Heart Disease Prediction Using Data Mining Approach

Abstract

Most of the data in today's world is computerized, these are usually scattered and not properly utilized. Data mining works like a blind stick to utilize these data. As elsewhere, Bangladesh also contains heart disease which puts people at a significant risk of death. According to the World Health Organization (WHO), an estimated 17.9 million people died from cardiovascular diseases (CVD) [10]. Although there is a lot of data, we have little knowledge of decision making. We have identified the major sources of heart disease by reviewing these data and using data mining techniques. In this paper, the data mining system uses for medical sections such as Smoke, blood pressure, diabetes, systolic blood pressure, diastolic blood pressure like 15 attributes to find predict heart disease. This prediction predicts by some data mining algorithm namely Decision tree, Artificial Neural Network (ANN), SVM. The accuracy of these algorithms is (76.94%), (79.40%) and (84.12%). This work is carried out to track the performance of certain data mining techniques on certain selected attributes, as explained later.