AI Applied to Apple Watch ECG Can ID Ejection Fraction ≤40 percent | Health

FRIDAY, May 13, 2022 (HealthDay News) — Single-lead electrocardiograms (ECGs) from an Apple Watch, interpreted by an artificial intelligence (AI) algorithm, can identify an ejection fraction of ≤40 percent, according to a study presented at the annual meeting of the Heart Rhythm Society, held April 29 to May 1 in San Francisco.

Itzhak Zachi Attia, Ph.D., of the Mayo Clinic in Rochester, Minnesota, and colleagues enrolled and followed subjects to study the use of a single-lead Apple Watch EKG to screen and monitor individuals. A total of 2,454 people downloaded the study app. View EKGs obtained within one month of a clinically graded echocardiogram were analyzed for the presence of an ejection fraction ≤40 percent by AI using a single-lead model.

Subjects were enrolled from 46 states and 11 countries. The researchers found that 92 percent of participants used the app more than once (an average of 2.1 per month). Subjects sent 125,610 EKGs between August 2021 and February 2022. A total of 421 subjects had at least one sinus rhythm EKG within 30 days of an echocardiogram. Of these, 16 (3.8 percent) had an ejection fraction ≤40 percent. Thirteen of the 16 patients with low ejection fraction were identified by the watch’s AI ECG, which had an area under the receiver performance characteristic curve of 0.875, and sensitivity and specificity of 81.2 and 81.3 percent, respectively.

“Although our data is early, the test had an area under the curve of 0.88, meaning it’s as good or slightly better than a medical treadmill test,” Attia said in a statement. “AI analysis of the watch EKG is a powerful test to identify a weak heart pump.”

Leave a Comment