Heart Disease Classification–Based on the Best Machine Learning Model

Abstract

    In recent years, predicting heart disease has become one of the most demanding tasks in medicine. In modern times, one person dies from heart disease every minute. Within the field of healthcare, data science is critical for analyzing large amounts of data. Because predicting heart disease is such a difficult task, it is necessary to automate the process in order to prevent the dangers connected with it and to assist health professionals in accurately and rapidly diagnosing heart disease. In this article, an efficient machine learning-based diagnosis system has been developed for the diagnosis of heart disease. The system is designed using machine learning classifiers such as Support Vector Machine (SVM), Nave Bayes (NB), and K-Nearest Neighbor (KNN). The proposed work depends on the UCI database from the University of California, Irvine for the diagnosis of heart diseases. This dataset is preprocessed before running the machine learning model to get better accuracy in the classification of heart diseases. Furthermore, a 5-fold cross-validation operator was employed to avoid identical values being selected throughout the model learning and testing phase. The experimental results show that the Naive Bayes algorithm has achieved the highest accuracy of 97% compared to other ML algorithms implemented.