A Vision Transformer for ECG-Based Detection of Left Ventricular Systolic Dysfunction Across Multiple Clinical Sites

2026-08-12

AI Summary

This study addresses the challenge of occult left ventricular systolic dysfunction (LVSD) screening by proposing a beat-by-beat 12-lead ECG analysis model based on an ensemble of Vision Transformers. Trained from scratch on multi-center data and validated for cross-site generalizability, the model incorporates beat-level attention maps to enhance interpretability. External validation demonstrated robust performance with an AUROC of 0.88, sensitivity of 81.2%, and negative predictive value of 97.8%, maintaining consistency across demographic subgroups. These findings substantiate the potential of standard ECG as a universal preliminary screening tool for LVSD, offering a scalable pre-screening strategy that can effectively prioritize patients for subsequent echocardiographic evaluation.

Abstract

Reduced left ventricular ejection fraction (LVEF) is frequently asymptomatic and often detected only after advanced heart failure develops. Electrocardiograms are recorded routinely yet underused for this condition, because reduced LVEF has no single diagnostic waveform. We trained an ensemble of vision transformers from scratch to detect reduced LVEF ($\leq$40%) from 12-lead ECGs, analyzing each heartbeat individually, using 10,142 patients across seven sites in three US health systems. In a held-out external cohort of 4,092 patients from three geographically independent US clinical sites at a real-world reduced-LVEF prevalence of 8.72%, the model achieved an AUROC of 0.88 (95% CI 0.86-0.89), sensitivity 81.2%, specificity 81.0%, and negative predictive value 97.8%. Sensitivity remained high across sex, race, ethnicity, and comorbidity subgroups, while specificity was lower in older patients and those with atrial fibrillation or cardiomyopathy. Beat-level attention maps provided interpretability into the model's predictions, showing consistent focus on the QRS complex rather than the P wave. These findings support the potential of routine ECGs as a scalable first-pass triage step to identify patients who should undergo echocardiography for reduced ejection fraction across diverse patient populations.

Problem

• Left Ventricular Systolic Dysfunction
• Reduced LVEF
• Electrocardiogram
• Asymptomatic Detection
• Heart Failure Screening

Innovation

• Vision Transformer
• Beat-level analysis
• Multi-site validation
• ECG interpretability
• Left ventricular systolic dysfunction detection