Prediction Of Cardiovascular Diseases Using Machine Learning

Abstract

A condition of the heart or blood vessels is called cardiovascular disease (CVD). Globally, cardiovascular diseases (CVDs) constitute the primary cause of mortality. Coronary heart disease is among the most frequent cardiovascular conditions. Additional examples of coronary heart disease include aortic disease, peripheral artery disease, strokes, and decreased or obstructed blood supply to the heart muscle. Another important fact regarding cardiovascular disorders is that they are typically linked to an accumulation of fatty deposits within the arteries and a heightened risk of blood clots. In this work, I developed a cardiovascular disease prediction model using machine learning techniques, with 92.62% and 89.05% accuracy rates, respectively, for the Stacking Classifier and k-Nearest Neighbors algorithms. This model is performed exceptionally well and demonstrates the potential utility of machine learning as a tool for cardiovascular disease. In addition to Random Forest and Decision Tree, I evaluated several other algorithms, including Support Vector Machine and Logistic Regression and an ensemble model using Voting Classifier. Here, a Support Vector Machine could provide better accuracy. Our findings show that Stacking Classifiers, KNN, and machine learning have the potential to predict cardiovascular disease and imply that these technologies may prove beneficial in enhancing the disease's detection and management.