A precise coronary artery disease prediction using Boosted C5.0 decision tree model

Abstract

In coronary artery disease, plaque builds up in the arteries that carry oxygen-rich blood to the heart. Having plaque in the arteries can constrict or impede blood flow, leading to a heart attack. Shortness of breath and soreness in the chest are common symptoms. Lifestyle modifications, medication, and potentially surgery are all options for treatment. In coronary artery disease, plaque builds up in the arteries that carry oxygen-rich blood to the heart. Having plaque in the arteries can constrict or impede blood flow, leading to a heart attack. Shortness of breath and soreness in the chest are common symptoms. Lifestyle modifications, medication, and potentially surgery are all options for treatment. This paper presents a Hybrid Boosted C5.0 model to predict coronary artery disease more precisely. A Hybrid Boosted C5.0 model is formed by combining the C5.0 decision tree and boosting methods. Boosting is a supervised machine learning method that leverages numerous inadequate models to construct a more robust and powerful model. The proposed model and some well-known existing machine learning models, i.e., decision tree, AdaBoost, and random forest, were implemented using an online coronary artery disease dataset of 6611 patients and compared based on various performance measuring parameters. Experimental analysis shows that the proposed model achieved an accuracy of 91.62% at training and 81.33% at the testing phase. The AUC value achieved in the training and testing phase is 0.957 and 0.88, respectively. The Gini value achieved in the training and testing phase is 0.914 and 0.759, respectively, far better than the proposed method.