This document discusses predicting cardiovascular disease using machine learning techniques. It begins with an introduction stating that cardiovascular disease is a leading cause of death and that predictive modeling using machine learning can help mitigate this situation. It then reviews literature on previous studies applying machine learning techniques like random forest classifiers, K-nearest neighbors, and neural networks to cardiovascular disease prediction. The document proposes using a random forest classifier on a cardiovascular disease dataset to classify patients' risk in 4 stages with an accuracy of 97.56%. It describes preprocessing the dataset, training a random forest model on 75% of the data and testing it on the remaining 25%. In summary, the document reviews previous work applying machine learning to cardiovascular disease prediction and proposes classifying patients' risk into 4