PVCuRe: a machine-learning based tool to predict left ventricular systolic function recovery in patients undergoing ablation for premature ventricular contraction.
TL;DR
This ML-based tool accurately estimates the probability of LVEF recovery after PVC ablation and may support clinical decision-making and patient counselling.
Abstract
Background
Ablation of frequent premature ventricular complexes (PVCs) can improve left ventricular ejection fraction (LVEF) in patients with systolic dysfunction, especially in suspected PVC-induced cardiomyopathy. However, many patients fail to normalize LVEF despite successful ablation, and current tools do not reliably distinguish true PVC-induced cardiomyopathy from underlying cardiomyopathy exacerbated by PVCs.
Objective
To develop and externally validate a machine learning (ML) model using routinely available clinical, echocardiographic, and electrocardiographic variables to predict LVEF recovery after PVC ablation.
Methods
In this retrospective multicenter study, 256 patients with LVEF <50% undergoing successful PVC ablation at three international referral centers were included. Predictors were selected using the Boruta algorithm, and five ML models were trained. Performance was assessed with 10-fold cross-validation and ROC curve analysis. The best-performing model underwent calibration and threshold analysis and was externally validated in an independent cohort from three additional centers.
Results
The Random Forest model showed the best performance, with an AUC of 0.88 (95% CI 0.79-0.98) in the internal test set and good calibration (Hosmer-Lemeshow p=0.562). External validation confirmed consistent discrimination (AUC 0.83, 95% CI 0.72-0.95). Key predictors included baseline PVC burden, QRS duration in sinus rhythm, and preprocedural LVEF.
Conclusion
This ML-based tool, built on widely available variables, accurately estimates the probability of LVEF recovery after PVC ablation and may support clinical decision-making and patient counselling.