Abstract—Cardiovascular diseases (CVD) involving the heart and blood vessels are reported as the leading causes of mortality worldwide. Coronary Artery Disease (CAD) is a major group of CVD in which presence of atherosclerotic plaques in coronary arteries leads to myocardial infarction or sudden cardiac death. In the past decades, several research efforts have been made to better understand the etiology of CAD, which will enable effective CAD diagnosis and treatment strategies. In this study, we have proposed a novel Self Optimized and Adaptive Ensemble Machine Learning Algorithm for the diagnosis of CAD. In our proposed method, the system automatically selects the most appropriate machine learning models. Our main goal is to design an Optimized Adaptive Ensemble Machine Learning Algorithm that works in different CAD datasets with high accuracy even with raw dataset. One of the important aspects of the proposed method is that the solution works on real-time data without using any pre-processing techniques on the datasets. Throughout this research attempt, we obtained 88.38% accuracy using two publicly available CAD diagnosis datasets.

Index Terms—Coronary artery disease, cardiovascular disease, machine learning, data mining, ensemble methods, classification.

Burak Kolukisa, Ahmet Soran, Burcu Bakir-Gungor, V. Cagri Gungor are with Department of Computer Engineering, Abdullah Gül University, Kayseri, Turkey (email: cagri.gungor@agu.edu.tr).
Levent Yavuz and Ahmet Onen are with Department of Electrical Engineering, Abdullah Gül University, Kayseri, Turkey.
Dilsad Tuncer is with Keydata Bilgi İşlem Teknoloji Sistemleri A.Ş., Ankara, Turkey.

Cite: Burak Kolukisa, Levent Yavuz, Ahmet Soran, Burcu Bakir-Gungor, Dilsad Tuncer, Ahmet Onen, V. Cagri Gungor, "Coronary Artery Disease Diagnosis Using Optimized Adaptive Ensemble Machine Learning Algorithm," International Journal of Bioscience, Biochemistry and Bioinformatics vol. 10, no. 1, pp. 58-65, 2020.

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).