Explainable machine learning for risk prediction of acute cardiac tamponade during atrial fibrillation ablation

Cardiac tamponade is a rare but catastrophic complication during AF catheter ablation, influenced by multiple procedural and patient-related factors, making prediction highly challenging. This study aimed to develop and interpret a machine learning–based predictive model for cardiac tamponade during AF catheter ablation. Data were retrospectively collected from 1,481 patients who underwent AF catheter ablation at a tertiary hospital in Nanjing, China, between October 2014 and December 2024. After identifying key predictors of intraoperative cardiac tamponade via LASSO regression, eight machine learning algorithms were trained using the mlr3 framework. Model performance was evaluated through cross-validation, and SHAP analysis was conducted for the best-performing model. The XGBoost model showed the best overall performance (AUC = 0.972 in the training set and 0.908 in internal validation), demonstrating excellent calibration and the highest clinical net benefit. SHAP analysis identified five major predictors—operator experience, D-dimer level, total heparin dose, AF type, and left atrial diameter—representing multidimensional determinants associated with procedural technique, coagulation status, and cardiac anatomy. The XGBoost-based model demonstrated strong discriminative ability and interpretability for predicting cardiac tamponade during AF ablation, supporting accurate preoperative risk stratification and guiding intraoperative management to improve procedural safety and precision. External validation across multiple centers is needed to confirm the model’s generalizability.