Intelligent systems for the diagnosis and classification of Endocrine Myopathy (EM) plays very significant role in the medical field. Neuro-fuzzy system is refers to combinations of artificial neural networks and fuzzy logic, in which fuzzy system works like human reasoning and the learning structure of neural networks. The plan of this paper is to present the Neuro-fuzzy system for the classification of Endocrine Myopathy diseases at second level. Neuro-fuzzy system has advantage to reduce the number of rules and decrease computational time, learns faster.