Enhancing Cardiovascular Risk Assessment Through Machine Learning

Heart disease is the reason, for mortality. When it comes to addressing concerns, in a facility one of the major challenges is that numerous healthcare professionals lack the necessary expertise and confidence to handle such cases. As a result they tend to make decisions leading to progress and unfortunately fatal outcomes. In order to address this, cardiac issues have been predicted using ML methods. In this study, many methods like Naïve Baiyes, K-Nearest Neighbour, Logistic Regression, Support Vector Machine, and Random Forest been applied. By the findings of this study, KNN has a maximum accuracy of 84.33% in predicting cardiac complaints based on health factors.