Precision Cardiology: Integrating Genetics and Artificial Intelligence for Cardiovascular Risk Prediction
DOI:
https://doi.org/10.63969/2k2psg72Keywords:
Artificial intelligence, Polygenic risk score, Electrocardiography, Cardiovascular risk prediction, Precision medicine, Latin AmericaAbstract
Cardiovascular diseases (CVDs) remain the leading cause of death worldwide, yet conventional predictive models often fail to capture the complex interplay of genetic and physiological risk factors in diverse populations. This study evaluated a hybrid predictive model integrating polygenic risk scores (PRS), artificial intelligence (AI) applied to electrocardiography (ECG), and traditional clinical variables to enhance cardiovascular risk prediction across Latin American cohorts from Mexico, Colombia, and Ecuador. A total of 6,450 participants aged 30 to 75 years were analyzed. PRS were derived from genome-wide association data, and ECGs were processed using deep convolutional neural networks. Model performance was assessed using AUROC, F1-score, and calibration metrics, with interpretability achieved through SHAP (Shapley Additive Explanations) analysis. The hybrid model demonstrated superior predictive accuracy (AUROC 0.91; F1-score 0.87; calibration slope 0.97) compared with the clinical (0.72), PRS (0.78), and AI-ECG (0.86) models. The most influential predictors were PRS, systolic blood pressure, age, and AI-derived electrical age. Subgroup analyses revealed consistent performance across ancestries (Mestizo 0.91; Amerindian 0.89; European 0.93; Afro-descendant 0.87) and countries, confirming the model’s generalizability and fairness. These findings demonstrate that integrating genetic and AI-based physiological data significantly improves cardiovascular risk assessment, enabling early, equitable, and personalized prevention. The proposed hybrid framework provides a scalable foundation for implementing AI-driven genomic precision medicine in multi-ancestry populations, marking an essential step toward reducing cardiovascular disparities in Latin America.
Downloads
References
Anjewierden, S., et al. (2025). Artificial intelligence–derived electrocardiographic age correlates with comorbidities and mortality. JACC: Advances, 4(2), 101777. https://doi.org/10.1016/j.jacadv.2025.101777
Baek, Y. S., et al. (2023). Artificial intelligence-estimated biological ECG heart age and association with cardiovascular outcomes. Frontiers in Cardiovascular Medicine, 10, 1137892. https://doi.org/10.3389/fcvm.2023.1137892
Cai, Y., Tang, L.-Y., Gong, M., Wang, Y.-H., & Hu, W. (2024). Artificial intelligence in the risk prediction models of cardiovascular disease: a systematic review and independent validation screening. BMC Medicine, 22, 56. https://doi.org/10.1186/s12916-024-03273-7
Dapamede, T., Urooj, A., Joshi, V., Gershon, G., Li, F., Chavoshi, M., & van Assen, M. (2025). Novel AI-based quantification of breast arterial calcification to predict cardiovascular risk. arXiv preprint. https://doi.org/10.48550/arXiv.2503.14550
Dhingra, L., et al. (2025). Artificial intelligence–enabled prediction of heart failure using 12-lead ECG: a multicenter study. Journal of the American College of Cardiology, 85(3), 201–214. https://doi.org/10.1016/S0735-1097(24)02267-8
Gollob, M. H. (Ed.). (2010). Principles and Practice of Clinical Cardiovascular Genetics. Oxford University Press. https://global.oup.com/academic/product/principles-and-practice-of-clinical-cardiovascular-genetics-9780195368956
Hempel, P., et al. (2025). Explainable artificial intelligence associates ECG aging effects with cardiovascular risk. NPJ Digital Medicine, 8(1), 45. https://doi.org/10.1038/s41746-024-01428-7
Hughes, J. W., et al. (2023). A deep learning–based electrocardiogram risk score for long-term cardiovascular mortality and disease. NPJ Digital Medicine, 6(1), 169. https://doi.org/10.1038/s41746-023-00916-6
Lusis, A. J. (Ed.). (2014). The Genetics of Cardiovascular Disease. Springer. https://doi.org/10.1007/978-1-4613-2305-1
Natarajan, P., O’Sullivan, J. W., Raghavan, S., Marquez-Luna, C., Chaffin, M., Kanai, M., et al. (2022). Polygenic risk scores for cardiovascular disease: A scientific statement from the American Heart Association. Circulation, 146(8), e93–e118. https://doi.org/10.1161/CIR.0000000000001077
Ouyang, D., Theurer, J., Stein, N. R., Hughes, J., Elias, P., et al. (2023). Expanding electrocardiogram abilities for postoperative mortality: PreOpNet deep-learning model. The Lancet Digital Health, 5(4), e195–e206. https://doi.org/10.1016/S2589-7500(23)00023-3
Papageorgiou, V. E., Zegkos, T., Efthimiadis, G., & Tsaklidis, G. (2022). Analysis of digitalized ECG signals based on artificial intelligence and spectral analysis methods specialized in ARVC. arXiv preprint. https://doi.org/10.48550/arXiv.2203.00504
Patel, A. P., et al. (2023). A multi-ancestry polygenic risk score improves risk prediction for coronary artery disease. Nature Medicine, 29(1), 183–192. https://doi.org/10.1038/s41591-023-02429-x
Pavluk, D., et al. (2025). AI-ECG-derived biological age as a predictor of mortality and cardiovascular outcomes. European Heart Journal Digital Health, 6(2), ztaf109. https://doi.org/10.1093/ehjdh/ztaf109
Poterucha, T. J., Jing, L., Pimentel, R., et al. (2025). Detecting structural heart disease from electrocardiograms using deep learning. Nature. https://doi.org/10.1038/s41586-025-09227-0
Samani, N. J., Beeston, E., Greengrass, C., Riveros-McKay, F., Debiec, R., Lawday, D., Wang, Q., Budgeon, C. A., Braund, P. S., Bramley, R., … Nelson, C. P. (2024). Polygenic risk score adds to a clinical risk score in the prediction of cardiovascular disease in a clinical setting. European Heart Journal, 45(34), 3152–3160. https://doi.org/10.1093/eurheartj/ehae342
Sau, A., et al. (2024). Artificial intelligence–enabled electrocardiogram for mortality and cardiovascular risk estimation: a model development and validation study. The Lancet Digital Health, 6(11), e791–e802. https://doi.org/10.1016/S2589-7500(24)00172-9
Singh, M., Kumar, A., Khanna, N. N., Laird, J. R., Nicolaides, A., Faa, G., Johri, A. M., et al. (2024). Artificial intelligence for cardiovascular disease risk assessment in a personalised framework: a scoping review. EClinicalMedicine, 73, 102660. https://doi.org/10.1016/j.eclinm.2024.102660
Sun, L., et al. (2023). Using polygenic risk scores for prioritizing individuals at greatest risk of cardiovascular disease. Journal of the American Heart Association, 12(5), e029296. https://doi.org/10.1161/JAHA.122.029296
Xiang, F., et al. (2022). A polygenic risk score improves risk stratification of coronary artery disease: A large-scale prospective Chinese cohort study. European Heart Journal, 43(18), 1702–1711. https://doi.org/10.1093/eurheartj/ehac093
Downloads
Published
Issue
Section
License
Copyright (c) 2025 César Eduardo Ceja Tovar , Jose Ruben Romero Castellares, Mario Alfonso Blanco Gomez, José Enrique González Araujo , Erick Trejo López , Andrés Marcelo Córdova López, Saúl Cruz Ramirez , Cristian Alonso Duarte Carreño (Autor/a)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Los artículos publicados en la revista se distribuyen bajo la licencia Creative Commons Atribución 4.0 Internacional (CC BY 4.0). Esta licencia permite a terceros descargar, copiar, distribuir, adaptar y reutilizar una obra, incluso con fines comerciales, siempre que se otorgue el crédito adecuado al autor original.
