Knowledge modelisation for brainstem auditory evoked potential interpretation: EPEXS

EPEXS is an expert system based on classification for evoked potentials analysis and interpretation (a medical examination performed in clinical neurophysiology laboratories), working from available clinical records and numerical data measured from the evoked potential traces. EPEXS integrates two formalisms of knowledge representation: rules and structured objects. The rules represent the elementary concepts (shallow knowledge) and include a model of possibility based on the Dubois and Prade´s default reasoning and possibility theory. The structured objects (prototypes) are organized as hierarchical taxonomies (underlying knowledge). They allow the description of both the objects and their relationships. The heuristics used to interpret the knowledge are based on two hypothesis: the unicity of the pathological process leading to several symptoms, and the progression from the general to the specific, leading to decide between the presence or absence of a class of diagnosis. This avoids the problem of the differential diagnosis. These various knowledges are used in a dynamical way that could be described as a four step process: acquisition of clinical data in order to define the nosological frame of the pathology, production of hypothesis about the nature and topography of lesions, interpretation of data in accordance with these hypothesis and finally evaluation of their likelihood.