A New Approach to Help Diagnose Coronary Artery Disease

Coronary Artery Disease (CAD) is a significant risk factor for everyone worldwide in recent decades. Reducing this risk depends on early diagnosis and treatment of the disease. Software that can help experts is as essential as experts for early diagnosis. In this paper, we propose an approach that can help diagnose CAD. This approach is developed using the Z-Alizadeh Sani dataset. This dataset has an unbalanced data distribution, so the dataset is balanced with the ADASYN method. Then, feature selection was performed with particle swarm optimization (PSO). The dataset with balanced and optimized feature vectors was classified into two classes, CAD or normal, by the Support Vector Machine (SVM) classifier. Performance evaluation was performed using accuracy (98,89%), sensitivity (98,89%), specificity (98,79%), and f-score (99,01%) metrics. From the evaluations, it can be concluded that the proposed work can be used as an auxiliary tool for CAD diagnosis, especially in underdeveloped regions with few experts.