Detecting low left ventricular ejection fraction from ECG using an interpretable and scalable predictor-driven framework

TL;DR

This study presents ECGPD-LEF, an interpretable, scalable framework that combines foundation model probabilities with structured modeling to detect low left ventricular ejection fraction from ECGs, outperforming existing methods.

Contribution

The paper introduces ECGPD-LEF, a novel framework integrating foundation model probabilities with interpretable modeling for improved LEF detection from ECGs.

Findings

Achieved AUROC of 88.4% internally and 86.8% externally for moderate LEF.

Outperformed official end-to-end baseline across diverse subgroups.

Identified high-impact predictors like normal ECG and incomplete left bundle branch block.

Abstract

Low left ventricular ejection fraction (LEF) frequently remains undetected until progression to symptomatic heart failure, underscoring the need for scalable screening strategies. Although artificial intelligence-enabled electrocardiography (AI-ECG) has shown promise, existing approaches rely solely on end-to-end black-box models with limited interpretability or on tabular systems dependent on commercial ECG measurement algorithms with suboptimal performance. We introduced ECG-based Predictor-Driven LEF (ECGPD-LEF), a structured framework that integrates foundation model-derived diagnostic probabilities with interpretable modeling for detecting LEF from ECG. Trained on the benchmark EchoNext dataset comprising 72,475 ECG-echocardiogram pairs and evaluated in predefined independent internal (n=5,442) and external (n=16,017) cohorts, our framework achieved robust discrimination for moderate LEF (internal AUROC 88.4%, F1 64.5%; external AUROC 86.8%, F1 53.6%), consistently outperforming the official end-to-end baseline provided with the benchmark across demographic and clinical subgroups. Interpretability analyses identified high-impact predictors, including normal ECG, incomplete left bundle branch block, and subendocardial injury in anterolateral leads, driving LEF risk estimation. Notably, these predictors independently enabled zero-shot-like inference without task-specific retraining (internal AUROC 75.3-81.0%; external AUROC 71.6-78.6%), indicating that ventricular dysfunction is intrinsically encoded within structured diagnostic probability representations. This framework reconciles predictive performance with mechanistic transparency, supporting scalable enhancement through additional predictors and seamless integration with existing AI-ECG systems.