Hepatitis B Diagnosis Using Logical Inference And Generalized Regression Neural Networks

Medical diagnosis is considered an art regardless of all standardization efforts made, which is greatly due to the fact that medical diagnosis necessitates an expertise in coping with uncertainty simply not found in today´s computing machinery. The researchers are encouraged by the advancement in computer technology to develop software to assist doctors in making decision without necessitating the direct consultation with the specialists. Comprehensibility is very significant for any machine learning technique to be used in computer-aided medical diagnosis. Since an artificial neural network ensemble is composed of multiple artificial neural networks, its comprehensibility is worse than that of a single artificial neural network. For medical problems, a reasonably high-quality solution could be given by the neural network algorithms. In this paper, application of artificial intelligence in typical disease Hepatitis B diagnosis has been investigated. In this research, an intelligent system based on logical inference along with a generalized regression neural network is presented for the diagnosis. An expert system based on logical inference is used to decide what type of hepatitis is possible to appear for a patient, whether it is Hepatitis B or not. Then artificial neural networks will be used in order to do the predictions regarding hepatitis B. The Generalized regression neural network is applied to hepatitis data for predictions regarding the Hepatitis B which gives severity level on the patient. Results obtained show that generalized regression neural network can be successfully used for diagnosing hepatitis B. The role of effective diagnosis and the advantages of data training on neural networks-based automatic medical diagnosis system are suggested by the outcomes.