Classification of psychiatric disorders using artificial neural network

One fourth of the world population is affected by mental disorders during their lives. Due to lack of distinct etiology, classification of such mental disorder is based on signs and symptoms and is vulnerable to errors. In this paper, an Artificial Neural Network (ANN) classifier is proposed that is trained using past classification data so that it can correctly classify new patients based on their signs and symptoms. A set of signs and symptoms to be used as feature input has been identified. A multilayer neural network with a single hidden layer is used for the purpose of classification. The average accuracy of the proposed classifier when trained with the past data of 60 patients is found to be 96.5%. The ANN output is to be used for validating the classification of an expert so that the reliability of the traditional classification process is improved.