Modeling for predicting the severity of hepatitis based on artificial neural networks

Abstract

This work aims to design an intelligent model capable of diagnosing and predicting the severity of the hepatitis of illness that assists physicians to make an accurate decision. The main contribution is achieved by adopting a new multiclass classifier approach based on a collected real database with new proposed features that reflect the precise situation of the disease. In this work, three artificial neural networks (ANNs) methods, namely, Back Propagation neural network (BPNN), Radial Basis Function Network (RBFN) and, K-nearest neighbor (KNN), used to forecast the level of hepatitis intensity. Real data Collected from the Gastroenterology and Liver Education Hospital of the City of Medicine in Baghdad used as modeling and forecasting samples, respectively, to compare the results of forecasting. The results show that the prediction result by the KNN network will be better than the two other methods in time record to reach an automatic diagnosis with an error rate of less than 1%. Diagnosis accuracy was 99.33% for 2-class and 88% for 5-class, which considered excellent accuracy.