Using Machine Learning Algorithms for Coronary Artery Disease (CAD) Prediction Prediction of Coronary Artery Disease (CAD) Using Machine Learning Algorithms

Coronary Artery Disease (CAD) is one of the main causes of mortality across the world. It is crucial to detect the disease at its earliest phase so as to lower the risk of death. A definitive diagnosis of CAD can only be made through a coronary angiography. However, angiography is an invasive procedure and can, in turn, lead to a number of complications. This study deals with processing the data of CAD patients to predict the right diagnosis. The research focuses on developing a model for CAD diagnosis and conducts a performance comparison of different machine learning algorithms on five hybrid medical datasets. Evaluation criteria are tried to find the best technique that works for the selected datasets. For each plan, the best results for the datasets are given. The primary purpose of the study is to compare the performance of these algorithms in diagnosing CADs with regards to factors such as sensitivity and accuracy. A simulation environment (Jupiter Notebook) is created for the experiments and Python is used as the tool for data mining. Among these algorithms, as the experimental results show, Random Forest and Decision Tree are the most accurate with the least amount of error. Decision Tree (DT) and Random Forest (RF) have demonstrated their performance in identifying CAD and achieved the simplest performance-imprecision with a low error rate. Therefore, we suggest trying to use these algorithms in a user-friendly application and testing them in clinical settings, and implementing decision support systems to assist physicians and professionals.