Classification of chronic kidney failure by applying different tree-based methods on a medical data set

Abstract

The purpose of this study is to classify chronic kidney failure (CKF) by applying different tree-based methods on the open-access CKF data set and to compare the performance of the methods used. Classification models will be created using decision trees, J48, Random Forest, and Gradient Boosted Trees from tree-based methods used in the study were applied to an open-access data set named "Chronic Kidney Disease". There are 400 patients in the data set used, 250 (62.5%) of these patients have chronic kidney failure. Different tree-based methods were implemented to classify chronic kidney failure. Among the 4 different tree-based classification models used, the model with the best classification metrics is the Random Forest model, and other models have also yielded successful results. As a result, very successful results were obtained in the study performed with the classification methods used and the chronic renal failure data set. Each model was able to classify the data with high classification performance.