ICARUS: integrating rule-based and case-based reasoning on the base of unsharp symptoms

One of the major tasks when developing diagnostic decision support systems is to find the best fitting inference method and knowledge representation model for the domain at hand. There are many existing approaches for decision support in different fields such as technology, economies and medicine, each using different knowledge representations and inference methods. Inference methods mainly have been designed for certain domains or at least been adapted to the domain, so that often the application of methods or representation models in other fields is not working well. Especially in fields where the knowledge is characterized by uncertainty, imprecision and vagueness, standard approaches fail. In this article a new approach (ICARUS) is presented integrating rule-based and case based reasoning in a hybrid system and using fuzzy sets and fuzzy relations for the representation and application of uncertain or imprecise knowledge. The main idea of the integration is that rule-based reasoning applies knowledge on a higher level of abstraction and is used to represent the normal case while case-based reasoning does so on a lower level of abstraction and is there for an ideal method to manage special cases. This approach was designed for a diagnostic decision support system in the field of acute abdominal pain (AAP)