Prediction of coronary heart diseases using supervised machine learning algorithms

Abstract

Cardiovascular disease is a leading cause of death worldwide. According to the Centers for Disease Control and Prevention, one person dies from heart disease every 36 seconds in the United States. In 2019, an estimated 17.9 million people died from CVD worldwide. High blood pressure, an unhealthy diet, high cholesterol, diabetes, air pollution, obesity, tobacco use, kidney disease, physical inactivity, harmful alcohol use, and stress can all contribute to it. Family history, ethnic background, sex, and age are some other contributing factors to a person’s risk of heart disease. This paper seeks to predict heart diseases using a dataset that has factors like age, sex, the number of cigarettes smoked, etc. This prediction will be done by analyzing different parameters like blood pressure, oxygen level, hemoglobin count, etc. which are the major deciding factors to measure heart risks. The research will use supervised Machine Learning (ML) algorithms such as decision tree (a classification algorithm that works on categorical as well as numerical data), K-Nearest Neighbor (K-NN), Random forest algorithm, etc. to provide an accurate prediction. After applying ML on medical data, the outcome will be used to conduct a comparative analysis to measure the efficiency of different ML algorithms in predicting cardiovascular diseases. Furthermore, the major objective of this research is to use the algorithms and process in Bangladeshi dataset and explore the result outcome and newer possibilities.