The document summarizes literature on using data mining classification techniques to predict kidney disease. It first provides background on data mining and kidney disease, describing common risk factors, symptoms, and types of kidney diseases. It then reviews several studies that have applied techniques like decision trees, artificial neural networks, naive Bayes, support vector machines, and logistic regression to kidney disease data with promising results in predicting disease and survival rates. Overall, the literature suggests data mining methods show high potential for successful kidney disease prediction.