PREDICTIVE ANALYTICS IN CARDIOVASCULAR HEALTH: A MACHINE LEARNING FRAMEWORK

Abstract

Heart is an essential organ for living things to operate. The heart disease has become the leading cause of death globally. It includes different disorders that affect the heart. Many risk factors have been associated with heart diseases, which underlines a critical need for accurate, reliable, and efficient techniques for early diagnosis to assure prompt and successful management of diseases. Machine learning is a part of Artificial Intelligence, which provides very esteemed support in predicting any type of occurrence, taking priming from natural events. This research paper depicts various features associated with heart disease, and the model on basis of supervised learning algorithms as Logistic Regression, Naive Bayes, Support Vector Machine, decision tree, K-nearest neighbor, XG Boost, and random forest algorithm. It makes use of the available database of heart disease patients. The dataset comprises 303 instances and 14 attributes, and they are considered for testing that is important to test and validate the performance of different algorithms. This research paper aims at visualizing the probability of getting heart disease in the patients. The results are shown that maximum accuracy is achieved with the random forest.