ON THE APPLICABILITY OF DIAGNOSTIC-CRITERIA FOR THE DIAGNOSIS OF RHEUMATOID-ARTHRITIS IN AN EXPERT-SYSTEM

CADIAG-2/RHEUMA is a medical expert system developed to assist in the differential diagnosis of rheumatic diseases. Based on fuzzy set theor y and fuzzy logic, it supports the formalization of vague and uncertai n medical information (i.e., medical entities and relationships betwee n them) and draws justifiable conclusions from these imprecise data. G iven a patient's finding pattern, CADIAG-2 provides confirmed and excl uded diagnoses, diagnostic hypotheses, and suggestions for further exa minations. The knowledge base Of CADiAG-2 has been designed to contain simple finding/disease relationships as well as diagnostic rules of h igh complexity to confirm or hypothesize diseases. We shall present re sults obtained with 300 clinical cases from a hospital for rheumatic d iseases. Different rules for the diagnosis of rheumatoid arthritis bas ed upon classification criteria issued by the American Rheumatism Asso ciation were tested against each other. That diagnostic rule which had shown the best results was then further improved by a rheumatology ex pert, which finally yielded a sensitivity of 83.3% and a specificity o f 95.3%.