Study Finds Poor Accuracy In Smartwatch-Based ECG Assessments

A recent study published in the Canadian Journal of Cardiology suggests that the results smartwatches offer may not always be reliable, despite the fact that using them to identify cardiac conditions like atrial fibrillation (AFib) opens up intriguing new options for heart care. Using the Apple Watch’s electrical heart sensor, the electrocardiogram (ECG) application monitor’s the user’s heartbeat. The program then examines the recorded data to identify abnormal heart rhythms. The study was conducted in order to evaluate the Apple Watch’s  ECG feature’s ability to reliably identify AFib in its users. The study consisted of 734 patients, approximately a fifth of which had the condition. 

According to earlier studies, the Apple Watch can correctly identify the condition.“Earlier studies have validated the accuracy of the Apple Watch for the diagnosis of AF in a limited number of patients with similar clinical profiles,” explained lead investigator Marc Strik, MD, PhD, LIRYC institute, Bordeaux University Hospital, Bordeaux, France. “We tested the accuracy of the Apple Watch ECG app to detect AF in patients with a variety of coexisting ECG abnormalities.”

To test the Apple Watch’s accuracy, a 12-lead ECG was performed on each patient, which was immediately followed by a 30-second Apple Watch recording. Atrial fibrillation, no symptoms of atrial fibrillation, or an “inconclusive reading” were the three categories for the smartwatch’s automatic single-lead ECG AF detections. Smartwatch recordings were then provided to an electrophysiologist who subsequently performed a blinded interpretation. Each tracing was then assigned a diagnosis of “AF,” “absence of AF”, or “diagnosis unclear”. Finally, a second blinded electrophysiologist analyzes 100 randomly chosen traces in order to determine the extent to which the assessors agreed. 

According to the research, just one in five patients received an automatic diagnosis from the smartwatch ECG. Furthermore, 78 percent of patients with AFib and 81 percent of patients without the condition were properly diagnosed by the Apple Watch software. Electrophysiologists correctly identified 89 percent of individuals without AFib and 97 percent of patients with AFib. In addition, Researchers discovered that patients with sinus node dysfunction, second- or third-degree atrioventricular block, premature atrial and ventricular contractions (PACs/PVCs), and sinus node dysfunction were more likely to have a false positive ECG result. The likelihood that a false positive AFib diagnosis would result from the smartwatch ECG was three times higher in patients with PVCs. Finally, the researchers found that the wristwatch ECG had a poor capacity to detect individuals with atrial tachycardia (AT) and atrial flutter (AFL).