A LightGBM-based machine learning model achieved an AUC of 0.704 in predicting early recurrence after atrial fibrillation ablation, demonstrating higher discrimination than conventional logistic regression.
Observational (n=519)
No
Does a LightGBM-based machine learning model improve the prediction of early recurrence of atrial fibrillation after first-time catheter ablation compared to traditional risk scores?
A LightGBM machine learning model integrating structural and metabolic features modestly improves the prediction of early recurrence after first-time AF ablation compared to traditional clinical risk scores.
Absolute Event Rate: 0.704% vs 0.623%
Atrial fibrillation (AF) is the most prevalent sustained arrhythmia, yet tools for predicting early recurrence (ER) after catheter ablation remain limited. This study aimed to develop a machine learning model to estimate ER risk following first-time AF ablation. In this retrospective single-center study, 519 patients undergoing initial AF ablation were enrolled (ER rate: 9.2%). Eight predictors were selected via recursive feature elimination. A LightGBM model was constructed and internally validated against logistic regression and conventional risk scores. The LightGBM model achieved an AUC of 0.715 in training and 0.704 in testing, showing higher discrimination than logistic regression (AUC = 0.623) and traditional scores (APPLE AUC = 0.560). SHAP analysis identified mitral regurgitation severity, age, hemoglobin, and albumin as predominant predictors. Using a Youden-derived threshold (0.099), high- and low-risk groups exhibited significantly different recurrence rates in testing(11.4% vs. 2.9%; P < 0.05). We developed a LightGBM-based model integrating structural and metabolic features that modestly improves upon conventional approaches in predicting ER after AF ablation. This tool may facilitate personalized post-procedural management. Multicenter prospective validation is warranted.
Ma et al. (Thu,) conducted a observational in Atrial fibrillation (n=519). LightGBM-based predictive model vs. Logistic regression model was evaluated on Area under the curve (AUC) for predicting early recurrence in the test set (95% CI 0.533-0.874). A LightGBM-based machine learning model achieved an AUC of 0.704 in predicting early recurrence after atrial fibrillation ablation, demonstrating higher discrimination than conventional logistic regression.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: