Optimizing Machine Learning Algorithms for Accurate Heart Disease Detection

Heart disease is a leading global health challenge, emphasizing the need for effective diagnostic solutions. This study evaluated the accuracy of machine learning algorithms in heart disease diagnosis with the aim of finding the most reliable method. The algorithms examined contain Random Forest, Support Vector Classifier, Gradient Boosting, AdaBoost, Optimized Logistic Regression, SVM, Naive Bayes, K-Nearest Neighbors (KNN), Decision Trees, and SGD Classifier. Among them, optimized logistic regression and naive Bayes have the highest accuracy of up to 88.52%, demonstrating their predictive capabilities. The result of this work is optimized logistic regression and naive Bayes are capable of early detection of cardiovascular disease. Offering major perspective for integration into clinical practice. Future work will explore the refinement and real-world application of these models to further improve healthcare outcomes.