Arrhythmias & electrophysiologyResearch article
Serial Artificial Intelligence ECG-Derived Atrial Fibrillation Probability and Recurrence Risk After Pulsed Field Ablation
- consecutive patients undergoing index pulsed field ablation across 3 Mayo Clinic sites
- Cox regression adjusted for prespecified clinical and echocardiographic covariates
- Harrell C-statistic
Authors' conclusion
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.
Study context
- Population
- Consecutive patients undergoing index pulsed field ablation across 3 Mayo Clinic sites (February 2024-March 2025) with ≥1 sinus-rhythm ECG within 180 days preprocedure67±10 years, 33% women
- Participants
- 1,052 patients
- Comparison
- Baseline artificial intelligence-enabled ECG atrial fibrillation (AF) score and recovery indices (RI30/60/90) as predictors of post-blanking recurrence
- Outcome
- Time to first documented AF/atrial flutter/atrial tachycardia episode >30 seconds
- Follow-up
- Over 188 days
Main finding
As reported in the abstract
Recurred
320 (30%)
Further findings
| Outcome | hazard ratio (95% CI) | |
|---|---|---|
| Baseline artificial intelligence-enabled ECG AF score and recurrence · independently predicted recurrence | 1.08 (1.03–1.14) | |
| Recovery index RI-90 and recurrence | 1.15 (1.07–1.24) | |
| 0.512Hazard ratio (log scale) |
- Baseline artificial intelligence-enabled ECG AF score and recurrence — Median baseline score
- 0.35
- Recovery index RI-90 and recurrence: attenuated early recovery (higher recovery index) independently associated with recurrence
Score trajectories after ablation
- 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
- Not independently associated with recurrence after adjustment
Discrimination beyond baseline and covariates
- C-statistic
- 0.63-0.67
- ΔC
- 0.04
Historical thermal ablation cohort
- Findings were consistent
Original publication
Serial Artificial Intelligence ECG-Derived Atrial Fibrillation Probability and Recurrence Risk After Pulsed Field Ablation. Circ Arrhythm Electrophysiol. Published 8 October 2026. doi:10.1161/circep.126.015183
Summarised from the published abstract; every number is checked against it