MACHINE LEARNING MODELS FOR EARLY PREDICTION OF CARDIOVASCULAR DISEASES IN PRIMARY CARE SETTINGS
Keywords:
machine learning, cardiovascular diseases, early prediction, primary care, clinical decision support, preventive healthcare, explainable artificial intelligence.Abstract
Early prediction of cardiovascular diseases (CVDs) in primary care is crucial for effective prevention and timely intervention. Conventional risk assessment methods often have limited accuracy due to their inability to analyze complex clinical data. This study examines the use of machine learning (ML) models for early prediction of cardiovascular diseases in primary care settings. Demographic data, clinical indicators, laboratory results, and electronic health records were used to train and evaluate multiple ML algorithms, including logistic regression, random forest, and gradient boosting models. Model performance was assessed using accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC). The results show that ML-based models outperform traditional risk assessment tools in identifying high-risk patients. The integration of explainable AI methods improves model transparency and supports clinical decision-making. Overall, machine learning approaches demonstrate strong potential as decision support tools for enhancing cardiovascular disease prevention in primary healthcare.
References
Taylan O, Alkabaa A S, Alqabbaa H S, Pamukçu E, Leiva V. Early Prediction in Classification of Cardiovascular Diseases with Machine Learning, Neuro‑Fuzzy and Statistical Methods. Biology. 2023;12(1):117. DOI:10.3390/biology12010117. This study compares multiple ML and neuro‑fuzzy methods for early CVD prediction and demonstrates high classification performance of combined approaches.
Ogunpola A, Saeed F, Basurra S, Albarrak A M, Qasem S N. Machine Learning‑Based Predictive Models for Detection of Cardiovascular Diseases. Diagnostics. 2024;14(2):144. Open Access. This work reviews recent ML models for detecting CVD using diverse clinical features and highlights performance metrics of modern approaches.
Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta‑analysis. PubMed. This systematic review examines ML models using EHR data and compares their predictive performance against traditional risk scores, showing superior AUC values in many ML models.
Early Prediction in Classification of Cardiovascular Diseases with Machine Learning, Neuro‑Fuzzy and Statistical Methods – PubMed. This article proposes ML methods including support vector regression, M5Tree, and neural networks for CVD prediction and highlights their role in improving diagnostic accuracy.
Interpretable machine learning model for cardiovascular disease risk prediction: a feature decomposition‑based study. BMC Public Health. 2025;25:3639. This research constructs and validates interpretable ML models for CVD risk, using SHAP for feature importance to support clinical interpretability.
Noori Mohammad Ali S, Ahmed N M. Comparing Some Machine Learning Models for Cardiovascular Disease. Journal of Pioneering Medical Sciences. 2025;14(4):60‑66. This paper compares performance of several ML classifiers for CVD prediction, useful for understanding strengths and limitations across models.
Effective Heart Disease Prediction Using Machine Learning Techniques. This study evaluates several supervised ML algorithms and reports that models like k‑nearest neighbor can achieve high predictive accuracy, illustrating ML utility in early detection.
Bazarbayev, M. I., Bozarov, U. A., Maxsudov, V. G., & Ermetov, E. Y. (2023). Application of differential equations in the field of medicine. International Journal of Engineering Mathematics (Online), 5(1).
Maxsudov, V. G., Bazarbayev, M. I., Ermetov, E. Y., & Norbutayeva, M. Q. (2020). Types of physical education and the technologies of organization of matters in the modern education system. European Journal of Research and Reflection in Educational Sciences Vol, 8(9).
Махсудов, В. Г. (2017). Гармоник тебранишларни инновацион технологиялар асосида ўрганиш («Кейс-стади»,«Ассесмент»,«Венн диаграммаси» мисолида). Современное образование (Узбекистан), (7), 11-16.
Maxsudov, V. G. (2018). Improvement of the methodological basics of training of the section «Mechanical oscillations» in higher educational institutions (Doctoral dissertation, Dissertation.–Tashkent: 2018. https://scholar. google. com/citations).
Zuparov, I. B., Ibragimova, M. N., Norbutayeva, M. K., Otaxonov, P. E., Normamatov, S. F., Safarov, U. Q., & Maxsudov, V. G. (2023). Modern directions and perspectives of using medical information systems. Switzerland: Innovations in technology and science education, 1218-1233.
Maxsudov, V. G., Ermetov, E. Y., & Jo, Z. R. rayeva. Types of physical education and the technologies of organization of matters in the modern education system. Fan, ta‘lim va amaliyot integratsiyasi 2022. Vol. 4. P29-34.
Maxsudov, V. G. (2018). Improvement of the methodological basics of training of the section «Mechanical oscillations» in higher educational institutions (Doctoral dissertation, Dissertation.–Tashkent).
