R 4 : A System to Support the Exploration of a ( Medical ) Knowledge Web

The Refiner series of intelligent systems are used to create non-overlapping category descriptions from a set of cases which have been assigned to categories by an expert. The systems generalise values for descriptors (fields) for each of the categories to create category descriptions, and suggest to the user various means by which any inconsistencies can be removed. In this proposal we put forward a suggestion for an expert system, R4, which will be the fourth iteration of the Refiner series. Unlike previous iterations, R4 will include a nondeterministic feature which will enable it to better handle noisy datasets by generating category descriptions with ‘fuzzy’ boundaries. The R4 system will be based on a case-based algorithm focussed on performing a classification task, in particular medical (differential) diagnosis; R4 will be aimed primarily at medical students and junior doctors (i.e., novice diagnosticians). The R4 algorithm will incorporate concepts from case-based reasoning, hypotheticodeductive reasoning (HDR) and illness scripts, and will perform diagnosis by means of a diagnostic web, which is an expansion of the illness script concept. This system supports the novice user as they develop and navigate through a medical knowledge web.