Role of Coexisting ECG Anomalies in the Accuracy of Smartwatch ECG Detection of Atrial Fibrillation

Smartwatch electrocardiography (ECG) may be used to detect atrial fibrillation (AF), but its accuracy has been validated in only a limited number of patients with similar clinical profiles. We tested the accuracy of the Apple Watch ECG to detect AF in 734 patients (21% were in AF) with various ECG anomalies. The risk of having false positive automated AF detection was higher for patients with premature complexes, sinus node dysfunction, and atrioventricular (AV) block, and the risk of having false negative tracings was associated with broad QRScomplexes and pacing. In these patients, detection of AF by an automatic smartwatch algorithm is challenging.