Artificial-Intelligence Enhanced Screening For Cardiac Amyloidosis By Electrocardiography

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.