ELECTRICA

Chronic Kidney Disease Prediction with Reduced Individual Classifiers

1.

Department of Electrical and Electronics Engineering, Istanbul University Cerrahpaşa School of Engineering, İstanbul, Turkey

2.

Department of Biomedical Engineering Department, İzmir Katip Celebi University School of Engineering, İzmir, Turkey

ELECTRICA 2018; 18: 249-255
DOI: 10.26650/electrica.2018.99255
Read: 1084 Downloads: 625 Published: 03 August 2018

Chronic kidney disease is a rising health problem and involves conditions that decrease the efficiency of renal functions and that damage the kidneys. Chronic kidney disease may be detected with several classification techniques, and these have been classified using various features and classifier combinations. In this study, we applied seven different classifiers (Naïve Bayes, HoeffdingTree, RandomTree, REPTree, Random Subspaces, Adaboost, and IBk) for the diagnosis of chronic kidney disease. The classification performances are evaluated with five different performance metrics, i.e., accuracy, kappa, mean absolute error (MAE), root mean square error (RMSE), and F measures. Considering the classification performance analyses of these methods, six reduced features provide a better and more rapid classification performance. Seven individual classifiers are applied to the six features and the best results are obtained using individual random tree and IBk classifiers.

Files
EISSN 2619-9831