Serial Artificial Intelligence ECG-Derived Atrial Fibrillation Probability and Recurrence Risk After Pulsed Field Ablation.

BACKGROUND

Pulsed field ablation is now widely used for atrial fibrillation (AF) ablation, but atrial tachyarrhythmia recurrence remains common and postablation risk tools are limited. We assessed whether a validated sinus‑rhythm artificial intelligence- enabled ECG AF probability score, and its early postablation change, predicts recurrence after pulsed field ablation.

METHODS

We studied consecutive patients undergoing index pulsed field ablation across 3 Mayo Clinic sites (February 2024-March 2025) with ≥1 sinus‑rhythm ECG within 180 days preprocedure. Baseline artificial intelligence-enabled ECG AF score (range 0-1) was the mean across baseline ECGs. Recovery indices (RI30/60/90), defined as mean postprocedure artificial intelligence-enabled ECG score within days 1-30/60/90 minus baseline, predicted post‑blanking recurrence using corresponding 30‑, 60‑, and 90‑day blanking windows. The primary outcome was time to first documented AF/atrial flutter/atrial tachycardia episode >30 seconds, ascertained via clinic ECGs, ambulatory monitoring, and device interrogations. Cox regression adjusted for prespecified clinical and echocardiographic covariates assessed associations; Harrell C‑statistic quantified discrimination.

RESULTS

Among 1052 patients (67±10 years; 33% women), median baseline score was 0.35; 320 (30%) recurred over 188 days. Higher baseline score independently predicted recurrence (hazard ratio per 0.1 increase, 1.08 [95% CI, 1.03-1.14]). Scores rose on day 0 after ablation, then declined over subsequent weeks, with persistently higher, less‑improving trajectories among patients who recurred (time×recurrence interaction P<0.001). Day 0 score was not independently associated with recurrence after adjustment. Attenuated early recovery (higher recovery index) was independently associated with recurrence, most robustly for RI-90 (hazard ratio per 0.1 increase, 1.15 [95% CI, 1.07-1.24]), and improved discrimination beyond baseline and covariates (C‑statistic, 0.63-0.67; ΔC=0.04). Findings were consistent in a historical thermal ablation cohort.

CONCLUSIONS

Baseline and early postablation dynamics of a sinus‑rhythm artificial intelligence-enabled ECG AF probability score are associated with pulsed field ablation recurrence and may aid multivariable risk stratification; prospective validation is warranted.