Prediction of ischemic heart disease and stroke using machine learning

Abstract

Cardiovascular disease (CVD) is the leading cause of death worldwide and represents a group of disorders affecting the heart and blood vessels. A major underlying cause is Arteriosclerosis and degeneration of vessels, which lead to insufficient blood flow to the heart and brain. Risk factors include age, sex, blood pressure, and blood glucose level etc. The objective of this study was to develop machine learning models for predicting Ischemic heart disease and Stroke to investigate the influential risk factors. Patient data diagnosed with cardiovascular disease were collected from Fort Surasi Hospital, comprising 448 records. The dataset was divided into training and testing sets at an 80:20 ratio, and three models were compared: Logistic Regression, Random Forest, and XGBoost. The results revealed that the Random Forest Model achieved the highest predictive performance with an accuracy of 73.46%, indicating a moderate level of Predictive. The most influential factors contributing to Cardiovascular disease were age, Cholesterol, and Systolic Blood Pressure. Although the developed models were limited by data, which affected predictive accuracy, they can still be applied for initial risk assessment and as a guideline for planning and preventive. Furthermore, the models can be further refined to improve predictive performance for medical use in the future.

References

World Health Organization, “Cardiovascular diseases,” WHO, 2025. [Online]. Available: https://www.who.int/ health-topics/cardiovascular-diseases.

กรมควบคุมโรค, “กรมควบคุมโรค ร่วมรณรงค์วันหัวใจโลก 2566 เผยคนไทยเสียชีวิตโรคหัวใจและหลอดเลือดมากถึง 7 หมื่นราย,” ข่าวสาร กรมควบคุมโรค. [Online]. Available: https://ddc.moph.go.th/brc/news.php?news=37372&deptcode=brc

N.D. Wong et al., “Atherosclerotic cardiovascular disease risk assessment: An American Society for Preventive Cardiology clinical practice statement,” Am. J. Prev. Cardiol., vol. 10, p. 100335.

J. Bosomworth, “Practical use of the Framingham risk score in primary prevention: Canadian perspective,” Can. Fam. Physician, vol. 57, no. 4, pp. 417–423, Apr. 2011. K. Elissa, “Title of paper if known,” unpublished.

คณะแพทยศาสตร์ โรงพยาบาลรามาธิบดี มหาวิทยาลัย มหิดล, “Thai CV risk score,” เว็บไซต์คณะแพทยศาสตร์ โรงพยาบาลรามาธิบดี มหาวิทยาลัยมหิดล, [ออนไลน์]. เข้าถึงได้จาก: https://www.rama.mahidol.ac.th/cardio_vascular_risk/thai_cv_risk_score/

A. Jabbar, B. L. Deekshatulu, and P. Chandra, “Prediction of cardiovascular disease (CVD) using hybrid machine learning techniques,” in Proc. Int. Conf. Current Trends Towards Converging Technologies (ICCTCT), Coimbatore, India, Mar. 2018, pp. 1–7, doi: 10.1109/ICCTCT.2018.8550857

A. Quesada et al., “Machine learning to predict cardiovascular risk,” Int. J. Clin. Pract., vol. 73, no. 10, p. e13389, Oct. 2019, doi: 10.1111/ijcp.13389

Subramani et al., “Cardiovascular diseases prediction by machine learning incorporation with deep learning,” Front. Med., vol. 10, p. 1150933, Apr. 2023, doi: 10.3389/fmed.2023.1150933

Bagheri et al., “Multimodal Learning for Cardiovascular Risk Prediction using EHR Data,” arXiv preprint arXiv:2008.11979, 2020.

Motwani et al., “Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis,” Eur. Heart J., vol. 38, no. 7, pp. 500-507, Feb. 2017, doi: 10.1093/eurheartj/ehw188

Chomsri, S. Suratana, W. Henkaew, M. Matrakul, and A. Suntranon, “The association between cardiovasclar risk factors with levels of cardiovascular disease risk factors and the health literacy in olde r adult,” Royal Thai Army Nurses Journal, vol. 22, no. 3, pp. 387–395, Sep.–Dec. 2021.

Wachirapant, S. Chotnaphan, K. Jamroonsawat, P. Tanyasitthasuntorn, “Association of behavioral risks and cardiovascular disease in Thai population,” Journal of Bamrasnaradura Institute, vol. 17, no. 1, pp. 1–12, Jan.–Apr. 2023.