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

TL;DR

This paper introduces an interpretable AI framework using a generalized additive model with ECG predictors to detect structural heart disease, achieving high accuracy and clinical transparency with less data.

Contribution

The study presents a novel, interpretable model combining ECG foundation-model predictors within a generalized additive framework for SHD detection, outperforming black-box deep learning methods.

Findings

Improved AUROC by 0.98% over state-of-the-art

Enhanced AUPRC by 1.01%

Achieved better performance with only 30% of training data

Abstract

Structural heart disease (SHD) is a prevalent condition with many undiagnosed cases, and early detection is often limited by the high cost and accessibility constraints of echocardiography (ECHO). Recent studies show that artificial intelligence (AI)-based analysis of electrocardiograms (ECGs) can detect SHD, offering a scalable alternative. However, existing methods are fully black-box models, limiting interpretability and clinical adoption. To address these challenges, we propose an interpretable and effective framework that integrates clinically meaningful ECG foundation-model predictors within a generalized additive model, enabling transparent risk attribution while maintaining strong predictive performance. Using the EchoNext benchmark of over 80,000 ECG-ECHO pairs, the method demonstrates relative improvements of +0.98% in AUROC, +1.01% in AUPRC, and +1.41% in F1 score over the latest state-of-the-art deep-learning baseline, while achieving slightly better performance even with only 30% of the training data. Subgroup analyses confirm robust performance across heterogeneous populations, and the estimated entry-wise functions provide interpretable insights into the relationships between risks of traditional ECG diagnoses and SHD. This work illustrates a complementary paradigm between classical statistical modeling and modern AI, offering a pathway to interpretable, high-performing, and clinically actionable ECG-based SHD screening.