Classification and Ensemble Machine Learning Techniques to Improve Healthcare Decision Making For Heart Disease

Abstract

Cardiovascular disease is one of the main reasons for demise of people in the world today, whether it is a developed country or a developing country. It is not only affecting the people living in the urban but it has also affected the people of rural areas. If we know it at the primary stage, then its side effects can be avoided by reducing the chances of heart disease. So, correct prediction of heart disease is an imperative task to assist doctors and medical experts to take decision and make effective treatment policy to save the lives of people. In this paper, we use and combine multiple classification method of data mining and machine learning to perk up the precision of classifier. We intend an iterative ensemble approach to integrate various low-performance classifiers to form a strong classifier with high precision. We took dataset from IEEE data port for its implementation which contains around 1190 instances with 11 features of heart disease. We examine on the basis of initial symptoms whether the patient has heart disease or not. We explore the application of classification and ensemble machine learning techniques to augment healthcare decision-making for heart disease. By bridging the gap between data-driven insights and clinical decision-making, these techniques pave the way for a more proactive and patient-centric approach to cardiovascular health management.