Automated diagnosis of coronary artery disease (CAD) patients using optimized SVM.

BACKGROUND AND OBJECTIVE: Currently Coronary Artery Disease (CAD) is one of the most prevalent diseases, and also can lead to death, disability and economic loss in patients who suffer from cardiovascular disease. Diagnostic procedures of this disease by medical teams are typically invasive, although they do not satisfy the required accuracy.

METHODS: In this study, we have proposed a methodology for the automatic diagnosis of normal and Coronary Artery Disease conditions using Heart Rate Variability (HRV) signal extracted from electrocardiogram (ECG). The features are extracted from HRV signal in time, frequency and nonlinear domains. The Principal Component Analysis (PCA) is applied to reduce the dimension of the extracted features in order to reduce computational complexity and to reveal the hidden information underlaid in the data. Finally, Support Vector Machine (SVM) classifier has been utilized to classify two classes of data using the extracted distinguishing features. In this paper, parameters of the SVM have been optimized in order to improve the accuracy.

RESULTS: Provided reports in this paper indicate that the detection of CAD class from normal class using the proposed algorithm was performed with accuracy of 99.2%, sensitivity of 98.43%, and specificity of 100%.

CONCLUSIONS: This study has shown that methods which are based on the feature extraction of the biomedical signals are an appropriate approach to predict the health situation of the patients.