AI Model Far Outperforms Doctors in Predicting Sudden Cardiac Death Risk: Study Finds

Tested against real-world patient data from Johns Hopkins Hospital and the Sanger Heart & Vascular Institute in North Carolina, MAARS achieved 89% overall accuracy and 93% accuracy in patients aged 40 to 60—those most vulnerable to sudden cardiac death. Importantly, the AI model also explains why a patient is high risk, enabling doctors to tailor treatment more precisely.

“Currently we have patients dying in the prime of their life because they aren't protected and others who are putting up with defibrillators for the rest of their lives with no benefit,” said senior author Natalia Trayanova. “We have the ability to predict with very high accuracy whether a patient is at very high risk for sudden cardiac death or not.”

Reference: Changxin Lai, Minglang Yin, Eugene G. Kholmovski, Dan M. Popescu, Dai-Yin Lu, Erica Scherer, Edem Binka, Stefan L. Zimmerman, Jonathan Chrispin, Allison G. Hays, Dermot M. Phelan, M. Roselle Abraham, Natalia A. Trayanova. Multimodal AI to forecast arrhythmic death in hypertrophic cardiomyopathy. Nature Cardiovascular Research, 2025; DOI: 10.1038/s44161-025-00679-1