Cardiovascular Disease Forecast Using Machine Learning Paradigms

Abstract

In this recent era, Cardiovascular disease (CVD) propagation rate has been intensifying the cause of death worldwide among the non-communicable disease. In particular the south asian countries have a tremendous risk of cardiovascular disease at an early age than any other ethnic group. Most often it's challenging for medical practitioners to predict cardiovascular disease as it requires experience and knowledge which is a complex task to accomplish. This health industry has enormous amounts of data which is useful for making effective conclusions using their hidden information. So, using appropriate results and making effective decisions on data, some superior data analysis techniques are used, for example Naive Bayes, Decision Tree. By using some properties like (age, gender, bp, stress, etc) it can be predicted the chances of cardiovascular disease. In this study, we collected 301 sample data with 12 clinical attributes. Logistic regression, Decision tree, SVM, and Naive bayes classification algorithms have been applied to predict heart disease. In this case, logistic regression provided 86.25% accuracy. However, we also compared the UCI dataset based results with our model.