Ensemble Methods Toward Prediction Kidney Disease

Abstract

Healthcare transactions produces massive amounts of data that are so overwhelming and voluminous that it cannot be managed or evaluated using standard means. The technique and creativity needed for transforming these mountains of data into data that can be used to make decisions are provided by data mining. Most of the healthcare sector is "data rich," making physical management impractical. In order to separate out useful details and make links between the attributes, data mining needs these vast volumes of data. Understanding renal disease is a challenging task that requires much insight and expertise. As one of the top causes of illness in developing nations is kidney disease, which is also a silent killer in advanced nations. The medical industry uses data mining mostly to find diseases in databases. On the Kidney illness data set, the different data mining processes Decision trees, random forest, logistic-regression, and Naive Bayes are evaluated.