A Hybrid Model for Liver Disease Classification

Abstract

Data Mining is one of the supreme expository aspects of automated disease newlineclassification and detection. It implicates data mining algorithms and techniques newlineto examine medical data. In recent years, liver complaints have disproportionately newlineaugmented and liver illnesses are flattering one of the most mortal sicknesses in a newlinenumber of countries. Early diagnosis of Liver Disorder is very essential for the newlinewelfare of human society. This complaint should be considered seriously by setting newlineup intelligent systems for the early diagnose and prognosis of Liver diseases. The newlineautomated classification system suffers with lack of accuracy results when compared newlinewith surgical biopsy. We propose a new a hybrid model for liver syndrome classification for analyzing the patients medical data using hybrid artificial neural network. The medical records are classified whether there is a possibility of existence of disease or not. This proposed method uses M-PSO for feature selection of input variables and M-ANN algorithm for disease classification. The presented hybrid approach improves the accuracy when compared to existing classification algorithms. The results of the algorithm were examined and evaluated using Spark tool in this work. newline