BackgroundChronic kidney disease (CKD) is a disorder associated with breakdown of kidney structure and function. CKD can be diagnosed in its early stage only by experienced nephrologists and urologists (medical experts) using the disease history, symptoms and laboratory tests. There are few studies related to the automatic diagnosis of CKD in the literature. However, these methods are not adequate to help the medical experts. MethodsIn this study, a new method was proposed to automatically diagnose the chronic kidney disease in its early stage. The method aims to help the medical diagnosis utilizing the results of urine test, blood test and disease history. Classification algorithms were used as the data mining methods. In the method section of the study, analysis data were first subjected to pre-processing. In the first phase of the method section of the study, pre-processing was applied to CKD data. K-Means clustering method was used as the pre-processing method. Then, the classification methods (KNN, SVM, and Naïve Bayes) were applied to pre-processed data to diagnose the CKD. ResultsHighest success rate obtained by classification methods is 97.8% (98.2% for ages 35 and older). This result showed that the data mining methods are useful for automatic diagnosis of CKD in its early stage. ConclusionA new automatic early stage CKD diagnosis method was proposed to help the medical doctors. Attributes that would provide the highest diagnosis success rate were the use of specific gravity, albumin, sugar and red blood cells together. Also, the relation between the success rate of automatic diagnosis method and age was identified.