New hybrid hepatitis diagnosis system based on Genetic algorithm and adaptive network fuzzy inference system

In this paper, a hybrid method for diagnosing hepatitis diseases is introduced. The proposed method consists of two stages: the feature selection and the classification. The feature selection has been performed by Genetic algorithm (GA) as a fast and common intelligent method for feature selection to reduce the number of employed features. For the classification, a major intelligent classification method, Adaptive Network Fuzzy Inference System (ANFIS), is employed. In this way, a hybrid method of GA-ANFIS is developed and evaluated via a set of experimental data. The results are representative of the out-performance the proposed methods with respect to other methods in the literature considering the classification accuracy as the comparison tool.