In this study, a method based on Principle Component Analysis and Least Square Support Vector Machine Classifier for Expert Hepatitis Diagnosis System (PCA-LSSVM) is introduced. This intelligent diagnosis system deals with combination of the feature extraction and classification. This intelligent hepatitis diagnosis system is separated into two phases: (1) the feature extraction from hepatitis diseases database and feature reduction by PCA, (2) the classification by LSSVM classifier. The hepatitis diseases features were obtained from UCI Repository of Machine Learning Databases. The number of these feature attributes are 19. Then, number of these features was reduced to 10 from 19 by using PCA. In second phase, these reduced features are given to inputs LSSVM classifier. The correct diagnosis performance of the PCA-LSSVM intelligent diagnosis system for hepatitis disease is estimated by using classification accuracy, sensitivity and specifity analysis respectively. (C) 2011 Elsevier Ltd. All rights reserved.