A Framework for Verification of Fuzzy Rule Bases Representing Clinical Guidelines

摘要: The increase of expert knowledge is characterizing medical domain and determining a constantly growing interacting number relevant standardized specifications for care known as clinical guidelines. However, most guidelines, especially when expressed in the form condition-action recommendations, embody different kinds structural errors that compromise their effectiveness. With this respect, paper presents framework to represent recommendations “IF-THEN” fuzzy rules verify presence some anomalies. In particular, we propose method detect redundancy, inconsistency contradictoriness—a anomaly introduced first time—in very simple understandable way by using concept similarity between antecedents consequents. Formalization degrees these anomalies can be straightly interpretable measurements suggesting how suitably modify eliminate or mitigate undesired effects. has been assessed on sample set identified from literature with profitable results.