Cardiovascular Disease Detection Using Machine Learning Algorithms

Cardiovascular diseases (CVDs) are considered as the prime cause of death across the globe. Early and highly accurate detection of heart diseases can really be helpful for the world population. Addressing this problem on a large scale is essential for keeping the world healthy. Machine learning (ML) algorithms play a vital role in detecting cardiovascular diseases, offering the potential for higher accuracy in identification. Achieving precise detection with ML algorithms holds significant benefits for people worldwide. Our research utilizes various ML algorithms including Gaussian Naive Bayes (GNB), Random Forest (RF) and Logistic Regression (LR) to identify cardiovascular diseases. After assessing individual model accuracies, we combine GNB, RF and LR using hard voting, creating the 'voting_model'. Additionally, a stacking classifier is applied using GNB, RF, LR as base estimators and LR as the final estimator. The ensemble approach demonstrates maximum accuracy compared to individual models highlighting the potential of combining diverse algorithms through ensemble learning for enhanced predictive models in cardiovascular health.