Artificial Intelligence-Guided Catheter Ablation Targeting Spatiotemporal Dispersion Areas for Persistent Atrial Fibrillation: A Systematic Review and Meta-Analysis

Objective: Pulmonary vein isolation (PVI) alone shows limited long-term success in persistent atrial fibrillation (AF). Additional ablation strategies targeting spatiotemporal dispersion areas (SDAs) exhibit variable outcomes, possibly due to multiple factors. The integration of artificial intelligence (AI) could standardize ablation procedures, offering an individualized yet consistent approach. This systematic review and meta-analysis aimed to evaluate the efficacy and safety of AI-guided SDA ablation for persistent AF. Methods: Systematic searches were conducted in PubMed, the Cochrane Library, and Europe PMC up to January 13, 2025. Studies were eligible if they included patients with persistent AF who underwent PVI combined with AI-guided SDA ablation. The risk of bias was assessed using the Newcastle-Ottawa Scale for non-randomized studies and the Cochrane Risk of Bias 2 tool for randomized studies. The primary outcome was the 12-month freedom from AF after a 3-month blanking period. A random-effects meta-analysis of proportions with Freeman-Tukey double arcsine transformation was performed to estimate the pooled freedom-from-AF rate using Stata 17.0. The systematic review was conducted according to Preferred Reporting Items for Systematic Reviews and Meta‐Analyses 2020 guidelines. This review was not registered in PROSPERO because it was an exploratory synthesis of rapidly emerging evidence. Results: A total of 1,296 records were identified through database searches. After removal of duplicates, records were screened by title and abstract, and irrelevant records were excluded. The remaining full-text articles were assessed for eligibility. Finally, 3 studies involving 322 patients were included. Two observational studies were judged to have a low risk of bias, whereas the randomized controlled trial was considered to be of good methodological quality. The freedom-from-AF rate in patients undergoing PVI plus SDA ablation was 87% (95% confidence interval 82%–91%). Heterogeneity was not formally quantified due to the small number of included studies. In a randomized controlled trial, AI-guided SDA ablation was associated with higher freedom from AF compared with PVI alone (89% vs. 67%, P = 0.001). Publication bias was not assessed because fewer than 10 studies were included. Conclusion: Early evidence suggests that AI-guided SDA ablation may improve freedom from AF in persistent AF, although the current evidence base remains limited and requires confirmation in larger studies. While early results are encouraging, further large-scale randomized studies are required to validate these findings and define their role in routine clinical practice.