Why the study?
Low left ventricular ejection fraction often remains undetected until symptomatic heart failure develops, and existing AI-ECG screening approaches rely either on black-box end-to-end models with limited interpretability or on commercial algorithm-dependent tabular systems with suboptimal performance.
Does the ECG-based Predictor-Driven LEF (ECGPD-LEF) framework improve the detection of moderate low left ventricular ejection fraction compared to an end-to-end baseline model in patients undergoing ECG and echocardiography?
Does the ECG-based Predictor-Driven LEF (ECGPD-LEF) framework improve the detection of moderate low left ventricular ejection fraction compared to an end-to-end baseline model in patients undergoing ECG and echocardiography?
An interpretable, predictor-driven AI-ECG framework (ECGPD-LEF) accurately detects moderate low left ventricular ejection fraction (external AUROC 86.8%) and outperforms end-to-end black-box baseline models while providing mechanistic transparency.
Answers are grounded in this paper and cite their sources.
Supports interpretable ECG-based low LVEF detection in validation cohorts; extends AI-ECG research but leaves prospective utility open.
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.
No takes yet. Share an insight, caveat, or question.
Zhou et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: