Artificial Intelligence–Derived Electrocardiographic Age Enhances Stroke Risk Stratification in Patients with a CHA₂DS₂-VA Score of 1

Aims: To evaluate whether artificial intelligence(AI) -derived electrocardiographic (ECG)-age enhances the predictive utility of the CHA₂DS₂-VA score in atrial fibrillation(AF) patients representing a borderline indication for anticoagulation with a score of 1. Methods and Results: This retrospective cohort study analyzed data from a registry of 38,443 patients with atrial fibrillation collected between 2011 and 2024. We identified 832 anticoagulation-naïve patients with a CHA₂DS₂-VA score of 1 and a valid ECG obtained within 90 days of diagnosis. Using a validated AI algorithm, we replaced chronological age in the CHA₂DS₂-VA score with ECG-age to construct an ECG-age–modified CHA₂DS₂-VA score (EA-CHA₂DS₂-VA). Patients were subsequently categorized into two groups based on their updated score: those with an EA-CHA₂DS₂-VA score ≥ 2(n = 315) and those with an EA-CHA₂DS₂-VA score < 2 (n = 517). Kaplan–Meier analyses and Cox proportional hazards models were used to evaluate the incidence of ischemic stroke and all-cause mortality. Compared with patients with an EA-CHA₂DS₂-VA score < 2, those with an EA-CHA₂DS₂-VA score ≥ 2 had a significantly higher risk of ischemic stroke (HR 1.82; 95% CI 1.06–3.13; P = 0.028). All-cause mortality was also significantly elevated in the EA-CHA₂DS₂-VA ≥ 2 group (HR 2.22; 95% CI 1.43–3.45; P < 0.001). Conclusion: Substituting chronological age with AI-derived ECG-age in the CHA₂DS₂-VA score enhances risk stratification in AF patients with intermediate stroke risk. This refined risk stratification facilitates timely initiation of anticoagulation therapy, potentially reducing stroke and mortality. Future prospective studies are essential to integrate this AI-enhanced strategy into clinical practice.