Improving the Estimation of Coronary Artery Disease by Classification Machine Learning Algorithm

This research paper aims to predict coronary artery disease (CAD) using data from 350 patients collected at one of the hospitals in Armenia. CAD is a critical parameter which can have a significant impact on patients' life and survival. The study considers several input variables, including level of cholesterol (LOC), patient's age (PA), type of chest pain (TCP), number of arteries blocked (NAB), sex (S), and family history (FH), to make accurate predictions. To achieve this crucial task of CAD prediction, the researchers employed three powerful classification algorithms: Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR). Among these, the Random Forest algorithm stands out for its robustness and numerous advantages, including high accuracy, ability to handle outliers effectively, provision of feature importance insights, and reduced risk of overfitting. The research findings presented in this article demonstrate the impressive performance of the Random Forest algorithm, showcasing an accuracy value of 0.95 and a precision value of 0.94. These results indicate the model's ability to make precise and reliable predictions, essential when dealing with a life-or-death parameter like CAD. By conducting a comparative analysis based on statistical parameters, the researchers establish that Random Forest outperforms both SVM and LR. Thus, the conclusion drawn from the study suggests that the ranking of the algorithms based on their performance is as follows: RF > SVM > LR.