A STATISTICALLY RULE-BASED DECISION-SUPPORT SYSTEM FOR THE MANAGEMENTOF PATIENTS WITH SUSPECTED LIVER-DISEASE

The paper describes how a decision support system in liver diseases, m ostly oriented to prediction of the necessity for liver biopsy, has be en developed. The system designed is a hybrid one and consists of two parts: logical and statistical. The logical part contains rules, formu lated on the basis of current medical knowledge, which enables recogni tion of clear cases; diseased or non-diseased. The unclear cases are c lassified on the basis of rules statistically extracted from databases . These rules have been reached after a comprehensive exploratory anal ysis of the sample of 165 patients with slightly to moderately raised levels of routine liver tests but without signs or symptoms of liver d iseases. The extracted decision diagrams which simulate traditional me dical diagnosis conduct have been found to be superior to discriminant analysis and probabilistic inductive learning. They use only a limite d number of laboratory tests to detect the necessity for biopsy.