Evaluation of Kernel-Based Extreme Learning Machine Performance for Prediction of Chronic Kidney Disease

Abstract

Chronic Kidney Disease (CKD) prevalence is going to increase year by year. CKD prediction can be used as one of references for further treatment. The success of CKD prediction usually depend on classifier selected. This paper proposes and evaluates Kernel-based Extreme Learning Machine to predict Chronic Kidney Disease. Subsequently, various kernel-based ELM were evaluated. We compared the performance of four kernels-based ELM, namely RBF-ELM, Linear-ELM, Polynomial-ELM, Wavelet-ELM and the performance of standard ELM. The result showed that radial basis function extrem learning machine (RBF -ELM) was higher than those from the other tested and give the best prediction sensitivity and specificity of 99.38% and 100% respectively.