Feasibility of Remote Monitoring for Fatal Coronary Heart Disease using Apple Watch ECGs

Abstract

BackgroundFatal Coronary Heart Disease (FCHD) is often described as sudden cardiac death (affects >4 million people/year), where coronary artery disease is the only identified condition. Electrocardiographic-Artificial Intelligence (ECG-AI) models for FCHD risk prediction using ECG data from wearable devices could enable wider screening/monitoring efforts. ObjectivesTo develop a single-lead ECG-based deep learning model for FCHD risk prediction and assess concordance between clinical and Apple Watch ECGs. MethodsA FCHD single-lead (‘Lead I’ from 12-Lead ECGs) ECG-AI model was developed using 167,662 ECGs (50,132 patients) from the University of Tennessee Health Sciences Center. 80% of the data (five-fold cross-validation) was used for training and 20% as a holdout. Cox Proportional Hazard (CPH) models incorporating ECG-AI predictions with age, sex and race were also developed. The models were tested on paired clinical single-lead and Apple Watch ECGs from 243 St. Jude Life Cohort participants. The correlation and concordance of the predictions were assessed using Pearson’s correlation(R), Spearman’s correlation(ρ) and Cohen’s Kappa. ResultsThe ECG-AI and CPH models resulted in AUCs=0.76 and 0.79, respectively, on the 20% holdout and AUC=0.85 and 0.87 on the AHWFB external validation data. There was moderate-strong positive correlation between predictions (R=0.74, ρ=0.67 and Kappa=0.58) when tested on the 243 paired ECGs. The clinical (Lead I) and Apple Watch predictions led to the same low/high risk FCHD classification for 99% of the participants. CPH prediction correlation resulted in a R=0.81, ρ=0.76 and Kappa=0.78. ConclusionRisk of FCHD can be predicted from single-lead ECGs obtained from wearable devices and are statistically concordant with Lead I of a 12-lead ECG.