Cardiovascular Disease Prediction using Machine Learning and Deep Learning
Thirupati Sai Eswar Reddy, Satwik Reddy Sripathi, Akula Dhanush, Suja Palaniswamy, R Subramani
Abstract
One of the leading causes of death is CVD(Cardiovascular disease) which is communally referred to as heart disease. CVD is the summation of disorders that affect the heart's ability to function. Every year, over 18 million people worldwide die as a result of heart disease. One in three deaths from cardiovascular disease in them is preventable, and heart attacks can be predicted months in advance by assessing the patient's risk factors. Obesity, Blood Pressure, Cholesterol, and Glucose levels are some of the risk factors. The aim is to predict CVD based on risk factors of patients, who are affected by their habits and patients' basic health information, using the Cardiovascular Disease Dataset from Kaggle using Machine Learning and Deep Learning Algorithms. Smoking and Alcohol consumption are some practices that will maximize the possibility of getting cardiovascular disorders, and doing workouts will reduce the risk of getting cardiovascular disease. In our work, we have implemented four models for predicting CVD namely Logistic Regression, Naive Bayes, Deep Learning Model and Random Forest. The DL model, with an accuracy of 73.78 %, outperformed the other three models.