Key result
Random forest machine learning outperforms logistic regression in predicting AF ablation complications with ~0.72 AUC.
Why the study?
Radiofrequency ablation for atrial fibrillation carries a risk of complications, prompting the need for models to predict procedural complications.
Can machine learning-based risk models accurately predict postoperative procedural complications in patients with atrial fibrillation undergoing radiofrequency ablation?
Cohort (n=3,365)
No
Can machine learning-based risk models accurately predict postoperative procedural complications in patients with atrial fibrillation undergoing radiofrequency ablation?
Machine learning models, particularly Random Forest, can effectively predict in-hospital procedural complications following radiofrequency ablation for atrial fibrillation using readily available clinical and laboratory features.
Answers are grounded in this paper and cite their sources.
May inform risk assessment before AF ablation; leaves open prospective validation before clinical use.
BACKGROUND: Radiofrequency ablation (RFA) for atrial fibrillation (AF) is associated with a risk of complications. This study aimed to develop and validate risk models for predicting complications after radiofrequency ablation of atrial fibrillation patients. METHODS: This retrospective cohort study included 3365 procedures on 3187 patients with atrial fibrillation at a single medical center from 2018 to 2021. The outcome was the occurrence of postoperative procedural complications during hospitalization. Logistic regression, decision tree, random forest, gradient boosting machine, and extreme gradient boosting were used to develop risk models for any postoperative complications, cardiac effusion/tamponade, and hemorrhage, respectively. Patients' demographic characteristics, medical history, signs, symptoms at presentation, electrocardiographic features, procedural characteristics, laboratory values, and postoperative complications were collected from the medical record. The prediction results were evaluated by performance metrics (i.e., the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, F score, and Brier score) with repeated fivefold cross-validation. RESULTS: Of the 3365 RFA procedures, there were 62 procedural complications with a rate of 1.84% in the entire cohort. The most common complications were cardiac effusion/tamponade (28 cases, 0.83%), and hemorrhage (21 cases, 0.80%). There was no procedure-related mortality. The machine learning algorithms of random forest (RF) outperformed other models for any complication (AUC 0.721 vs 0.627 to 0.707), and hemorrhage (AUC 0.839 vs 0.649 to 0.794). The extreme gradient boosting (XGBoost) model outperformed other models for cardiac effusion/tamponade (AUC 0.696 vs 0.606 to 0.662). CONCLUSIONS: The developed risk models using machine learning algorithms showed good performance in predicting complications after RFA of AF patients. These models help identify patients at high risk of complications and guiding clinical decision-making.
No takes yet. Share an insight, caveat, or question.
Li et al. (2023) conducted a cohort in Atrial fibrillation (n=3,365). Random forest machine learning model vs. Logistic regression was evaluated on Prediction of any postoperative procedural complication (Area Under the Curve) (AUC 0.721, 95% CI 0.713-0.729). A random forest machine learning model outperformed logistic regression in predicting any procedural complication after radiofrequency ablation for atrial fibrillation, achieving an AUC of 0.721.
Synapse has enriched 10 related papers. Consider them for comparative context: