Using Support Vector Machine Algorithm to Predict Coronary Heart Disease in Active Middle-aged Women

Document Type : Original Research

Authors

1 Department of Physical Education and Sport Sciences, Faculty of Humanities, Tarbiat Modares University, Tehran, Iran

2 Department of Physical Education and Sport Science, Faculty of Psychology and Education Science, University of Mohaghegh Ardabili, Ardabil, Iran

Abstract

Background and Aim: Coronary artery disease is the most common form of cardiovascular disease, and it frequently causes myocardial infarction. It causes billions of dollars in property damage and millions of deaths worldwide every year. The standard method for diagnosing cardiovascular disease is angiography, which is invasive and dangerous. A machine learning system has been widely used as a fast, cost-effective, and non-invasive approach to the diagnosis of cardiovascular disease. Therefore, the purpose of this research was to use a support vector machine algorithm to predict coronary heart disease in active middle-aged women.
Methods: In this study, the medical records of 372 middle-aged women with coronary artery disease who were hospitalized in two selected hospitals during 2015-2016 were used. A support vector machine algorithm was used to diagnose coronary artery disease. MATLAB software was used for data analysis at a significance level of 0.05.
Results: The results showed that by using medical records containing 14 common features, related to anthropometric information, diagnostic tests, angiography results, and physical activity, the support vector machine algorithm can detect vascular diseases with 70% accuracy and 76% precision.
Conclusion: The use of a machine learning approach provides the ability to predict the presence of coronary artery disease with high accuracy and sensitivity. Therefore, it allows doctors to provide timely preventive treatment in patients with coronary artery disease.

Keywords

Journal of Military Medicine
Volume 25, Issue 5 - Serial Number 123
November and December 2023
Pages 2016-2023

Files

Share

How to cite

Statistics