Estimating the Surveillance of Liver Disorder using Classification Algorithms

Abstract

Data mining is an activity of extracting some useful knowledge from a large data base, by using any of its techniques. In this paper we are using classification, one of the major data mining models, which is used to predict previously unknown class of objects. Unlike other diseases, liver disorder prediction from common symptoms is typically difficult job for medical practitioners. Most of the features or symptoms are seen in many other fever related diseases and so it is not free from false assumptions. In most cases the opportunity of liver disease will not identified because of the domination of other diseases.

Keywords: Data mining, Classification, Liver Disease, Preprocessing, Naive Bayesian, C4.5 decision tree