How Artificial Intelligence Discovered A New Way To Detect Patients At Risk Of Cardiac Death Using Simple EKGs

Researchers trained AI on 110,000 EKGs from 35,000 Swedish patients to identify people at high risk of sudden cardiac death.

The model flagged a subgroup with a 7.0% annual risk and outperformed echocardiogram-based screening.

It also generalized to validation data from the U.S. and Taiwan, and a second AI method pointed to a signal pattern in lead aVL.

The approach could improve selection for implantable cardioverter-defibrillators, reducing both missed high-risk cases and unnecessary procedures.