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

2026-03-30

AI Summary

This study addresses the critical challenge of underdiagnosing low left ventricular ejection fraction (LVEF) prior to the onset of heart failure symptoms, highlighting the urgent need for efficient screening tools. The authors propose ECGPD-LVEF, a novel framework that integrates diagnostic probabilities derived from foundation models with interpretable machine learning to detect LVEF abnormalities from routine electrocardiograms (ECGs). Notably, this approach enables zero-shot inference without task-specific fine-tuning and employs structured modeling to uncover key ECG-based predictors. Evaluated across multiple external and internal test cohorts, the method achieves AUROC scores ranging from 86.8% to 88.4%, significantly outperforming end-to-end baseline models while offering both high performance and clinically meaningful interpretability.

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.

Problem

• low ejection fraction
• ECG
• scalable screening
• interpretability
• heart failure

Innovation

• predictor-driven framework
• interpretable AI
• foundation model
• zero-shot inference
• low ejection fraction detection