An improved comparative model for chronic kidney disease (CKD) prediction

Abstract

This paper exploit machine learning (ML) technique to find and diagnose chronic kidney disease (CKD) at mild damaged stage. Kidney disease are syndromes that cause the functions and Glomerular filtration rate (GFR) of the kidney. Nephrologist caution that the ratio of patients affected by CKD are significantly increasing. More precise Data mining and ML methods are required to predict and diagnose CKD successfully. In this paper we apply different ML classification procedures on a data set obtained from UCI repository which comprise of 400 instances, 24 features and binary classification labels. The 7-fold and 10-fold cross-validation procedures are applied on dataset to evaluate the model. The most familiar ML classification algorithms are included in this paper are Random Forest (RF), Discriminant Analysis (DA), Naive Bayes (NB), Support Vector Machine (SVM), and K-Nearest Neighbor (K-NN). All the experiments are performed in MATLAB tools. The statistical results of all algorithms proved that RF performed better then DA, NB, SVM, and K-NN with accuracies of 99.75%, 98.25%, 98%, 97%, and 92% respectively.