Predicting Cardiovascular Disease Risk with Machine Learning

The word “cardiovascular disease” (CVD) indicates a group of disorders that affect the circulatory system containing the heart and the blood vessels that carry blood through the body. This phrase is called to a group of health conditions that collectively impair the cardiovascular system's ability to operate normally. CVD is the reason for 30% of the world's mortality rate. Predicting CVD in a person is tough and very confusing. In this research paper, the authors have used the publicly available dataset of 304 people to train the model. The authors have applied machine learning classification techniques: Decision tree (DT), Logistic regression (LR), Naive Bayes (NB), and K nearest neighbor (KNN). The authors applied two kinds of feature extraction methods: Singular Value Decomposition (SVD) and Linear Discriminant Analysis (LDA). NB achieved the highest accuracy of 88.52 % to detect if a person is suffering from CVD or not.