Neutrosophic recommender system for medical diagnosis based on algebraic similarity measure and clustering

In this paper, we propose a neutrosophic recommender system for medical diagnosis using both neutrosophic similarity measure and neutrosophic clustering to capture the treatment of similar patients at different levels within a concurrent group. The proposed algorithm allows similar patients being treated concurrently in a group. Firstly, the similarities are measured based on the algebraic operations and their theoretic properties. Secondly, a clustering algorithm is used to identify neighbors that are in the same cluster and share common characteristics. Then, a prediction formula using results of both the clustering algorithm and the similarity measures is designed. Experiment indicates the advantages and superiority of the proposal.