Heart disease prediction using machine learning

Heart disease is currently the leading cause of death worldwide and has become one of the most challenging diseases to diagnose. Consequently, the use of machine learning techniques for rapid disease diagnosis is recommended, which saves time for both doctors and patients. I conducted a comparative study on heart disease prediction using machine learning algorithms such as Logistic Regression, Random Forest, Decision Tree, SVM (Support Vector Machine), Naive Bayes (NB), and KNN (k-nearest neighbors). The accuracy rates obtained were 98%, 78%, 98%, 60%, 66%, and 63% for Random Forest, Logistic Regression, Decision Tree, KNN, NB, and SVM, respectively. This study explored more than just one approach to heart disease prediction. Additionally, I investigated ensemble learning techniques such as bagging, stacking, and boosting on a publicly available dataset of patients with heart disease. I found that combining these techniques significantly increased the accuracy of the predictions: 98% for stacking, 99% for bagging, and 97% for boosting. This demonstrates how integrating various techniques can enhance the precision of heart disease predictions.