Wake Forest AI Detects Multiple Heart Failure Types via ECG

Researchers at Wake Forest University School of Medicine have developed an artificial intelligence model that can identify three forms of heart failure—reduced ejection fraction, mildly reduced ejection fraction, and heart failure with preserved ejection fraction (HFpEF)—from standard electrocardiograms. The model was trained on more than one million ECGs from Atrium Health Wake Forest Baptist and validated on a separate set of over 72,000 ECGs from the University of Tennessee Health Science Center, showing comparable performance with both 12‑lead and single‑lead data.

The single‑lead version performed nearly as well as the 12‑lead version, suggesting potential adaptation for wearable devices such as smartwatches, although it has not yet been tested on data collected directly from wearables. The tool also demonstrated strong detection of reduced ejection fraction in pediatric patients and generalized well across diverse demographic groups. "Our AI model can detect various types of heart dysfunction from a simple, single‑lead ECG alone," said corresponding author Oguz Akbilgic, Ph.D.