Towards Application of Machine Learning in Classification and Prediction of Heart Disease

Abstract

Recently, the advancement in science has been heavily credited for the advancement in medical diagnosis. The use of machine learning techniques in the medical industry is the focus of extensive ongoing research. In most countries, heart disease has developed as the leading cause of death in both urban and rural areas. According to a World Health Organization estimate, almost 23.6 million people will die from cardiovascular diseases by 2030. (CVDs). Researchers are often encouraged by advances in machine learning technology to create Computer Aided Diagnosis (CAD) systems to support doctors in making decisions. This article presents framework for the classification and prediction of heart disease. C4.5, ID3, Random Forest, KNN, and SVM are the five algorithms studied. The UCI Cleveland database database was used for the assessment. The assessment of the usefulness and consistency of data mining techniques for these algorithms revealed that the SVM was the most reliable process, followed by the KNN, Random Forest, C4.5, and finally the ID3 algorithm.