Abstract—The purpose of this study was to assess the role of a Bayesian classifier and back propagation neural network classifier in the diagnosis of severity of appendicitis in patients presenting with right iliac fossa (RIF) pain using Alvarado scoring method. The input parameters of the classifier are the pain site, pain nature, nausea, previous surgery, RIF Tenderness, Rebound Tenderness, Guarding, Rigidity, Temperature, White blood cell count , Neutrophilcount and the output parameters are different classes of appendicitis namely mild (Inflammation only), moderate (Inflammation, Faceolith and Turgid) and severe (Gangrenous and Perforated) appendicitis. The methodology used was a back propagation neural network and Bayesian classifier for diagnosing Appendicitis. The data set is based on the statistics already collected about the presence of appendicitis from patients data set of around 2230 records collected from BHEL Hospital, Tiruchirappalli, India. The conclusion is that Bayesian classifier and back propagation neural network classifier can be used as an effective tool for accurately diagnosing the severity of appendicitis.
Index Terms—Data mining, Bayesian classification, Backpropagation Neural Networks, Appendicitis.
E. Sivasankar is working as a Lecturer in the Department of Computer Science & Engineering, National Institute of Technology, Tiruchirappalli-15,
Dr. R. S. Rajesh is working as a Reader in the Department of Computer Science & Engineering, Manonmaniam Sundaranar University Tirunelveli,
Dr. S. R. Venkateswaran is working as a Head of Surgery and Chief Administrator, BHEL Hospital, Tiruchirappalli,
Cite: E. Sivasankar, R. S. Rajesh and S. R. Venkateswaran, "Diagnosing Appendicitis Using Backpropagation Neural Network and Bayesian Based Classifier," International Journal of Computer Theory and Engineering vol. 1, no. 4, pp. 358-363, 2009.