Machine learning-based system to predicting the diagnosis of coronary artery disease

Abstract

Heart disease is now a regular occurrence and one of the leading causes of death all over the world. Among these diseases, coronary artery disease (CAD) is one of the common diseases around the world. This necessitates a prompt and precise identification of cardiac disease. Heart disease can be managed effectively with a combination of lifestyle changes, medicine, in some cases surgery. Heart disease symptoms can be decreased, and the heart's function can be enhanced with the correct treatment. But in recent times, heart disease prediction is one of the most complicated tasks in medical field. Because predicting cardiac illness is a difficult undertaking, it is necessary to automate the process in order to avoid the risks connected with it and to inform the patient well in advance. The proposed work predicts the chances of coronary artery disease and classifies patient's risk level by implementing different machine learning techniques such as Random Forest Tree Classification, Decision Tree Algorithm and K -Nearest Neighbor Algorithm (KNN). And also discusses the viable machine learning algorithm-based web-based system and mobile application for the prediction of coronary artery disease (CAD) diagnosis accurately predict the diagnosis of coronary artery heart disease using only a few tests and features. And also, these project outcomes can be used to avoid surgical treatment and other costs. As a result, this study provides a comparative analysis of the performance of several machine learning algorithms. The experiment results verify that the Random Forest Tree algorithm has the highest accuracy of 86 percent when compared to other machine learning algorithms.