AI analysis of ECG data measured by smartwatch may help detect reduced heart pumping function

A preliminary study presented at the American Heart Association's Scientific Sessions 2026 suggests that artificial intelligence (AI) software analyzing ECG data from smartwatches could potentially identify a dangerous heart condition called left ventricular systolic dysfunction (LVSD). LVSD occurs when the heart's main pumping chamber, the left ventricle, does not contract effectively, leading to reduced ejection fraction of 40% or less.

The researchers developed a novel AI model to analyze smartwatch ECG recordings for signs of reduced heart pumping function. However, the study found that AI classifications differed between smartwatch brands in 9% of the 2,211 adults examined. In 108 home users, requiring repeated positive results reduced false positives but also missed two additional cases of LVSD.

The study's lead author, Hak Seung Lee, a cardiologist at the Digital Healthcare Institute, emphasized that a single smartwatch ECG is a snapshot and that repeated recordings can yield different results. While the AI analysis detected LVSD, the classification varied between watches. Requiring repeated positive results helped reduce false positives but may have missed some additional cases.

Further research is needed to determine the optimal use of AI analysis of smartwatch ECGs to guide further evaluation for LVSD and other heart conditions. The findings may not generalize beyond patients referred for echocardiography.