Explainable Age Prediction Using a Transformer Trained on Diverse Global Electrocardiograms

Abstract Aims Artificial intelligence (AI) models trained on electrocardiograms (ECGs) can estimate age with deviations from chronological age (Δage) serving as markers of accelerated cardiovascular aging. We evaluated whether transformer-based AI models trained on globally diverse, heterogeneous ECG datasets outperform CNN-based models in generalizability and physiological interpretability. Methods and Results Using 11 public datasets (435,203 recordings) from four continents and an independent external cohort (14,462 recordings), we trained and validated transformer and CNN architectures. The transformer model trained on global data achieved strong correlation with chronological age (r = 0.90) and maintained robust performance in the external cohort (r = 0.88), outperforming both a CNN trained on global data and a model trained exclusively on a homogenous population-based cohort. Individuals with Δage≥+8 years exhibited a twofold increased mortality risk (HR = 2.08, 95% CI 1.93–2.24). Explainability analysis identified the P wave particularly in lead V1 as the dominant contributor to age prediction, consistent with known electrophysiological changes associated with atrial remodelling and aging. The model’s attribution to early atrial conduction features was consistent across age strata, peaking in midlife (30–50 years), and correlated positively with disease burden, including hypertension and smoking. Conclusion Our findings establish that transformer models trained on globally heterogeneous data generalize well and can provide insights to plausible aging signatures. Furthermore, Δage may offer insight into underlying physiological aging processes and associated risk, though further validation is needed to define its clinical utility in risk stratification.