A New Structure based on Filter-Wrapper Feature Selection and Optimized Hybrid Classification for Coronary Artery Disease Diagnosis

Coronary artery disease (CAD) is a major cause of death in the world, and requires accurate and rapid diagnosis.This study presents a new hybrid framework combining feature selection, hybrid classification, and Bayesian optimization for the improvement of CAD detection.The first approach screens the most relevant features using an Information Gain (IG) as filter feature selection method, and then those selected features are optimized by Grey Wolf Optimizer (GWO) algorithm as a wrapper feature selection method.For the classification stage, we utilized a hybrid ensemble of AdaBoost and XGBoost to exploit their complementary strengths and increase diagnostic performance.In addition, Bayesian Optimization is implemented to perform hyperparameters tuning for AdaBoost to produce the best model.Experimental results show that the proposed method achieves an average recognition accuracy of 98.72% on the Z-Alizadeh Sani dataset with the K-fold cross-validation technique, which performs much better than the conventional methods that have used the Z-Alizadeh Sani dataset.This hybrid approach has a potential of classification flexibility as a result of its feasibility and a minimum overfitting error, and an efficient selection of features, making it a reliable solution for CAD diagnosis.