In summary, the present study applied AI to an Apple Watch ECG acquired in nonclinical environments, demonstrating its utility for effective identification of left ventricular dysfunction, a potentially life-threatening and often asymptomatic disease. In contrast to consumer-based trials, clinic-enrolled patients remained highly engaged. This suggests an opportunity to use AI in remote care and to clinically validate AI-ECG models in geographically dispersed populations at lower cost using patients’ own devices, in a potentially massively scalable manner that could improve quality of life, lower cost through earlier detection and strengthen patient engagement.
