Comparative Evaluations of Six Risk Scores Proposed for Baseline Prediction of Atrial Fibrillation Recurrence Post Catheter Ablation

Background: Being able to identify patients who are at risk of arrhythmia recurrence following catheter ablation is important for prognostication, shared-decision making, etc. While numerous predictive models for atrial fibrillation recurrence (AFR) have been proposed, few models have underwent external validation, and few studies compared multiple models using the same patient cohort. Aims: To evaluate six prediction models using an external dataset. Methods: Data from 632 patients was pooled from two independent clinical trials that enrolled patients with anti-arrhythmic drug refractory atrial fibrillation who underwent catheter ablation. Primary outcome for both trials was documented atrial tachyarrhythmia (atrial fibrillation/flutter/tachycardia as adjudicated by a clinical committee blinded to treatment strategy). We compared 6 models for predicting AFR recorded between days 91-365 post ablation using standard metrics and ranked them according to the positive and negative clinical utility indices. Results: As the figure shows, the top performing model was CHA2DS2-VASc, followed by DR-FLASH, albeit both achieved positive and negative predictive values lower than 65%. Many models achieved high specificity but low sensitivity, except for CAAP-AF, which achieved high sensitivity but low specificity. In summary, all achieved area under receiver operating characteristic curve lower than 56% and were deemed to have poor clinical utility (less than 0.5 out of 1) when evaluated on our dataset. Conclusion: All models performed poorly and had objectively limited clinical utility. There remains a need to develop generalizable tools for predicting post ablation AFR.