Cardiovascular Disease Prediction Using Machine Learning Approaches

Abstract

As of the release of COVID-19, cardiovascular disease has surpassed all other causes of mortality among both sexes. In most cases, this condition is associated with atherosclerosis and the formation of blood clots. Heart disease, stroke, and other CVDs are major causes of mortality worldwide. Because even a small inaccuracy might lead to exhaustion or death, increased precision, perfection, and accuracy are required for diagnosing and predicting heart-related disorders. In this paper, data was collected from 1189 patients with some attributes related to heart disease and kept 80% data for training, and 20% data for testing and determining their accuracy using different models. In this study, enhanced preprocessing steps were used to increase the accuracy of cardiovascular disease prediction. It aids in determining whether a patient has heart disease and helps a doctor to determine whether or not a patient has cardiovascular disease. The applied models are Extreme Gradient Boosting, Random Forest, CART, Extra Tree Classifier, and Gradient Boosting Machine. This work compared the performance of several Machine Learning algorithms that make use of the accuracy of the metrics, $F_1$ -score, recall, and precision to demonstrate the validity of our findings. The Extreme Gradient Boosting model has achieved the best 91.9% accuracy in this research.