Comparison of Belief Network Classifier and Rule-based System for Diagnosis of Liver Diseases

Computer base methods are increasingly used to improve the quality of medical services. Expert system uses knowledge, facts and reasoning techniques to solve problems that normally require the expertise, experiences and the abilities of human experts. This paper presents the comparison of a belief network classifier and rule-based expert system for the liver diseases. Bayesian Belief Networks provide a mathematically correct and therefore more accurate method of measuring the effects of events on each other. Belief offers an approach for dealing with uncertain information in knowledge-based (expert) systems. The theory of belief networks is mathematically sound, based on techniques from probability theory. CN2 Rule is used to implement the rule-based expert system for the comparison process. The system intends to automatically create and maintain knowledge for an intelligence assistant system of various domains. Case study used in this system is, identifying liver disorder (cirrhosis and heptocellular carcinoma).Experimental Results show that Bayesian Belief Network approach outperforms over other classification algorithm