Results of Smartwatch-Based ECG Assessing Heart Rhythm Often Inconclusive

The use of smartwatches to detect cardiac issues, like atrial fibrillation (AFib), presents exciting new possibilities for heart care, but a new study shows that the results they provide may not always be accurate.

Published in the Canadian Journal of Cardiology, the study examined how accurately the Apple Watch's electrocardiogram (ECG) feature detected AFib in 734 patients with different ECG anomalies. About 21 percent of the patients had the condition.

The Apple Watch's ECG app records the user's heartbeat through the smartwatch's electrical heart sensor. The app then analyzes the recordings to detect irregular heart rhythms, also known as AFib.

Prior research has shown the Apple Watch can accurately diagnose the condition "in a limited number of patients with similar clinical profiles," said lead investigator Marc Strik, MD, PhD, of the LIRYC institute, Bordeaux University Hospital, in France, in a press release. "We tested the accuracy of the Apple Watch ECG app to detect AF[ib] in patients with a variety of coexisting ECG abnormalities."

In the recently published study, each patient underwent a 12-lead ECG, followed by a 30-second Apple Watch recording. Researchers classified the smartwatch's automated AFib diagnoses, based on its single-lead ECG, into three groups: "no signs of atrial fibrillation," "atrial fibrillation," or "inconclusive reading," the press release notes. Two electrophysiologists also conducted blinded interpretations of the Apple Watch recordings.

The study shows that the smartwatch ECG did not produce an automatic diagnosis for one in five patients.

Further, the Apple Watch app correctly identified 78 percent of the patients with AFib and 81 percent of those without the condition. Meanwhile, the electrophysiologists accurately determined 97 percent of the patients with AFib and 89 percent without.

Researchers found that patients with premature atrial and ventricular contractions (PACs/PVCs), sinus node dysfunction, and second-or third-degree atrioventricular block had a higher likelihood of a false positive ECG result. Patients with PVCs had three times higher odds of getting false positive AFib diagnoses from the smartwatch ECG.

In addition, researchers noted that the smartwatch ECG's ability to identify patients with atrial tachycardia (AT) and atrial flutter (AFL) was poor.

"Ideally, an algorithm would better discriminate between PVCs and AF[ib]," Strik said. "Any algorithm limited to the analysis of cycle variability will have poor accuracy in detecting AT/AFL. Machine learning approaches may increase smartwatch AF[ib] detection accuracy in these patients."

Andrés F. Miranda-Arboleda, MD, and Adrian Baranchuk, MD, of the cardiology division at Kingston Health Science Center, in Canada, wrote an editorial to accompany the study in which they noted the limitations of smartwatch capabilities in AFib detection and the need for more advanced algorithms.

"In a certain manner, the smartwatch algorithms for the detection of AF[ib] in patients with cardiovascular conditions are not yet smart enough. But they may soon be," they wrote.

Wearables use in healthcare is on the rise, with 90 percent of those who own these devices saying they use them to track fitness and monitor health, a recent survey shows. About 40 percent of survey respondents said they used their wearable device to track heart health.