Problems affecting the heart or blood vessels are collectively referred to as cardiovascular disease (CVD). This is usually linked to atherosclerosis, or the buildup of fatty deposits in the arteries, and a higher risk of blood clots. Cardiovascular disease is currently identified as one of the leading causes of death and disability worldwide. According to Alan Turing, clinical statistical analysis and healthcare professionals face a significant problem in predicting and diagnosing illnesses so that people might avoid them and save lives. It specifies the data collection, preprocessing, data cleaning, data transformation, data reduction, and feature scaling. It also add emphasis on encoding of categorical variables and reinforcement upon the role of feature engineering and feature selection techniques to improve prediction accuracy. This chapter presents the nominal machine learning approaches including Random Forest, Support Vector Machine, Logistic Regression, Gaussian Naive Bayes, Bernoulli Naive Bayes and Extreme Gradient Boosting and illustrates how such approaches can contribute in predicting cardiovascular disease in the study.