Breakthrough Software as a Medical Device (SaMD) to aid clinicians in detecting low ejection fraction (LEF) earlier than ever before
ECG-AI LEF: FDA cleared AI algorithm to detect low left ventricular ejection fraction
ECG-AI LEF is an algorithm developed in partnership with Mayo Clinic and nference
State-of-the-art deep learning model developed using over 100,000 ECGs and echo data pairs from unique patients
Early versions of ECG-AI LEF Evaluated in 25+ studies involving >40,000 patients in the U.S. and internationally
PHI secure and compliant, and seamlessly integrates into existing clinical workflows
Anumana's ECG-AI LEF can detect low EF earlier, without the onset of clear symptoms or conventionally identified ECG abnormalities
Heart failure is a progressive condition affecting over 6 million people in the U.S.1 Early intervention can improve outcomes, but detection of early heart failure is challenging as patients are often asymptomatic or present non-specific symptoms.2 Identification of patients with LEF (EF≤40%) can enable clinicians to intervene earlier and prevent the progression of the disease.3 An echocardiogram, while capable of diagnosing LEF, necessitates a clear indication of cardiac abnormalities for scheduling, often entails extended waiting periods, and demands significant resources, potentially resulting in diagnostic delays.
ECG-AI LEF represents a groundbreaking shift in ECG interpretation. The ECG is a widely utilized and swiftly administered test, used in both primary and specialized healthcare settings. While it generates intricate patterns across its 12 leads, the majority of clinicians and ECG analysis machines are trained to use simple sets of rules to identify signs of disease using ECG. In early heart failure stages, ECG-AI's ability to detect subtle yet complex ECG patterns surpasses those of conventional interpretation standards.
References:
ECG-AI LEF is a highly effective screening tool for identifying low EF and has the potential to uncover significantly more low EF cases than echocardiograms alone
In a multi-site, geographically-diverse, retrospective validation study with 16,000 patients, ECG-AI LEF demonstrated:
Sensitivity | Specificity | |
---|---|---|
Overall | 84.5% | 83.6% |
EAGLE Study:4
22,000+
Patients
120
Primary Care Teams
31% Increase
LEF Detection
In a prospective, randomized, controlled trial of 22,000+ individuals across 120 primary care teams, the investigational version of the ECG-AI LEF demonstrated 31% increase in LEF detection compared to standard of care, without increasing use of echocardiography, where the majority of patients received additional treatments.
Learn moreReferences:
Anumana’s ECG-AI LEF solution can be integrated with any ECG information management system or directly with any institution’s existing EHR on a zero-footprint dashboard (ECG Viewer).
ECG Viewer is a web based dashboard with a secure and compliant infrastructure that displays a patient’s ECG history and real-time ECG-AI results to support clinical decision making.
Prior standard 12L ECGs and displays results in patient timeline
Anumana received two Category III CPT® codes from the American Medical Association effective as of January 1 2023.
The approval of these codes is a major milestone for AI in cardiology, recognizing Anumana’s ECG-AI as innovative solutions necessitating the creation of a new procedure category.
Code | Description |
---|---|
+0764T | Assistive algorithmic ECG risk-based assessment from concurrently performed ECGs. |
0765T | Assistive algorithmic ECG risk-based assessment from previously performed ECGs. |
Featuring key corporate highlights and an overview of Anumana's technology
@2023 anumana, Inc. All rights reserved.