Applying Machine Learning Algorithms for Kidney Disease Diagnosis

Yenatfanta Shifferaw Bayleyegn, Tariku Adane Gelaw

Keywords: Kidney disease, Chronic kidney disease, Classification, Multi layer perceptron (MLP), SVM, KNN

Track: short paper

Abstract: Kidney disease is a ‘silent killer’; it usually develops over time, and many people do not know they have it until it is very far along. Chronic Kidney Disease (represents a major public health problem in both developed and developing countries. In this rese arch, three different classification algorithms have been used in order to evaluate the occurrence of ckd on a dataset collected from the UCI Repository which holds 400 samples with 25 attributes. By filtering out t he top 14 features from the 2 4 input variables which show high score of dependability, the experimental results manifest t hat Multi Layer Perceptron (MLP) works best for both normalized and unnormalized features yielding an accuracy of 100%.