Classification of Heart Diseases with Ensemble Learning Algorithms

The heart is one of the vital organs of the human body. Preserving heart health is a crucial factor that affects our overall well-being. Heart diseases are considered a prominent health issue of our time and are recognized as one of the leading causes of death worldwide. This underscores the importance of the heart once again. Understanding this critical health issue better, developing early diagnosis techniques, and creating effective treatment plans require continuous research and effort. In this study, performance measurements of three different machine learning algorithms were obtained using a dataset with 18 features from 319795 records of individuals with and without heart disease. The research results indicate that ensemble methods (AdaBoost, Stacking, and Gradient Boosting) can be successfully applied in the diagnosis of heart disease. The classification accuracies of these algorithms are as follows: 88.80% for AdaBoost, 91.50% for Stacking, and 91.60% for Gradient Boosting. Results from this study indicate that successful methods can be used to diagnose heart disease.