In this paper, we have detected diabetes disease, which is a very common and important disease using Principal Component Analysis (PCA) and adaptive neuro-fuzzy inference system (ANFIS). The aim of this study is to improve the diagnostic accuracy of diabetes disease by combining PCA and ANFIS. Firstly, we will introduce soft computing(SC) methods and briefly refer to the applications of these methods in medicine. After, an intelligent diagnostic system for diabetes will then be developed on the PCA and the ANFIS. The structure of ANFIS with PCA intelligent system for diagnosis of diabetes is composed of two processes: In the first process, it is used PCA to nd that the distinct classes of T2DM subjects and controls. Second, the features of two classes(healthy and T2DM patients) obtained in the first process are given to inputs of ANFIS classifier.