Key result
XGBoost machine learning model predicts pacing-induced cardiomyopathy with ~0.83 AUROC.
Why the study?
Pacing-induced cardiomyopathy is a major complication of chronic right ventricular pacing, and currently available prediction approaches demonstrate limited discriminative performance to guide individualized pacing strategy selection in patients with AVB and underlying HFmrEF or HFpEF.
Do machine learning models accurately predict pacing-induced cardiomyopathy in patients with atrioventricular block and underlying heart failure with mildly reduced or preserved ejection fraction undergoing chronic right ventricular pacing?
Cohort (n=125)
Yes
Do machine learning models accurately predict pacing-induced cardiomyopathy in patients with atrioventricular block and underlying heart failure with mildly reduced or preserved ejection fraction undergoing chronic right ventricular pacing?
An XGBoost machine learning model integrating baseline LVEF and paced QRS duration accurately predicts pacing-induced cardiomyopathy (AUROC 0.831) in AVB patients with HFmrEF or HFpEF, potentially guiding individualized selection between right ventricular and conduction system pacing.
May aid risk stratification in AV block; leaves open prospective validation before guiding pacing decisions.
Background Pacing-induced cardiomyopathy (PICM) is a major complication of chronic right ventricular pacing and develops in up to 25% of patients. Reliable prediction of PICM may facilitate individualized pacing strategy selection; however, currently available approaches demonstrate limited discriminative performance. This study aimed to develop and validate machine learning (ML) models for predicting PICM in patients with atrioventricular block (AVB) underlying heart failure with mildly reduced or preserved ejection fraction. Methods In this multicenter prospective study derived from the RISK-PICM registry (January 2002 to January 2026), 125 patients with AVB who underwent pacemaker implantation were analyzed. PICM was defined as a ≥10% reduction in left ventricular ejection fraction (LVEF) resulting in an LVEF <50%. Four ML algorithms, including logistic regression, support vector machine, random forest, and XGBoost, were trained using stratified 4-fold cross-validation with hyperparameter optimization and model discrimination was evaluated. Results PICM developed in 41 patients (32.8%) during a median follow-up of 4.8 years. Male sex, pre-implant minimum QTc interval, and post-implant maximum QRS duration were significantly associated with PICM in univariable Cox regression. XGBoost achieved the highest discriminative performance (AUROC 0.831; sensitivity 0.805; specificity 0.845). Feature importance analysis identified baseline LVEF and post-implant maximum QRS duration as the most influential features. Model-derived risk stratification significantly differentiated high-risk and low-risk groups on Kaplan-Meier analysis ( P < 0.001). Conclusions ML-based models, particularly XGBoost, demonstrated clinically meaningful performance for PICM and may support individualized pacing strategy selection in patients with AVB and underlying heart failure with mildly reduced or preserved ejection fraction. Clinical Perspective What Is New In pacing-dependent AVB patients with HFmrEF or HFpEF, ensemble ML (XGBoost) predicted PICM with an AUROC of 0.831. Model-derived risk stratification separated PICM-free survival (log-rank P<0.001). What Are the Clinical Implications An ML model combining baseline LVEF, paced QRS duration, and the full parameter set may guide individualized choice between right ventricular and conduction system pacing in AVB patients with HFmrEF or HFpEF. Using paced QRS duration combined with baseline LVEF during temporary pacing in AVB patients with HFmrEF or HFpEF, this risk estimate could inform pacing-strategy selection before permanent implantation, enabling pre-emptive use of conduction system pacing in high-risk patients.
No takes yet. Share an insight, caveat, or question.
Lee et al. (2026) conducted a cohort in Atrioventricular block with heart failure with mildly reduced or preserved ejection fraction (HFmrEF or HFpEF) (n=125). XGBoost machine learning risk prediction model for pacing-induced cardiomyopathy vs. Logistic regression, support vector machine, and random forest models (or low-risk stratification group) was evaluated on Pacing-induced cardiomyopathy (PICM), defined as ≥10% reduction in LVEF resulting in LVEF <50% (AUROC 0.831, p=<0.001). The XGBoost machine learning model predicted pacing-induced cardiomyopathy with an AUROC of 0.831 (sensitivity 0.805, specificity 0.845) and significantly stratified risk (P < 0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: