<![CDATA[Kidneys are important organs that function to maintain the composition of the blood by preventing the buildup of waste and controlling fluid balance in the body. Chronic kidney disease (CKD) is a global public health problem with an increasing incidence of kidney failure, poor prognosis and high treatment costs. The prevalence of CKD along with the increasing number of elderly people who have symptoms of diabetes and hypertension, about 1 in 10 of the world's population has chronic kidney disease at a certain stage. The results of a systematic review and meta-analysis conducted by Hill et al, 2016, found that the global prevalence of CKD was 13.4%. According to the results of the 2010 Global Burden of Disease, chronic kidney disease caused death ranked 27th in the world in 1990 and increased to 18th in 2010. Meanwhile, in Indonesia, it is the second most serious treatment, ranking the second largest health insurance provider after heart disease. . Based on data from the World Health Organization (WHO) shows the number of patients with acute and chronic kidney failure reaches 50%, while only 25% are known and received treatment and 12.5% are well treated. Stacked generalization is the stacking of several algorithms to determine which algorithm is more effective, because the author uses a decision tree algorithm. This algorithm is obtained from classifying three algorithms, namely decision tree, multilayer perceptron, stochastic gradient descent using weka application mining. From the classification algorithm, the decision tree algorithm is more effective than other algorithms, Decision tree is a very popular and practical approach in machine learning to solve classification problems. Data mining is a solution that is able to find hidden information content in the form of patterns and rules from large data sets so that they are easy to understand [3]. The results of the proposed research are in the form of a prediction model for kidney disease]]>
