Foundation models for electrocardiogram interpretation: clinical implications.

Clinical Snapshot

Key Findings

• P Value: P < 0.001 for atrial fibrillation prediction, P = 0.026 for LQTS genotype classification

• Effect Size: DeepECG-SSL: 0.990 (internal), 0.981 (external public), 0.983 (external private)

• Primary Outcome: Micro-averaged AUROC across 77 cardiac conditions

• Nnt Or Sensitivity: AUROC 0.931 vs 0.850 for LQTS genotype classification, 0.926 vs 0.917 for LVEF ≤40% detection

• Confidence Interval: 95% CI: 0.990-0.990 (internal), 0.981-0.981 (external public), 0.983-0.983 (external private)

Clinical Application

High feasibility given standardized ECG acquisition, though requires computational infrastructure for AI implementation Relevant to Australian practice given universal ECG use; would require TGA approval as medical device software; could integrate with existing ECG systems in public and private hospitals Adult patients undergoing routine 12-lead ECG across diverse healthcare settings

Abstract

BACKGROUND AND AIMS: The 12-lead electrocardiogram (ECG) remains a cornerstone of cardiac diagnostics, yet existing artificial intelligence (AI) solutions for automated interpretation often lack generalizability, remain closed source, and are primarily trained using supervised learning (SL), which requires extensive labelled datasets and may limit adaptability across diverse clinical settings. Self-supervised learning (SSL) can potentially overcome these limitations by learning robust representations from unlabelled data. To address these challenges, this study developed and compared two open-source foundational ECG models: DeepECG-SL, a supervised multilabel ECG model, and DeepECG-SSL, a self-supervised model. METHODS: Both models were trained on over 1 million ECGs using a standardized preprocessing pipeline and automated free-text extraction from ECG reports to predict 77 cardiac conditions. DeepECG-SSL leveraged unlabelled data through self-supervised contrastive learning and masked lead modelling before fine-tuning for downstream tasks, while DeepECG-SL was trained directly on labelled diagnostic data in an end-to-end fashion. Performance was evaluated across seven private, multilingual healthcare systems and four public ECG repositories, with assessment of fairness by age and sex, and investigation of privacy vulnerabilities as well as memory and compute requirements. RESULTS: DeepECG-SSL achieved micro-averaged area under the receiver operating characteristic curves (AUROCs) across all 77 cardiac conditions for ECG interpretation of 0.990 [95% confidence interval (CI): 0.990, 0.990] on the internal dataset (MHI-ds), 0.981 (95% CI: 0.981, 0.981) on external public datasets (UKB, CLSA, MIMIC-IV and PTB), and 0.983 (95% CI: 0.983, 0.983) on external private datasets (UW, UCSF, JGH, NYP, MGH, CSH and CHUM), while DeepECG-SL demonstrated AUROCs of 0.992 (95% CI: 0.992, 0.992), 0.980 (95% CI: 0.980, 0.980), and 0.983 (95% CI: 0.983, 0.984), respectively. Fairness analyses revealed minimal disparities (true-positive rate and false-positive rate difference <0.1) across age and sex groups for both models. DeepECG-SSL demonstrated superior performance on limited-data digital biomarker tasks, with the largest improvements in long QT syndrome (LQTS) genotype classification (AUROC 0.931 vs 0.850, P = .026, n = 127 ECGs) and 5 year atrial fibrillation risk prediction (AUROC 0.742 vs 0.734, P < 0.001, n = 132 050 ECGs), while achieving superior performance in left ventricular ejection fraction ≤40% classification (AUROC 0.926 vs 0.917, P < 0.001, n = 25 252 ECGs) and comparable performance in LQTS detection (AUROC 0.767 vs 0.735, P = 0.117, n = 934 ECGs). CONCLUSIONS: This study establishes SSL as a promising paradigm for ECG analysis, particularly in settings with limited annotated data, enhancing accessibility, generalizability, and fairness in AI-driven cardiac diagnostics. By releasing model weights, preprocessing tools, and validation code, this work aims to support robust, data-efficient AI diagnostics across diverse clinical environments and questions.

References

1. 1.Nolin-Lapalme, A., Sowa, A., Delfrate, J., Tastet, O., Corbin, D., Kulbay, M., Ozdemir, D., Noël, M. J., Marois-Blanchet, F. C., Harvey, F., Sharma, S., Ansari, M., Chiu, I. M., D'souza, V., Friedman, S. F., Chassé, M., Potter, B. J., Afilalo, J., Elias, P. A., Jabbour, G., Bahani, M., Dubé, M. P., Boyle, P. M., Chatterjee, N. A., Barrios, J., Tison, G. H., Ouyang, D., Maddah, M., Khurshid, S., Cadrin-Tourigny, J., Tadros, R., Hussin, J., & Avram, R. (2026). Foundation models for electrocardiogram interpretation: clinical implications. European Heart Journal. https://doi.org/10.1093/eurheartj/ehaf1119