| Title: | DEVELOPMENT AND MULTINATIONAL VALIDATION OF ARTIFICIAL INTELLIGENCE-ENABLED ASCVD RISK STRATIFICATION USING ELECTROCARDIOGRAMS |
| Journal: | American Journal of Preventive Cardiology |
| Published: | 1 Aug 2026 |
| DOI: | https://doi.org/10.1016/j.ajpc.2026.101794 |
Publication 21251
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Abstract
Aims Despite the availability of clinical risk scores for atherosclerotic cardiovascular disease (ASCVD), their use is limited because the required predictor data are often missing. We developed and validated ECG-ASCVD, a scalable risk prediction paradigm that utilizes ECGs to target ASCVD risk factor assessment. Methods Adults aged 30-79 who had undergone a clinical ECG were identified in the Yale New Haven Health System (YNHHS) and a state death index. We developed ECG-ASCVD-12, ECG-ASCVD-IMAGE, and ECG-ASCVD-1 to predict time-to-ASCVD from 12-lead ECG signals, ECG images, and lead-1 signals, respectively. Model performance was assessed in held-out individuals without prior ASCVD and in two external prospective cohorts, ELSA-Brasil (ELSA) and the UK Biobank (UKB). We then simulated the deployment of ECG-ASCVD in a random sample of 100,000 adults at YNHHS. Results The development cohort included 363,788 individuals (median age, 57.1 [45.5-67.2] years; 52% women). The YNHHS, ELSA, and UKB test cohorts included 83,917, 10,934, and 54,166 individuals, respectively. ECG-ASCVD-12 demonstrated generalizable discrimination (C-index: 0.684 to 0.746) and remained independently associated with ASCVD (adjusted hazard ratio: 1.23-1.34 per SD) after adjusting for PREVENT scores (C-index: 0.696-0.782) across the validation cohorts. ECG-ASCVD-IMAGE performed similarly (C-index: 0.673-0.748) while ECG-ASCVD-1 had modestly lower performance (C-index: 0.671-0.735). Simulated deployment suggested that ECG-ASCVD could enable the detection of high ASCVD risk patients who lack the data required for PREVENT. Conclusion We developed an ECG-ASCVD toolkit and validated it across diverse multinational cohorts. These results highlight the potential utility of resting ECG information for predicting ASCVD risk, enabling targeted screening. Lay Complete data to run clinical risk prediction equations for atherosclerotic cardiovascular disease are often missing in practice. We developed and made publicly available a series of models that can predict the risk of atherosclerotic cardiovascular disease using easily obtainable electrocardiograms (ECGs), including ECG printouts and the type of ECGs obtained by smartwatches.</p>
10 Authors
- Bruno Batinica
- Evangelos K Oikonomou
- Aline F Pedroso
- Arya Aminorroaya
- Dhruva Biswas
- Sandhi M Barreto
- Luisa C C Brant
- Antonio L P Ribeiro
- Lovedeep S Dhingra
- Rohan Khera
Enabling scientific discoveries that improve human health