Implementation of Machine Learning Model to Predict Heart Problem

Abstract

With the rapid growth of technology and data, the healthcare domain has emerged as one of the most important research areas in the modern period. Machine Learning is a novel method for disease prediction and diagnosis. This study demonstrates how machine learning can be used to forecast disease based on symptoms. Techniques of Machine learning such as Bayes, Random Forest, and SVM are used to forecast the disease on the supplied dataset. The research determines which algorithm is the best based on its accuracy. The accuracy of an algorithm is determined by its performance on a particular dataset. One of the most significant disorders is heart disease. We discovered machine learning models to predict heart problems in order to lower the incidence of death caused by heart disease. In this paper, we used a dataset from 1988 that included four databases: Cleveland, Hungary, Switzerland, and Long Beach V., and applied an algorithms to it to obtain the results. Previous studies had lower accuracy, therefore we focused on this research to enhance accuracy rate, precision, and recall which are very crucial parameters in medical field, in order to forecast heart problems and rescue patients. In this paper, we worked on different algorithms such as SVM, Random Forest, Naïve Bayes, Neural Network and Decision Tree. The model was implemented using the Python programming language. Analysis result indicates that SVM and Decision Tree algorithms have achieved highest accuracy which is 98.05%.