Creating An Effective Machine Learning Model For Monitoring And Maintaining Cardiac Health

Heart disease causes many deaths each year, making it a major global health problem. To improve patient outcomes and reduce mortality, early detection and accurate diagnosis of heart disease are essential. When the coronary arteries become blocked, poor blood flow to the heart can be prevented, leading to coronary artery disease. Early detection of heart disease can reduce medical costs and potentially save the patient's life. Recently demonstrated methods have improved the accuracy of heart disease diagnosis in experimental data without compromising the accuracy of training data, but most of these algorithms suffer from the problem of redundancy. In this study, we develop a new analysis system to solve this problem, and the resulting system shows high recognition and good performance on both training and test data. Machine learning (ML) algorithms have shown the ability to help healthcare professionals make accurate and precise decisions. In this paper, based on the machine learning methods investigated, Decision Tree (DT) and Random Forest(RF), Using a bar graph, the accuracy of each is compared with each other.