Detection and Prognostic Stratification of Left Ventricular Systolic Dysfunction in Left Bundle Branch Block Using an Artificial Intelligence-enabled ECG

Background Left bundle branch block (LBBB) significantly increases the risk of left ventricular systolic dysfunction (LVSD) due to cardiac dyssynchrony. While artificial intelligence-enabled electrocardiography (AI-ECG) models show promise in detecting LVSD, their performance in LBBB patients remains underexplored. We hypothesized that a clinically validated AI-ECG model for detecting LVSD, can accurately detect LVSD and predict future clinical outcomes in LBBB patients. Methods In this retrospective multicenter study, 5,689 expert-validated LBBB ECGs from 2,813 patients collected between 2016 and 2024 were analyzed using AI-ECG model that had been previously developed and validated. LVSD was defined as ejection fraction (EF) ≤ 40%. Model performance was assessed using area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, and specificity. Patients were stratified into high- and low-risk groups based on a threshold achieving 90% sensitivity. Kaplan–Meier analysis compared clinical outcomes. Results Among 2,813 LBBB patients (mean age 70.7, male 43.7%), hypertension and a history of heart failure were common. The AiTiALVSD model showed strong diagnostic performance for LVSD (AUROC 0.930 [95% CI, 0.924–0.937]; AUPRC 0.913 [95% CI, 0.902–0.923]; sensitivity 0.979; specificity 0.473). Mean follow-up duration was 4.1 years. High-risk patients had significantly higher hazards for all-cause mortality (Hazard Ratio [HR] 2.29, 95% CI 1.89–2.77), implantable cardioverter defibrillator (ICD)/cardiac resynchronization therapy (CRT) implantation (HR 2.29, 95% CI 1.89–2.77), and cardiovascular hospitalization (HR 1.40, 95% CI 1.22–1.60) (all p values < 0.001). Conclusion AiTiALVSD effectively detects LVSD and stratifies long-term cardiovascular risk in LBBB patients, supporting its clinical utility for early detection and management.