AN EXPERT-SYSTEM FOR THE ANALYSIS AND INTERPRETATION OF EVOKED-POTENTIALS BASED ON FUZZY CLASSIFICATION - APPLICATION TO BRAIN-STEM AUDITORY-EVOKED POTENTIALS

EPEXS is an expert system for evoked potential analysis and interpreta tion (a medical examination performed in clinical neurophysiology labo ratories), working from available clinical records and numerical data extracted from evoked potential traces. EPEXS integrates two formalism s of knowledge representation: rules and structured objects. The rules represent the elementary concepts (shallow knowledge) and include a m odel of possibility based on the Dubois and Prade default reasoning an d possibility theory. The structured objects (prototypes) are organize d as hierarchical taxonomies (underlying knowledge). These allow the d escription of both the objects and their relationships. The heuristics used to interpret knowledge are based on two hypotheses: the unicity of the pathological process leading to several given symptoms and the progression from the general to the specific, leading to the adoption or rejection of a class of diagnoses. This avoids the problem of the d ifferential diagnosis. These sources of knowledge are used in a dynami cal way that could be described as a four-step process: acquisition of clinical data in order to define the nosological frame of the patholo gy, production of hypotheses about the nature and topography of lesion s, interpretation of data in accordance with these hypotheses, and fin ally evaluation of their likelihood. The validation shows that EPEXS t opographic diagnoses were correct in 100% of cases and 92% of it nosol ogic diagnoses were correct, and no pathological record was interprete d as normal. When examined on a given pathology basis EPEXS was not si gnificantly different from human experts as regards to performance, sp ecificity, and sensitivity. (C) 1994 Academic Press, Inc.