Detecting Structural Heart Disease from Electrocardiograms via a Generalized Additive Model of Interpretable Foundation-Model Predictors

Researchers developed an interpretable AI framework for detecting structural heart disease from electrocardiograms, achieving better performance than existing deep-learning methods while providing clinical transparency. The model demonstrated improvements of nearly 1% across key metrics using the EchoNext benchmark of over 80,000 ECG-ECHO pairs.