Machine Learning–Driven Frameworks for Predicting Stroke Risk Factors: A Comprehensive Systematic Review

Stroke remains one of the leading causes of mortality and long-term disability worldwide, creating substantial clinical, economic, and social burdens. Despite significant advances in prevention and treatment, the increasing prevalence of cardiovascular diseases, aging populations, and lifestyle-related risk factors continue to elevate stroke incidence across diverse populations. Traditional stroke risk assessment approaches rely primarily on statistical models and clinician-based evaluations; however, these methods often struggle to capture complex nonlinear interactions among multiple risk determinants. The emergence of machine learning (ML) has introduced innovative opportunities for improving predictive accuracy, enabling personalized risk assessment, and supporting proactive healthcare interventions. This systematic review critically examines the role of machine learning–driven frameworks in predicting stroke risk factors, synthesizing evidence from contemporary studies addressing epidemiological trends, clinical determinants, predictive analytics, and computational modeling approaches. The review analyzes existing machine learning methodologies, including nonlinear predictive systems, cardiovascular risk-based frameworks, and healthcare analytics models applied to stroke prediction. Furthermore, it evaluates the strengths, limitations, and practical implications of ML-based risk prediction systems within clinical environments. Findings indicate that machine learning models consistently outperform conventional risk stratification approaches in handling multidimensional datasets, identifying hidden relationships among variables, and supporting individualized prediction. However, challenges related to data quality, model interpretability, generalizability, and clinical integration remain significant barriers to widespread adoption. The review proposes a conceptual framework integrating epidemiological, clinical, and computational dimensions to strengthen future stroke prediction systems. The study contributes to the growing literature on intelligent healthcare analytics by providing a comprehensive assessment of machine learning applications for stroke risk prediction and identifying future directions for research and implementation.

Stroke Prediction, Machine Learning, Risk Factors, Predictive Analytics

Arafa, A., Y. Kokubo, H.A. Sheerah, Y. Sakai and E. Watanabe et al., 2022. Developing a stroke risk prediction model using cardiovascular risk factors: The suita study. Cerebrovasc. Dis., 51: 323-330.

Deo, R.C., 2015. Machine learning in medicine. Circulation, 132: 1920-1930.

Feigin, V.L., M. Brainin, B. Norrving, S. Martins and R.L. Sacco et al., 2022. World Stroke Organization (WSO): Global stroke fact sheet 2022. Int. J. Stroke, 17: 18-29.

Ibrahim, M.S. and S. Saber, 2023. Machine learning and predictive analytics: Advancing disease prevention in healthcare. J. Contemp. Healthcare Anal., 7: 53-71.

Konduru, S.S.T., A. Ranjan, A. Bollisetty and V. Yadla, 2018. Assessment of risk factors Influencing functional outcomes in cerebral stroke patients using modified Rankin scale. World J. Pharm. Pharm. Sci., 7: 755-769.

Maida, C.D., R.L. Norrito, M. Daidone, A. Tuttolomondo and A. Pinto, 2020. Neuroinflammatory mechanisms in ischemic stroke: Focus on cardioembolic stroke, background, and therapeutic approaches. Int. J. Mol. Sci., Vol. 21. 10.3390/ijms21186454.

Murphy, S.J.X. and D.J. Werring, 2020. Stroke: Causes and clinical features. Medicine, 48: 561-566.

Nakibuuka, J., M. Sajatovic, J. Nankabirwa, A.J. Furlan and J. Kayima et al., 2015. Stroke-risk factors differ between rural and urban communities: Population survey in Central Uganda. Neuroepidemiology, 44: 156-165.

Orfanoudaki, A., E. Chesley, C. Cadisch, B. Stein, A. Nouh, M.J. Alberts and D. Bertsimas, 2020. Machine learning provides evidence that stroke risk is not linear: The non-linear Framingham stroke risk score. PLoS ONE, Vol. 15. 10.1371/journal.pone.0232414.

Ovbiagele, B., L.B. Goldstein, R.T. Higashida, V.J. Howard and S.C. Johnston et al., 2013. Forecasting the future of stroke in the United States: A policy statement from the American Heart Association and American Stroke Association. Stroke, 44: 2361-2375.

Rasool, S., A. Husnain, A. Saeed, A.Y. Gill and H.K. Hussain, 2023. Harnessing predictive power: Exploring the crucial role of machine learning in early disease detection. JURIHUM: J. Inovasi Humaniora, 1: 302-315.

Sacco, R.L., 1997. Risk factors, outcomes, and stroke subtypes for ischemic stroke. Neurology, 49: S39-S44.

Saceleanu, V.M., C. Toader, H. Ples, R.A. Covache-Busuioc and H.P. Costin et al., 2023. Integrative approaches in acute ischemic stroke: From symptom recognition to future innovations. Biomedicines, Vol. 11. 10.3390/biomedicines11102617.

Saini, N.R. and A.L. Gurvendra, 2022. Stroke-related risk factors: A review. Asian Pac. J. Health Sci., 9: 102-107.

South, K., L. McCulloch, B.W. McColl, M.S.V. Elkind, S.M. Allan and C.J. Smith, 2020. Preceding infection and risk of stroke: An old concept revived by the COVID-19 pandemic. Int. J. Stroke, 15: 722-732.

Thayabaranathan, T., J. Kim, D.A. Cadilhac, A.G. Thrift and G.A. Donnan et al., 2022. Global stroke statistics 2022. Int. J. Stroke, 17: 946-956.

Tsao, C.W., A.W. Aday, Z.I. Almarzooq, A. Alonso and A.Z. Beaton et al., 2022. Heart disease and stroke statistics-2022 update: A report from the American Heart Association. Circulation, 145: e153-e639.

Tsao, C.W., A.W. Aday, Z.I. Almarzooq, C.A.M. Anderson and P. Arora et al., 2023. Heart disease and stroke statistics-2023 update: A report from the American heart association. Circulation, 147: e93-e621.