PREDICTING HEART FAILURE USING CLASSIFICATION METHODS

Abstract

Many cardiovascular diseases are fatal, thus early detection and treatment are crucial. The most frequent disease, heart failure, has a high fatality rate and requires meticulous monitoring and treatment. Recent advances in machine intelligence and deep learning have expanded heart failure treatment options. However, unexpected variables may cause estimates to be inaccurate, with catastrophic consequences. To fix the problem, the scientists used a dataset with thirteen crucial failure prediction variables. In this study, prediction models include SVM, decision tree, k-nearest neighbors, random forest classifier, and logistic regression. This study seeks the most accurate categorization model