DPSN: A Novel approach for Disease Prediction based on Social Networks

Disease prediction has always been challenging and critical research area. A lot of machine learning approaches have been developed in past to address this problem. In this paper a novel approach for disease prediction has been proposed. The approach is based on social network of diseases which is constructed using similarity among patient symptoms. The edges are weighted on the basis of the cosine similarity between the diseases. Social network metrics like degree and closeness centrality are used to predict high probable disease. The proposed method has been compared with existing machine learning approaches. The experimental results show that, when predicting disease from the set of 18 possible diseases with 30 possible symptoms, the proposed technique show better performance than traditional machine learning methods.