Transthoracic echocardiographic and artificial intelligence-enabled electrocardiography predictors of atrial arrhythmia recurrence after surgical ablation

Le résumé fourni par la source

Background Recurrence of atrial fibrillation/flutter (AF/AFl) after surgical ablation remains difficult to predict. Integration of novel biomarkers may enhance risk stratification. Objective To assess whether combining preoperative transthoracic echocardiography (TTE) and artificial intelligence-enabled ECG (AI-ECG) scores improves prediction of AF/AFl recurrence after surgical ablation. Methods We retrospectively analyzed 1,696 patients who underwent surgical AF/AFl ablation from 2006–2025 with available preoperative TTE and ECG, and post-blanking (90-day) ECG follow-up. Clinical, TTE, and AI-ECG variables (AF probability, ECG-estimated age, HFpEF, LV dysfunction, and aortic stenosis scores) were assessed. Cox proportional hazards and Random Survival Forest (RSF) models (80:20 train-test split) identified predictors of recurrence. Results Among 1,696 patients (mean age 67.3±10.2 years; 61.7% male), 949 (56%) had AF/AFl recurrence over a median 3.14-year follow-up. Patients with recurrence had larger LA area (30.4 vs 24.5 cm 2 ), elevated mitral E-wave velocity (1.015 vs 0.896 m/s), and adverse AI-ECG biomarkers for AF probability, ECG-estimated age, HFpEF, LV dysfunction, and aortic stenosis (all p<0.001). In multivariable analysis, independent predictors of recurrence included higher ECG-AF probability (p<0.0001), older ECG-estimated age (p=0.0002), LA area (p=0.046), BMI (p=0.036), and diastolic BP (HR 1.008/mmHg, p=0.010). The final Cox model achieved a C-index of ∼0.67 and 3-year Brier score 0.21, with 3-year freedom-from-arrhythmia rates of ∼85% vs ∼43% for lowest- vs highest-risk quartiles. RSF modeling yielded a slightly higher C-index (∼0.69). Conclusions Preoperative AI-ECG biomarkers (AF probability, age discordance) and TTE markers of atrial remodeling independently predicted AF/AFl recurrence after surgical AF/AFl ablation. Integration of these metrics improved risk stratification.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.