The Application of Artificial Neural Network (ANN) can be time-consuming due to the selection of input features for the Multi Layer Perceptron(MLP). The number of layers, number of neurons in each layer is also determined by the input attributes. Reducing the dimensionality, or selecting a good subset of features, without sacrificing accuracy, is of great importance for neural networks to be successfully applied to the area. In this paper, we propose a neuro-genetic approach to feature selection in disease classification. Candidate feature subsets are evaluated by using three-layer feed forward neural networks. A MLP whose inputs are automatically selected using a Genetic Algorithm (GA) is developed for the diagnosis of Stroke disease and experimental results show that the classification accuracy is better with the fewer input features.

Artificial Neural Network, Genetic Algorithm, Neuro-Genetic Approach, Stroke disease