Smart watch for the detection of exercise-induced transient ST segment changes

Abstract Background Smartwatches are largely used and allowed to perform electrocardiogram one lead, usually a modified DI, used to diagnose atrial fibrillation. It is unknown whether or not smartwatches could be used to identify electrocardiographic transient ST changes during exercise-induced myocardial ischemia. The present study assessed the feasibility and reliability of using an Apple watch to record V5 in subjects scheduled for standard ECG stress tests. Methods One hundred eighty-nine subjects were included in this study. The mean age was 61+9 years, and 21.6 % were women (41 subjects). A single thoracic lead V5 was obtained with an Apple watch, positioned at the fifth intercostal space anterior axillary line, by creating a circuit between the back of the watch and the right index resting on the crown for 30 seconds. Four subjects were excluded because of the poor quality of the Apple watch signal. Forty-nine patients (25,92%) had a positive stress test with standard 12 lead ECG, 136 (71,96 %) negative stress test, and 4 (2,12%) the ECGs were non-diagnostic. The mean difference or bias between the Apple Watch and standard exercise-induced ST changes was quantified as 0.054, suggesting a generally minimal discrepancy in their readings. This consistency is critically affirmed by Cohen's Kappa (k) coefficient of 0.665. 9-1.0) Results A total of 189 subjects were included in the study; the mean age was 61 years (SD 9), and 21.6 % were women (41 subjects). Insightful outcomes were gleaned from the Bland-Altman analysis, which probed the concordance between the smartwatch ECG and the conventional standard ECG in measuring ST-segment deviations (Bias 0,054; SD 0.31, from -0.56 to 0.67, 95% limits of agreement), as vividly depicted in Figure. The dashed blue lines in Figure demarcate the 95% limits of agreement, which span from -0.56 to 0.67, offering a tangible visualization of the range within which most individual differences resided. A notable harmony was unveiled in the intricate exploration of the concordance between the two diagnostic methodologies, substantiated by an agreement of 87.6%. This demonstrates that, in most instances, the methodologies provided analogous results, exhibiting a commendable consistency between them in a substantial proportion of cases. Assuming the results of standard ECGs as the reference values, Apple Watch ST deviation showed a sensitivity of 69% and specificity of 94 %. The positive predictive value was 0.80952381, and the negative predictive value was 0,8951049. Conclusions In conclusion, this study demonstrated that the Apple Watch could detect transient ST changes with a sensitivity of 69% and a specificity of 94 %. Further prospective studies should be performed to assess the potential role of detecting transient myocardial ischemia with a smartwatch in a general population at risk.