A Comparative Study on Predicting Cardiovascular Disease Using Machine Learning Algorithms

Abstract

Heart disease is a global health concern because of eating patterns, office work cultures, and lifestyle changes. A machine learning-based heart attack prediction system is like having a vigilant watchdog in the medical field. To estimate the danger of a heart attack, it all boils down to analyzing data and complex algorithms. Four primary categories were established at the outset of this study: age, gender, BMI, and blood pressure. The data on heart illness was then classified using a variety of machine learning approaches, including XGBoost Model, Gradient Boosting Model, Random Forest, Logistic Regression, and Decision Trees. The results in terms of accuracy, false positive rate, precision, sensitivity, and specificity were then compared. Results in terms of accuracy, precision, recall, and f1_score were found to be greatest when using Logistic Regression (LR). It is therefore strongly recommended that data on cardiac disease can be classified using the logistic regression technique.