Diagnosis of Coronary Artery Disease Using Deep Belief Networks

In this study, a decision-support system is presented to aid cardiologists during the diagnosis and to create a base for a new diagnosis system which separates two classes (CAD and no-CAD patients) using an electrocardiogram (ECG). 24 hour filtered ECG signals from PhysioNet were used. 15 second short-term ECG segments were extracted from 24 hour ECG signals to increase the number of samples and to provide a convenient transformation in a short period of time. The Hilbert-Huang Transform, which is effective on non-linear and nonstationary signals, was used to extract the features from short-term ECG signals. Instinct Mode Function (IMF) was extracted by applying Empirical Mode Decomposition to short-term ECG signals. The Hilbert Transform (HT) was applied to each IMF to obtain instantaneous frequency characteristics of the signal. Dataset was created by extracting statistical features from HT applied to IMF. Deep Belief Networks (DBN) which have a common use in Deep Learning algorithms were used as the classifier. DBN classification accuracy in the diagnosis of the CAD is discussed. The extracted dataset was tested using the 10-fold cross validation method. The test characteristics (sensitivity, accuracy and specificity) that are the basic parameters of independent testing in the medical diagnostic systems were calculated using this validation method. Shortterm ECG signals of CAD patients and no-CAD groups were classified by the DBN with the rates of 98.05%, 98.88% and 96.02%, for accuracy, specificity and sensitivity, respectively. The DBN model achieved higher accuracy rates than the Neural Network