Cardiovascular Diseases Risk Prediction Based on Machine Learning Models

Abstract

Cardiovascular Diseases (CVD) are the leading cause of death worldwide, CVD has a high death rate of 95% as it causes a blockage in blood vessels, which prevents blood from flowing to the brain or heart. Necessitating accurate risk prediction for effective prevention and management becomes a necessity of lowering death caused by cardiovascular disease. This paper presents a comprehensive study utilizing Logistic Regression and Decision Tree models implemented via Python to predict CVD risk. The models were trained on a dataset comprising numerous variables such as age, checkup, sex, and BMI which are essential factors and indicators that are related to health and wellbeing. A detailed evaluation would be produced, including accuracy, precision, and confusion matrix, demonstrates the efficiency of the proposed approach, with the Logistic Regression model achieving an accuracy of 91.94% and a precision of 71.94%. followed by the decision tree model achieving an accuracy of 86.14% and a precision of 19.7%.