Computer-Aided Evaluation of Liver Functional Assessment

This paper describes the organization of a computerized system whose purpose is to ascertain the presence of functional impairments in the liver and to evaluate their seriousness. The system is composed of categorical rules and decision procedures. The symptoms and the anamnestic data of a given patient trigger the categorical rules which constrain the set of hypothesizable impairments. This set of hypotheses acts as a focus of attention of the system by allowing the selection of the bioclinical tests more relevant to determine the seriousness of those impairments. The outcome of the selected tests are input to the decision procedures operating on the basis of fuzzy relations which allow a quantitative evaluation of the seriousness of the hypothesized impairments. Whereas the categorical rules have been built on the basis of the a-priori knowledge of the physicians, the parameters of the fuzzy relations have been learned automatically by means of a fuzzy inference procedure.