Predicting Cardiovascular Disease using Machine Learning Techniques

The heart, which is considered to be the second most vital organ after the brain, is of great importance to the human body. Heart attack, also known as myocardial infarction, is a common cardiovascular disease with a major impact on the global mortality rate. The progression of cardiac ailments generally occurs gradually, making early detection challenging, particularly in developing nations, where knowledge and technology are limited. Despite its preventability, its high mortality rate is often attributed to insufficient expertise and inadequate medical equipment. Predicting the incidence of heart disease is a significant undertaking in healthcare and medicine. However, the volume of data that hospitals and medical industries receive makes this analysis challenging. For medical professionals, using Machine Learning (ML) algorithms for data analysis and prediction can be effective. In this study, different ML algorithms, such as Logistic Regression, Random Forest, Decision Tree, Gradient Boosting, and Extreme Gradient Boosting, are utilized to analyze a dataset to predict cardiovascular disease in individuals. The performance of the models was compared using various metrics such as accuracy, precision, recall, and F1-score. Among these, the Gradient Boosting algorithm performed the best, with an accuracy of 92.68%.