Software-based Prediction of Liver Disease with Feature Selection and Classification Techniques

Abstract

Today’s health care is very important aspect for every human, so there is a need to provide medical services that are easily available to everyone. In this paper, the main focus is to predict the liver disease based on a software engineering approach using classification and feature selection technique. The implementation of proposed work is done on Indian Liver Patient Dataset (ILPD) from the University of California, Irvine database. The different attributes like age, direct bilirubin, gender, total bilirubin, Alkphos, sgpt, albumin, globulin ratio and sgot etc, of the liver patient dataset, are used to predict the liver diseases risk level. The various classification algorithms such as Logistic Regression, SMO, Random Forest algorithm, Naive Bayes, J48 and k-nearest neighbor (IBk) are implemented on the Liver Patient dataset to find the accuracy. The comparison different classifier results are done of feature selection and without using feature selection technique. The development of intelligent liver disease prediction software (ILDPS) is done by using feature selection and classification prediction techniques based on software engineering model.