Featue selection effects on kidney desease analysis

Abstract

Chronic kidney disease is a universal common obstacle which its outcomes can be prevented or delayed by early detection and cure. Classification of kidney disease is vital for global improvement and accomplishment of practical guidance. Therefore, data mining and machine learning techniques can be used to discover knowledge and identify patterns for classification. Since there exist features that make noise or have low information, feature selection issue identifies useful subset of features from raw data. The fact that dimensionality reduction improves computation performance creates fast and low-cost classifiers and produces quick classified models, makes it popular in data mining and machine learning techniques. In this article, we use a set of filter and wrapper methods followed by machine learning techniques to classify chronic kidney disease. We show that feature selection techniques enable us to perform precise classification in minimum time using fewer dimensions.