Identification and Classification of Coronary Artery Disease Patients using Neuro-Fuzzy Inference Systems

In this research patients with coronary artery disease were identified and classified through the neuro-fuzzy network with the capacity of automatically extracting fuzzy rules. Fuzzy expert system was implemented using facilities and functions of MATLAB software (7.12.0 version). Network parameters, introductory and lower parameters, were trained by back-propagation error (gradient descent) method. The proposed method was evaluated through data collected from medical files of 152 patients with coronary angiography in Kowsar Hospital, Shiraz, Iran during September, 2013. The performance indicators of this system were specificity and sensitivity. The indicators, as extracted from testing results, were found to be 0.88 and 1, respectively.