for Atrial Fibrillation Identifies Cognitive Decline Risk and Cerebral Infarcts","spans":[]}],"abstract":[{"type":"paragraph","text":"This study was designed to investigate whether artificial intelligence-enabled electrocardiograms (AI-ECG) assessment of Atrial Fibrillation (AF) risk predicts cognitive decline and cerebral infracts. Participants included patients who had a sinus-rhythm ECG as well as a brain magnetic resonance imaging (MRI). To determine the AI-ECG-AF relationship with baseline cognitive dysfunction, we compare linear mixed-effects models with global and domain-specific cognitive z-scores from longitudinal neuropsychological assessments. AI-ECG-AF score was logit transformed and modeled with cubic splines. Participants in the study underwent cognitive analysis. We found that the AI-ECG-AF score correlated with worse cognition and gradual global cognition and attention decline. High AF probability by AI-ECG-AF score correlated with MRI cerebral infarcts .","spans":[]}],"body":[],"link":{"link_type":"Web","key":"0b3964ff-3760-4fea-9dba-f22a6ff1d326","url":"https://pubmed.ncbi.nlm.nih.gov/35512882/"},"date":"2022-04-30T18:30:00+0000","algorithm":"Atrial Fibrillation","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbdnBAAACMAC2Kx","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbdnBAAACMAC2Kx%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:36:47+0000","last_publication_date":"2022-07-20T08:07:06+0000","slugs":["clinical-trial-design-data-for-electrocardiogram-artificial-intelligence-guided-screening-for-low-ejection-fraction-eagle"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Clinical trial design data for electrocardiogram artificial intelligence-guided screening for low ejection fraction (EAGLE)","spans":[]}],"abstract":[{"type":"paragraph","text":"The article details the materials that will be used in a clinical trial - ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial [1]. It includes a clinician-facing action recommendation report that will translate an artificial intelligence algorithm to routine practice and an alert when a positive screening result is found. This report was developed using a user-centered approach via an iterative process with input from multiple physician groups. Such data can be reused and adapted to translate other artificial intelligence algorithms.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"c358f4ef-9021-4aa3-af10-dd3e7f4a942e","url":"https://doi.org/10.1016/j.dib.2019.104894"},"date":"2020-01-31T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"American Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbXEBAAACMAC0Rr","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbXEBAAACMAC0Rr%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:08:52+0000","last_publication_date":"2022-07-20T07:56:19+0000","slugs":["noninvasive-blood-potassium-measurement-using-signal-processed-single-lead-ecg-acquired-from-a-handheld-smartphone"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Noninvasive blood potassium measurement using signal-processed, single-lead ecg acquired from a handheld smartphone","spans":[]}],"abstract":[{"type":"paragraph","text":"We have previously used a 12-lead, signal-processed ECG to calculate blood potassium levels. We now assess the feasibility of doing so with a smartphone-enabled single lead, to permit remote monitoring. Twenty-one hemodialysis patients held a smartphone equipped with inexpensive FDA-approved electrodes for three 2min intervals during hemodialysis. Individualized potassium estimation models were generated for each patient. ECG-calculated potassium values were compared to blood potassium results at subsequent visits to evaluate the accuracy of the potassium estimation models. The mean absolute error between the estimated potassium and blood potassium 0.38±0.32 mEq/L (9% of average potassium level) decreasing to 0.6 mEq/L using predictors of poor signal. A single-lead ECG acquired using electrodes attached to a smartphone device can be processed to calculate the serum potassium with an error of 9% in patients undergoing hemodialysis.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"8dada9d8-b743-4c7e-8858-57f2b7344140","url":"https://www.sciencedirect.com/science/article/abs/pii/S0022073617301826"},"date":"2017-08-31T18:30:00+0000","algorithm":"Hyperkalemia","publishedIn":"Journal of Electrocardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbWmRAAACAAC0Ik","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbWmRAAACAAC0Ik%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:06:52+0000","last_publication_date":"2022-07-20T07:55:36+0000","slugs":["an-automated-screening-algorithm-using-electrocardiograms-for-pulmonary-hypertension"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"An Automated Screening Algorithm Using Electrocardiograms for Pulmonary Hypertension","spans":[]}],"abstract":[{"type":"paragraph","text":"Pulmonary hypertension (PH) is a life-threatening disease that is typically detected after significant","spans":[]},{"type":"paragraph","text":"pulmonary vascular remodeling has occurred. Longer diagnostic delays are associated with higher mortality and","spans":[]},{"type":"paragraph","text":"there is a need for a simple, fast, non-invasive PH screening tool. Currently, electrocardiograms often only","spans":[]},{"type":"paragraph","text":"identify abnormalities in severe PH. However, deep learning-based algorithms may enable detection of early,","spans":[]},{"type":"paragraph","text":"subtle, disease-specific changes, and could allow this inexpensive and ubiquitous test to serve as a powerful","spans":[]},{"type":"paragraph","text":"screening tool for PH. We used convolutional neural networks (CNN) to develop an algorithm for PH","spans":[]},{"type":"paragraph","text":"using retrospective electrocardiogram voltage-time data from Mayo Clinic. Each standard 12-lead","spans":[]},{"type":"paragraph","text":"electrocardiogram was paired with right heart catheterization to define patients as PH or non-PH, and the non-","spans":[]},{"type":"paragraph","text":"PH group was supplemented with patients in whom PH was excluded by echocardiogram. PH was defined as","spans":[]},{"type":"paragraph","text":"mean pulmonary arterial pressure (mPAP) ≥25 mmHg (at rest or during drug or exercise challenge), and non-PH","spans":[]},{"type":"paragraph","text":"was defined as mPAP <21 mmHg or tricuspid regurgitation velocity ≤2.8 m/s, if mPAP was not available. All","spans":[]},{"type":"paragraph","text":"patients were then randomly partitioned into training (48%), validation (12%) and test sets (40%) for building,","spans":[]},{"type":"paragraph","text":"optimizing and testing the models, respectively. Models were trained using electrocardiograms performed within","spans":[]},{"type":"paragraph","text":"1 month of PH diagnosis (diagnostic dataset) and performance was tested on the diagnostic dataset and on","spans":[]},{"type":"paragraph","text":"electrocardiograms from 6-18 months (pre-emptive dataset) and 36-60 months before diagnosis. Model","spans":[]},{"type":"paragraph","text":"performance was evaluated by calculating the area under the curve (AUC) of the receiver operating","spans":[]},{"type":"paragraph","text":"characteristic curve, sensitivity, specificity, and diagnostic odds ratios. In total, 56,612 unique patients","spans":[]},{"type":"paragraph","text":"were identified: 11,138 PH and 45,474 non-PH patients. Several model structures were tested, and the best","spans":[]},{"type":"paragraph","text":"performing were CNNs with residual connections incorporating the 12-lead voltage-time electrocardiogram data.","spans":[]},{"type":"paragraph","text":"The final model yielded an AUC, sensitivity and specificity, respectively, of 0.91, 83.5%, and 83.6% in the","spans":[]},{"type":"paragraph","text":"diagnostic test set and 0.86, 77.8% and 78.3% in the pre-emptive dataset (Table). AUC remained above 0.81 for","spans":[]},{"type":"paragraph","text":"detection of PH using electrocardiograms from 6-monthly intervals up to 5 years before diagnosis. Among the","spans":[]},{"type":"paragraph","text":"PH patients, 2,134 patients had pre-capillary PH, which includes some progressive but potentially treatable forms","spans":[]},{"type":"paragraph","text":"of PH, and AUC was 0.95 for detection of PH in this diagnostic dataset. The electrocardiogram","spans":[]},{"type":"paragraph","text":"algorithm was able to detect PH up to 5 years prior to diagnosis. This type of algorithm has the potential to","spans":[]},{"type":"paragraph","text":"accelerate diagnosis and management of PH.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"17e14179-c20e-419d-86a0-8e440b91fecd","url":"https://www.atsjournals.org/doi/pdf/10.1164/ajrccm-conference.2021.203.1_MeetingAbstracts.A1179"},"date":"2020-10-31T18:30:00+0000","algorithm":"Pulmonary Hypertension","publishedIn":"American Journal of Respiratory and Critical Care Medicine / American Thoracic Society (ATS) 2021 International Conference","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbYSBAAACMAC0pL","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbYSBAAACMAC0pL%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:14:05+0000","last_publication_date":"2022-07-20T07:59:05+0000","slugs":["automated-detection-of-low-ejection-fraction-from-a-one-lead-electrocardiogram-application-of-an-ai-algorithm-to-an-ecg-enabled-digital-stethoscope"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Automated Detection of Low Ejection Fraction from a One-lead Electrocardiogram: Application of an AI algorithm to an ECG-enabled Digital Stethoscope","spans":[]}],"abstract":[{"type":"paragraph","text":"ECG-enabled stethoscopes (ECG-Scope) acquire single lead ECGs during cardiac auscultation, and may facilitate real-time screening for pathologies not routinely identified by cardiac auscultation alone. Since we previously demonstrated an artificial intelligence (AI) algorithm can identify left ventricular dysfunction(LVSD) (defined as ejection fraction (EF) ≤ 40%) with an AUC of 0.91 using a 12 lead ECG, we conducted a prospective study to determine the efficacy of applying AI to an ECG-enabled Digital Stethoscope. We found that an AI algorithm applied to an ECG-enabled Digital Dtethoscope reliably detected the presence of a low EF in patients (AUC 0.91 when using the model to select recording automatically). The ability to screen patients with a possible low EF during routine physical examinations may facilitate rapid detection of LVSD.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"1810965d-9958-47cf-82e7-968eb71fef94","url":"https://academic.oup.com/ehjdh/advance-article/doi/10.1093/ehjdh/ztac030/6590492"},"date":"2022-05-22T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbl9RAAACIAC4lx","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbl9RAAACIAC4lx%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:12:24+0000","last_publication_date":"2022-07-20T09:13:23+0000","slugs":["development-of-the-ai-cirrhosis-ecg-ace-score-an-electrocardiogram-based-deep-learning-model-in-cirrhosis"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Development of the AI-Cirrhosis-ECG (ACE) Score: An electrocardiogram-based deep learning model in cirrhosis","spans":[]}],"abstract":[{"type":"paragraph","text":"Cirrhosis is associated with cardiac dysfunction and distinct ECG abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. A review of Mayo Clinic’s electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years of age who underwent liver transplantation (LT) at the three Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease, then divided into training, validation, and test sets using a 70%-10%-20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. Additionally, the association between the ACE score and the severity of patients’ liver disease was assessed. The model’s AUC in the testing set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing MELD-Na. Longitudinal trends in the ACE scores before and after LT mirrored the progression and resolution of liver disease. The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"d24aef03-9586-41ba-9159-89a0dac6b14d","url":"https://journals.lww.com/ajg/Abstract/9900/Development_of_the_AI_Cirrhosis_ECG__ACE__Score_.204.aspx"},"date":"2021-12-28T18:30:00+0000","algorithm":"Other Programs","publishedIn":"The American Journal of Gastroenterology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbfnhAAACMAC2w9","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbfnhAAACMAC2w9%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:45:21+0000","last_publication_date":"2022-07-20T09:09:08+0000","slugs":["artificial-intelligenceenabled-electrocardiograms-for-identification-of-patients-with-low-ejection-fraction-a-pragmatic-randomized-clinical-trial"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial intelligence–enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial","spans":[]}],"abstract":[{"type":"paragraph","text":"We have conducted a pragmatic clinical trial aimed to assess whether an electrocardiogram (ECG)-based, artificial intelligence (AI)-powered clinical decision support tool enables early diagnosis of low ejection fraction (EF), a condition that is underdiagnosed but treatable. In this trial (NCT04000087), 120 primary care teams from 45 clinics or hospitals were cluster-randomized to either the intervention arm (access to AI results; 181 clinicians) or the control arm (usual care; 177 clinicians). ECGs were obtained as part of routine care from a total of 22,641 adults (N = 11,573 intervention; N = 11,068 control) without prior heart failure. The primary outcome was a new diagnosis of low EF (≤50%) within 90 days of the ECG. The trial met the prespecified primary endpoint, demonstrating that the intervention increased the diagnosis of low EF in the overall cohort (1.6% in the control arm versus 2.1% in the intervention arm, odds ratio (OR) 1.32 (1.01–1.61), P = 0.007) and among those who were identified as having a high likelihood of low EF (that is, positive AI-ECG, 6% of the overall cohort) (14.5% in the control arm versus 19.5% in the intervention arm, OR 1.43 (1.08–1.91), P = 0.01). In the overall cohort, echocardiogram utilization was similar between the two arms (18.2% control versus 19.2% intervention, P = 0.17); for patients with positive AI-ECGs, more echocardiograms were obtained in the intervention compared to the control arm (38.1% control versus 49.6% intervention, P < 0.001). These results indicate that use of an AI algorithm based on ECGs can enable the early diagnosis of low EF in patients in the setting of routine primary care.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"214cfda3-3a5a-40f9-afce-0119b7e2abc1","url":"https://doi.org/10.1038/s41591-021-01335-4"},"date":"2021-05-05T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Nature Medicine","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtblNxAAACIAC4YM","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtblNxAAACIAC4YM%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:09:14+0000","last_publication_date":"2022-07-20T09:33:46+0000","slugs":["an-artificial-intelligenceenabled-ecg-algorithm-for-comprehensive-ecg-interpretation-can-it-pass-the-turing-test"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"An artificial intelligence–enabled ECG algorithm for comprehensive ECG interpretation: Can it pass the ‘Turing test’?","spans":[]}],"abstract":[{"type":"paragraph","text":"The objective of this study is to build infrastructure for digital trials to improve efficiency and generalizability and test it using a study to validate an artificial intelligence algorithm to detect atrial fibrillation (AF). We will prospectively enroll 1,000 patients who underwent an electrocardiogram for any clinical reason in routine practice, do not have a previous diagnosis of AF or atrial flutter and would be eligible for anticoagulation if AF is detected. Eligible patients will be identified using digital phenotyping algorithms, including natural language processing that runs on the electronic health records. Study invitations will be sent in batches via patient portal or letter, which will direct patients to a website to verify eligibility, learn about the study (including video-based informed consent), and consent electronically. The method aims to enroll participants representative of the general patient population, rather than a convenience sample of patients presenting to clinic. A device will be mailed to patients to continuously monitor for up to 30 days. The primary outcome is AF diagnosis and burden; secondary outcomes include patients' experience with the trial conduct methods and the monitoring device. The enrollment, intervention, and follow-up will be conducted remotely, ie, a patient-centered site-less trial. This is among the first wave of trials to adopt digital technologies, artificial intelligence, and other pragmatic features to create efficiencies, which will pave the way for future trials in a broad range of disease and treatment areas.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"92171faa-6805-4a03-92be-e7b2b9af6230","url":"https://www.cvdigitalhealthjournal.com/article/S2666-6936(21)00046-3/fulltext"},"date":"2021-05-04T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Cardiovascular Digital Health Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbcIxAAACMAC1vc","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbcIxAAACMAC1vc%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:30:30+0000","last_publication_date":"2022-07-20T08:04:23+0000","slugs":["application-of-artificial-intelligence-to-the-standard-12-lead-ecg-to-identify-people-with-left-ventricular-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Application Of Artificial Intelligence To The Standard 12 Lead Ecg To Identify People With Left Ventricular Dysfunction","spans":[]}],"abstract":[{"type":"paragraph","text":"Asymptomatic left ventricular dysfunction (ALVD) is present in 2-9% of the population, is associated with reduced longevity and is treatable when found. Inexpensive, reliable, in office screening is not available. The area under the curve (AUC) for a BNP screening blood test is 0.79 to 0.89. We hypothesized that use of artificial intelligence (AI) would enable the ECG, a ubiquitous, inexpensive test, to identify ALVD. Of the 51,979 patients tested, 4,064 (8%) had an EF< 35%. The AUC of the ROC was 0.93 (Fig). The sensitivity, specificity and accuracy were 85%, 86% and 86%, respectively. In patients with an abnormal AI screen but normal EF (false positives, 1317), 153 had at least one abnormal EF in the future (5 year incidence 10.1%). This five-fold increased risk of developing a future low EF suggests that the network may be detecting early, subclinical, metabolic or structural abnormalities that manifest in the ECG.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"aa95cb2b-1b43-4de5-981b-e7f0f717db8c","url":"https://www.jacc.org/doi/full/10.1016/s0735-1097%2818%2930847-7"},"date":"2018-02-28T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Journal of the Americal College of Cardiology (JACC) / ACC.18","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbbShAAACEAC1fg","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbbShAAACEAC1fg%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:26:54+0000","last_publication_date":"2022-07-20T08:02:34+0000","slugs":["prospective-validation-of-a-deep-learning-electrocardiogram-algorithm-for-the-detection-of-left-ventricular-systolic-dysfunction"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Prospective Validation of a Deep Learning Electrocardiogram Algorithm for the Detection of Left Ventricular Systolic Dysfunction","spans":[]}],"abstract":[{"type":"paragraph","text":"Patients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging. We applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. Among 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 “false-positives screens,” 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT-pro-BNP after the initial “positive screen.”","spans":[]}],"body":[],"link":{"link_type":"Web","key":"33ee8434-372d-47cb-b528-140b755263e1","url":"https://pubmed.ncbi.nlm.nih.gov/30821035/"},"date":"2019-02-27T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Journal of Cardiovascular Electrophysiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbkXRAAACIAC4Ij","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbkXRAAACIAC4Ij%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:05:36+0000","last_publication_date":"2022-07-20T09:31:37+0000","slugs":["artificial-intelligence-enhanced-screening-for-cardiac-amyloidosis-by-electrocardiography"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial-Intelligence Enhanced Screening For Cardiac Amyloidosis By Electrocardiography","spans":[]}],"abstract":[{"type":"paragraph","text":"Cardiac amyloidosis (CA) is a life-threatening disease with poor outcomes often related to delayed diagnosis. We developed an artificial-intelligence (AI) based screening tool that identifies CA from the 12 lead ECG as well as single and six lead acquisitions. We collected 12-lead ECG data for 2,541 patients with light chain (AL) or transthyretin (ATTR) CA seen at Mayo Clinic from 2000-2019. These cases were propensity score-matched on age and sex with 2,454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with a 999 (20%) threshold-tuning set and a 999 (20%) holdout test set. We performed experiments using single lead and six lead ECG subsets. The area under the receiver operating characteristic curve (AUC) was 0.92 (CI = 0.90-0.94) with a precision (positive predictive value) for detecting either AL or ATTR-CA of 0.87. Using a cut-off probability of 0.5, 424 (83%) of the hold-out patients with CA were detected by the model. Of the CA patients with pre-diagnosis ECG studies, in 47% the AI model successfully predicted the presence of CA >six months before the clinical diagnosis (Fig.1). The best single lead model was V5 with an AUC of 0.83 and a precision of 0.84, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.88 and a precision of 0.89. An AI-driven ECG screening tool can effectively detect CA and may promote early detection of this life-threatening disease.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"30e1d78c-43c1-470a-b3a4-66b4c8e6f8f2","url":"https://www.jacc.org/doi/full/10.1016/S0735-1097%2821%2901886-6"},"date":"2021-04-30T18:30:00+0000","algorithm":"Amyloidosis","publishedIn":"Journal of the Americal College of Cardiology (JACC) / ACC.21","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbe1hAAACMAC2ht","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbe1hAAACMAC2ht%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:42:01+0000","last_publication_date":"2022-07-20T08:10:11+0000","slugs":["artificial-intelligence-ecg-to-detect-left-ventricular-dysfunction-in-covid-19-a-case-series"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Artificial Intelligence ECG to Detect Left Ventricular Dysfunction in COVID-19: A Case Series","spans":[]}],"abstract":[{"type":"paragraph","text":"COVID-19 can result in deterioration of cardiac function, which is associated with high mortality. A simple point-of-care diagnostic test to screen for ventricular dysfunction would be clinically useful to guide management. We sought to review the clinical experience with an artificial intelligence electrocardiogram (AI ECG) to screen for ventricular dysfunction in patients with documented COVID-19. We examined all patients in the Mayo Clinic system who underwent clinically indicated electrocardiography and echocardiography within 2 weeks following a positive COVID-19 test and had permitted use of their data for research were included. Of the 27 patients who met the inclusion criteria, one had a history of normal ventricular function who developed COVID-19 myocarditis with rapid clinical decline. The initial AI ECG in this patient indicated normal ventricular function. Repeat AI ECG showed a probability of ejection fraction (EF) less than or equal to 40% of 90.2%, corroborated with an echocardiographic EF of 35%. One other patient had a pre-existing EF less than or equal to 40%, accurately detected by the algorithm before and after COVID-19 diagnosis, and another was found to have a low EF by AI ECG and echocardiography with the COVID-19 diagnosis. The area under the curve for detection of EF less than or equal to 40% was 0.95. This case series suggests that the AI ECG, previously shown to detect ventricular dysfunction in a large general population, may be useful as a screening tool for the detection of cardiac dysfunction in patients with COVID-19.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"1420797b-588e-415e-bd5e-23f156e0c951","url":"https://pubmed.ncbi.nlm.nih.gov/33153634/"},"date":"2020-10-31T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"Mayo Clinic Proceedings","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbj1xAAACIAC3-6","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbj1xAAACIAC3-6%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T17:03:22+0000","last_publication_date":"2022-07-20T09:30:22+0000","slugs":["electrocardiogram-screening-for-aortic-valve-stenosis-using-artificial-intelligence"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Electrocardiogram screening for aortic valve stenosis using artificial intelligence","spans":[]}],"abstract":[{"type":"paragraph","text":"Early detection of aortic stenosis (AS) is becoming increasingly important with a better outcome after aortic valve replacement in asymptomatic severe AS patients and a poor outcome in moderate AS. We aimed to develop artificial intelligence-enabled electrocardiogram (AI-ECG) using a convolutional neural network to identify patients with moderate to severe AS. Between 1989 and 2019, 258 607 adults [mean age 63 ± 16.3 years; women 122 790 (48%)] with an echocardiography and an ECG performed within 180 days were identified from the Mayo Clinic database. Moderate to severe AS by echocardiography was present in 9723 (3.7%) patients. Artificial intelligence training was performed in 129 788 (50%), validation in 25 893 (10%), and testing in 102 926 (40%) randomly selected subjects. In the test group, the AI-ECG labelled 3833 (3.7%) patients as positive with the area under the curve (AUC) of 0.85. The sensitivity, specificity, and accuracy were 78%, 74%, and 74%, respectively. The sensitivity increased and the specificity decreased as age increased. Women had lower sensitivity but higher specificity compared with men at any age groups. The model performance increased when age and sex were added to the model (AUC 0.87), which further increased to 0.90 in patients without hypertension. Patients with false-positive AI-ECGs had twice the risk for developing moderate or severe AS in 15 years compared with true negative AI-ECGs (hazard ratio 2.18, 95% confidence interval 1.90–2.50). An AI-ECG can identify patients with moderate or severe AS and may serve as a powerful screening tool for AS in the community.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"fadb3de1-947a-4406-9c46-fe3ccc8e4116","url":"https://doi.org/10.1093/eurheartj/ehab153"},"date":"2021-03-21T18:30:00+0000","algorithm":"Aortic Stenosis","publishedIn":"European Heart Journal","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbfIBAAACIAC2nG","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbfIBAAACIAC2nG%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:43:16+0000","last_publication_date":"2022-07-20T08:10:54+0000","slugs":["left-ventricular-systolic-dysfunction-identification-using-artificial-intelligence-augmented-electrocardiogram-in-cardiac-intensive-care-unit-patients"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Left ventricular systolic dysfunction identification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients","spans":[]}],"abstract":[{"type":"paragraph","text":"An artificial intelligence-augmented electrocardiogram (AI-ECG) can identify left ventricular systolic dysfunction (LVSD). We examined the accuracy of AI ECG for identification of LVSD (defined as LVEF ≤40% by transthoracic echocardiogram [TTE]) in cardiac intensive care unit (CICU) patients. We included unique Mayo Clinic CICU patients admitted from 2007 to 2018 who underwent AI-ECG and TTE within 7 days, at least one of which was during hospitalization. Discrimination of the AI-ECG for LVSD was determined using receiver-operator characteristic curve (AUC) values. We included 5680 patients with a mean age of 68 ± 15 years (37% females). Acute coronary syndrome (ACS) was present in 55%. LVSD was present in 34% of patients (mean LVEF 48 ± 16%). The AI-ECG had an AUC of 0.83 (95% confidence interval 0.82–0.84) for discrimination of LVSD. Using the optimal cut-off, the AI-ECG had 73%, specificity 78%, negative predictive value 85% and overall accuracy 76% for LVSD. AUC values were higher for patients aged <70 years (0.85 versus 0.80), males (0.84 versus 0.79), patients without ACS (0.86 versus 0.80), and patients who did not undergo revascularization (0.84 versus 0.80). The AI-ECG algorithm had very good discrimination for LVSD in this critically-ill CICU cohort with a high prevalence of LVSD. Performance was better in younger male patients and those without ACS, highlighting those CICU patients in whom screening for LVSD using AI ECG may be more effective.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"73e17c16-57e8-4e79-bb4b-7e4a2a796c76","url":"https://doi.org/10.1016/j.ijcard.2020.10.074"},"date":"2020-11-01T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"International Journal of Cardiology","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"Ytbb3hAAACAAC1qZ","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ytbb3hAAACAAC1qZ%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:29:21+0000","last_publication_date":"2022-07-20T08:03:50+0000","slugs":["assessment-of-disease-status-and-treatment-response-with-artificial-intelligenceenhanced-electrocardiography-in-obstructive-hypertrophic-cardiomyopathy"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Assessment of Disease Status and Treatment Response With Artificial Intelligence−Enhanced Electrocardiography in Obstructive Hypertrophic Cardiomyopathy","spans":[]}],"abstract":[{"type":"paragraph","text":"Although hypertrophic cardiomyopathy (HCM) causes significant morbidity and is a leading cause of sudden death in adolescents, initial detection remains difficult. Echocardiography is an important diagnostic modality for HCM, but since the electrocardiogram (ECG) is more widely accessible, we created an ECG-based AI algorithm to achieve a fully automated diagnosis of HCM. We ran the AI-ECG algorithms on ECGs from a pre-treatment group and an on-treatment group from the phase 2 PIONEER-OLE trial of the cardiac myosin inhibitor, mavacamten in patients with obstructive HCM. We found that AI-ECG HCM scores correlated with disease status in patients with obstructive HCM on mavacamten treatment. Disease status was measured by decreases over time in left ventricular outflow tract gradients and NT-proBNP levels. Therefore, AI-ECGs might hold promise as a potential tool for monitoring disease status, cardiac hemodynamics, and drug therapeutic response.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"099cedad-382f-4621-90aa-438b4ac92c32","url":"https://www.jacc.org/doi/abs/10.1016/j.jacc.2022.01.005"},"date":"2022-02-28T18:30:00+0000","algorithm":"Hypertrophic Cardiomyopathy","publishedIn":"Journal of the Americal College of Cardiology (JACC)","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}},{"id":"YtbbnBAAACMAC1ld","uid":null,"url":null,"type":"publication","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YtbbnBAAACMAC1ld%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-19T16:28:15+0000","last_publication_date":"2022-07-20T08:03:09+0000","slugs":["point-of-care-screening-for-heart-failure-with-reduced-ejection-fraction-using-artificial-intelligence-during-ecg-enabled-stethoscope-examination-in-london-uk-a-prospective-observational-multicentre-study"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"title":[{"type":"heading1","text":"Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study","spans":[]}],"abstract":[{"type":"paragraph","text":"Most patients who have heart failure with a reduced ejection fraction, when left ventricular ejection fraction (LVEF) is 40% or lower, are diagnosed in hospital. This is despite previous presentations to primary care with symptoms. We aimed to test an artificial intelligence (AI) algorithm applied to a single-lead ECG, recorded during ECG-enabled stethoscope examination, to validate a potential point-of-care screening tool for LVEF of 40% or lower. We conducted an observational, prospective, multicentre study of a convolutional neural network (known as AI-ECG) that was previously validated for the detection of reduced LVEF using 12-lead ECG as input. We used AI-ECG retrained to interpret single-lead ECG input alone. Patients (aged ≥18 years) attending for transthoracic echocardiogram in London (UK) were recruited. All participants had 15 s of supine, single-lead ECG recorded at the four standard anatomical positions for cardiac auscultation, plus one handheld position, using an ECG-enabled stethoscope. Transthoracic echocardiogram-derived percentage LVEF was used as ground truth. The primary outcome was performance of AI-ECG at classifying reduced LVEF (LVEF ≤40%), measured using metrics including the area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity, with two-sided 95% CIs. The primary outcome was reported for each position individually and with an optimal combination of AI-ECG outputs (interval range 0–1) from two positions using a rule-based approach and several classification models. Between Feb 6 and May 27, 2021, we recruited 1050 patients (mean age 62 years [SD 17·4], 535 [51%] male, 432 [41%] non-White). 945 (90%) had an ejection fraction of at least 40%, and 105 (10%) had an ejection fraction of 40% or lower. Across all positions, ECGs were most frequently of adequate quality for AI-ECG interpretation at the pulmonary position (979 [93·3%] of 1050). Quality was lowest for the aortic position (846 [80·6%]). AI-ECG performed best at the pulmonary valve position (p=0·02), with an AUROC of 0·85 (95% CI 0·81–0·89), sensitivity of 84·8% (76·2–91·3), and specificity of 69·5% (66·4–72·6). Diagnostic odds ratios did not differ by age, sex, or non-White ethnicity. Taking the optimal combination of two positions (pulmonary and handheld positions), the rule-based approach resulted in an AUROC of 0·85 (0·81–0·89), sensitivity of 82·7% (72·7–90·2), and specificity of 79·9% (77·0–82·6). Using AI-ECG outputs from these two positions, a weighted logistic regression with l2 regularisation resulted in an AUROC of 0·91 (0·88–0·95), sensitivity of 91·9% (78·1–98·3), and specificity of 80·2% (75·5–84·3). A deep learning system applied to single-lead ECGs acquired during a routine examination with an ECG-enabled stethoscope can detect LVEF of 40% or lower. These findings highlight the potential for inexpensive, non-invasive, workflow-adapted, point-of-care screening, for earlier diagnosis and prognostically beneficial treatment.","spans":[]}],"body":[],"link":{"link_type":"Web","key":"d1d1b387-e642-4440-9ff4-c9e75961c6e0","url":"https://www.thelancet.com/journals/landig/article/PIIS2589-7500(21)00256-9/fulltext"},"date":"2022-01-04T18:30:00+0000","algorithm":"Low Ejection Fraction","publishedIn":"The Lancet Digital Health","publishedInDetails":[],"datePublished":null,"postedIn":[],"datePosted":null,"sourceLogo":{},"paperImage":{},"downloadPdf":{"link_type":"Media"},"authors":null,"authorsInstituteAddress":null,"correspondenceTo":null,"citedBy":[],"televisionCoverageIn":null,"featuredIn":[],"affiliationsText":[],"affiliations":{},"copyright":null,"usecase":[],"focusArea":[],"institutionalAuthors":[],"publicationTypes":[],"slices":[]}}],"theme":{"id":"Ysjy1BAAACIAWvti","uid":null,"url":null,"type":"theme","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ysjy1BAAACIAWvti%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-09T03:15:35+0000","last_publication_date":"2022-11-18T03:39:07+0000","slugs":["theme"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"facebook":null,"twitter":"https://twitter.com/anumanainc","linkedIn":"https://www.linkedin.com/company/anumana-inc","YouTube":"https://www.youtube.com/channel/UCZlMq0PGtuZg3hLPJaVIetA"}},"mainMenu":{"id":"YsjzBRAAACMAWvxJ","uid":null,"url":null,"type":"main-menu","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22YsjzBRAAACMAWvxJ%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-09T03:16:24+0000","last_publication_date":"2024-03-19T03:14:00+0000","slugs":["main-menu"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"links":[{"link":{"id":"ZGExlxEAACIAobEi","type":"page","tags":[],"lang":"en-us","slug":"anumanas-platform","first_publication_date":"2023-05-15T01:37:44+0000","last_publication_date":"2024-02-05T19:17:13+0000","uid":"platform","link_type":"Document","key":"80d69979-6f72-4ebe-8f9a-f536e0120d1c","isBroken":false},"linkText":"Platform"},{"link":{"id":"ZQsZnxAAACcAgNBS","type":"page","tags":[],"lang":"en-us","slug":"-","first_publication_date":"2023-10-02T10:45:01+0000","last_publication_date":"2024-04-11T14:32:31+0000","uid":"ecg-ai-lef","link_type":"Document","key":"3ecaa596-4547-48c3-bab5-63ec6bdca46f","isBroken":false},"linkText":"ECG-AI™ LEF"},{"link":{"id":"Zffi1xIAAExWcRys","type":"submenu","tags":[],"lang":"en-us","slug":"publications","first_publication_date":"2024-03-18T06:47:24+0000","last_publication_date":"2024-03-19T03:31:41+0000","link_type":"Document","key":"b45dec86-c31d-4f05-a1af-1261b737598e","isBroken":false},"linkText":"Resources"},{"link":{"id":"YskDARAAACEAW0KU","type":"page","tags":[],"lang":"en-us","slug":"-","first_publication_date":"2022-07-09T04:24:35+0000","last_publication_date":"2024-04-19T15:58:27+0000","uid":"pipeline","link_type":"Document","key":"40956f31-6c2c-435e-8eaa-b54b0f639382","isBroken":false},"linkText":"Pipeline"},{"link":{"id":"YskDdxAAACEAW0Sm","type":"page","tags":[],"lang":"en-us","slug":"news","first_publication_date":"2022-07-09T04:26:35+0000","last_publication_date":"2022-07-09T04:26:35+0000","uid":"newsroom","link_type":"Document","key":"bc7a7aa7-4c55-4554-9d63-3599e302a82d","isBroken":false},"linkText":"News"},{"link":{"id":"YskDyBAAACEAW0YV","type":"page","tags":[],"lang":"en-us","slug":"about-us","first_publication_date":"2022-07-09T04:27:55+0000","last_publication_date":"2025-01-09T12:30:08+0000","uid":"about-us","link_type":"Document","key":"f6dd034e-c444-4caf-8b91-2acd97eb08e8","isBroken":false},"linkText":"Team"}]}},"footer":{"id":"Ysjy9xAAACIAWvwC","uid":null,"url":null,"type":"footer","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ysjy9xAAACIAWvwC%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-09T03:16:10+0000","last_publication_date":"2023-10-02T10:45:01+0000","slugs":["footer"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"leadFormTitle":[{"type":"heading2","text":"Download Our One-Pager","spans":[]}],"leadFormDescription":[{"type":"paragraph","text":"Featuring key corporate highlights and an overview of Anumana's technology","spans":[]}],"leadFormButtonText":"Submit and Download","onePager":{"link_type":"Media","key":"a54ac2d1-bc50-4d53-84d8-de2b2c81d2ba","kind":"file","id":"ZRpIYhAAACUAxgsk","url":"https://anumana.cdn.prismic.io/anumana/2c68fa77-c554-4f8e-8119-90bf7b422c79_2023-10-01_Corporate+One-Pager_Q4.pdf","name":"2023-10-01_Corporate One-Pager_Q4.pdf","size":"2679929"},"menu1":[{"link":{"id":"YskEBhAAACMAW0cm","type":"page","tags":[],"lang":"en-us","slug":"privacy-policy","first_publication_date":"2022-07-09T04:28:57+0000","last_publication_date":"2022-07-09T04:43:54+0000","uid":"privacy-policy","link_type":"Document","key":"abe54877-a8c5-4fdc-be2d-6822bf44c017","isBroken":false},"linkText":"Privacy Policy"},{"link":{"id":"YskEOBAAACAAW0gL","type":"page","tags":[],"lang":"en-us","slug":"terms-of-use","first_publication_date":"2022-07-09T04:29:47+0000","last_publication_date":"2022-07-09T04:45:11+0000","uid":"terms-of-use","link_type":"Document","key":"46539aea-ae6e-4ca9-bd29-837a4fd80189","isBroken":false},"linkText":"Terms of Use"},{"link":{"id":"ZLFTQRIAACIAb_6E","type":"page","tags":[],"lang":"en-us","slug":"vulnerability-disclosure","first_publication_date":"2023-07-14T13:59:36+0000","last_publication_date":"2023-07-14T15:21:42+0000","uid":"vulnerability-disclosure","link_type":"Document","key":"56845587-89b2-476e-9fe4-567496127064","isBroken":false},"linkText":"Vulnerability Disclosure"}],"menu2":[{"link":{"id":"YskDARAAACEAW0KU","type":"page","tags":[],"lang":"en-us","slug":"-","first_publication_date":"2022-07-09T04:24:35+0000","last_publication_date":"2024-04-19T15:58:27+0000","uid":"pipeline","link_type":"Document","key":"7c22d31b-9d48-4831-8802-730823c6a993","isBroken":false},"linkText":"Pipeline"},{"link":{"id":"YskDMBAAACAAW0Np","type":"page","tags":[],"lang":"en-us","slug":"publications","first_publication_date":"2022-07-09T04:25:32+0000","last_publication_date":"2022-07-09T04:26:57+0000","uid":"publications","link_type":"Document","key":"326731cf-22e7-4f1f-b89d-35e32ba751b7","isBroken":false},"linkText":"Publications"},{"link":{"id":"YskDdxAAACEAW0Sm","type":"page","tags":[],"lang":"en-us","slug":"news","first_publication_date":"2022-07-09T04:26:35+0000","last_publication_date":"2022-07-09T04:26:35+0000","uid":"newsroom","link_type":"Document","key":"ab6ba702-e5bd-4034-9088-71748aa78d3d","isBroken":false},"linkText":"News"},{"link":{"id":"YskDyBAAACEAW0YV","type":"page","tags":[],"lang":"en-us","slug":"about-us","first_publication_date":"2022-07-09T04:27:55+0000","last_publication_date":"2025-01-09T12:30:08+0000","uid":"about-us","link_type":"Document","key":"e1ce3f9f-db46-4ce8-88ed-edddeb54e18d","isBroken":false},"linkText":"Team"},{"link":{"id":"YzHf7BMAALxVR7ms","type":"page","tags":[],"lang":"en-us","slug":"careers","first_publication_date":"2022-09-26T20:53:05+0000","last_publication_date":"2023-03-15T19:42:14+0000","uid":"careers","link_type":"Document","key":"0beb99fc-5452-46eb-8c4e-bb32dd405b39","isBroken":false},"linkText":"Careers"}]}},"banner":{"id":"Ysjy6BAAACAAWvu_","uid":null,"url":null,"type":"announcement-banner","href":"https://anumana.cdn.prismic.io/api/v2/documents/search?ref=Z5IFKhkAAEYA5duG&q=%5B%5B%3Ad+%3D+at%28document.id%2C+%22Ysjy6BAAACAAWvu_%22%29+%5D%5D","tags":[],"first_publication_date":"2022-07-09T03:15:55+0000","last_publication_date":"2025-01-07T12:34:13+0000","slugs":["announcement-banner"],"linked_documents":[],"lang":"en-us","alternate_languages":[],"data":{"enabled":true,"message":[{"type":"paragraph","text":"Anumana and AliveCor Collaborate to Advance AI for Cardiology","spans":[],"direction":"ltr"}],"buttonText":"See Release","buttonLink":{"link_type":"Web","key":"fb77a92c-4212-491a-85f6-0cb8a5584175","url":"https://anumana.ai/newsroom/Z3wWLBoAAEgAkMd5"}}}},"__N_SSG":true}