Fuzzy logic inference model for a rule-based system in medical diagnosis

Intrinsically vague knowledge is typical of the decision processes involved in medical diagnosis, especially when they are based on complex and non numeric data. Linquistic descriptions of the symptoms exhibited by a given patient do not, by definition, represent a precise numeric concept and diagnostic classes cannot be modelled in terms of crisp sets. Fuzzy set theory and fuzzy logic provide an appropriate framework for the representation of imprecise medical concepts and imprecise modes of reasoning. A medical expert system with a fuzzy inference model, for the diagnosis of involutional osteoporosis is presented. Medical knowledge is represented in the form of relationships between combinations of symptoms and diagnostic classes. Two categories of disease, postmenopausal osteoporosis and senile osteoporosis are identified and three diagnostic classes are introduced for each disease category expressing the degree of severity of the disease: Definite, Possible, Excluded. For each diagnostic class the system infers a conclusion expressing the degree of satisfaction in the choice of the diagnostic class.