Heart Disease Classification–Based on the Best Machine Learning Model

Abstract

In recent years, predicting heart disease has become one of the most demandingtasks in medicine. In modern times, one person dies from heart disease everyminute. Within the field of healthcare, data science is critical for analyzing largeamounts of data. Because predicting heart disease is such a difficult task, it isnecessary to automate the process in order to prevent the dangers connected with itand to assist health professionals in accurately and rapidly diagnosing heart disease.In this article, an efficient machine learning-based diagnosis system has beendeveloped for the diagnosis of heart disease. The system is designed using machinelearning classifiers such as Support Vector Machine (SVM), Nave Bayes (NB), andK-Nearest Neighbor (KNN). The proposed work depends on the UCI database fromthe University of California, Irvine for the diagnosis of heart diseases. This dataset ispreprocessed before running the machine learning model to get better accuracy inthe classification of heart diseases. Furthermore, a 5-fold cross-validation operatorwas employed to avoid identical values being selected throughout the modellearning and testing phase. The experimental results show that the Naive Bayesalgorithm has achieved the highest accuracy of 97% compared to other MLalgorithms implemented.