Automatic disease diagnosis systems using pattern recognition based genetic algorithm and neural networks

This paper presents three disease diagnosis systems using pattern recognition based on genetic algorithm and neural networks. All systems deal with feature selection and classification. Genetic algorithm chooses subsets of features for the input of the classifier (neural network) and the accuracy of the classifier determine the percentage of effectiveness of each subsets of features. The classifiers using in this paper are general regression neural network (GRNN), radial basis function (RBF) and radial basis network exact fit (RBEF). We use breast cancer and hepatitis disease datasets taken from UCI machine learning database as medical dataset. The system performances are estimated by classification accuracy and they are compared with similar methods without feature selection.