Versions :<12345Live
Snapshot 5:Tue, Sep 1, 2026 7:48:21 PM GMT last edited by Nick

Study: AI Detects Heart Failure via ECG in Under 2 Seconds

Study: AI Detects Heart Failure via ECG in Under 2 Seconds

Could this ease heart-test backlogs or fail to hold up in the real world?
Study: AI Detects Heart Failure via ECG in Under 2 Seconds
Above: Session during the European Society of Cardiology's congress in Munich, Germany, on Aug. 31. Image credit: European Society of Cardiology/X

The Spin


AI diagnosing heart failure from an ECG in under two seconds is a genuine breakthrough that could save thousands of lives. Trained on over 10 million real ECG results, the tool hit up to 90% accuracy spotting conditions invisible to the human eye. With nearly 400,000 people currently stuck on NHS waiting lists for heart tests, this technology could provide the kind of solution the system desperately needs.

Labeling this ECG tool "superhuman" is hyperbole that exaggerates what this technology can actually do. Strong performance in a large U.S. trial is encouraging, but AI-ECG performance has been shown to fall in broader, lower-risk populations, where disease is less prevalent, milder and presents differently. In one community study, positive predictive value was just 14%. So the real test is whether these results will hold up in everyday NHS screening.


Go Deeper

© 2026 Improve the News Foundation. All rights reserved.Version 7.4.1

© 2026 Improve the News Foundation.

All rights reserved.

Version 7.4.1