Skip to content
Open access

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

Oct 2026 · Circulation: Arrhythmia and Electrophysiology · pp. e015183 · 0 citations · 20 references
Medicine

TL;DR

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.

Abstract

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.

Read PDF

Similar papers

Open access Oct 2026

ECG-derived atrial fibrillation organisation index, but not atrial fibrillatory rate, is associated with 30-day recurrence after cardioversion of the first-ever persistent atrial fibrillation episode

Electrocardiogram-based measures of atrial fibrillation (AF) organisation have been linked to rhythm outcomes after electrical cardioversion. Interpretation is complicated when cohorts include rhythm-control interventions such as ablation and antiarrhythmic drugs that may modify atrial electrophysiology and elect...

T. Hagsund, F. Holmqvist, B. Hardig et al. · 0 citations
Review Open access Oct 2026

New-Onset Atrial Fibrillation After Typical Flutter Ablation: Risk-Stratified Monitoring Using Implantable Loop Recorders.

BACKGROUND Atrial flutter and atrial fibrillation (AF) arise from a common arrhythmogenic atrial substrate and frequently coexist in the same patient over the course of their lifetime. We aimed to examine the true incidence and risk factors associated with new-onset AF after successful typical atrial flutter ablation i...

S. Singireddy, Ragavendar Saravanabavanandan, Kyle Coombes et al. · 0 citations
Oct 2026

Atrial fibrillation recurrence pattern and subsequent heart failure hospitalization after ablation in left ventricular systolic dysfunction: A time-dependent analysis.

BACKGROUND Catheter ablation improves outcomes in patients with atrial fibrillation (AF) and left ventricular (LV) systolic dysfunction, but the prognostic significance of postablation recurrence pattern and its evolution remains unclear. We investigated whether evolving postablation recurrence pattern was associated w...

M. Okada, Nobuaki Tanaka, Koji Tanaka et al. · 0 citations
Open access Sep 2026

Impact of Early Atrial Tachyarrhythmia Within the Blanking Period on Late Recurrence After Pulsed Field Ablation of Atrial Fibrillation.

BACKGROUND Early atrial tachyarrhythmias (ERAT) occurring during the first 3 months after atrial fibrillation (AF) ablation were not traditionally considered a treatment failure, and this defined the blanking period after thermal energy ablations. More recent data suggest that the blanking period after pulsed field abl...

Ali Dakik, Jaafar Ismail, Joe Demian et al. · 0 citations
Open access Sep 2026

Left atrial anatomy and atrial arrhythmia recurrence after pulsed-field ablation.

BACKGROUND The impact of left atrial (LA) anatomical features on atrial arrhythmia (AA) recurrence after pulsed-field (PF)-based pulmonary vein isolation (PVI) is unknown. This study aimed to assess LA anatomical features associated with long-term AA recurrence after PVI. METHODS We prospectively enrolled patients un...

M. Mutti, D. Spreen, Jonas Brügger et al. · 0 citations
Open access Oct 2026

Deep learning-based detection of paroxysmal atrial fibrillation from sinus rhythm electrocardiograms and its association with stroke risk

Atrial fibrillation (AF) is associated with increased stroke risk and deep-learning model by electrocardiogram (ECG) enabled AF early detection even during normal sinus rhythm (NSR). However, impact of AF early detection on subsequent stroke is not well known. The primary aim was to develop and externally...

K. H. Lee, Y.-H. Ji, M. Park et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.