A general architecture for intelligent tutoring of diagnostic classification problem solving

Rebecca S Crowley, Olga Medvedeva
2003 AMIA Annual Symposium Proceedings  
We report on a general architecture for creating knowledge-based medical training systems to teach diagnostic classification problem solving. The approach is informed by our previous work describing the development of expertise in classification problem solving in Pathology. The architecture envelops the traditional Intelligent Tutoring System design within the Unified Problem-solving Method description Language (UPML) architecture, supporting component modularity and reuse. Based on the domain
more » ... ontology, domain task ontology and case data, the abstract problem-solving methods of the expert model create a dynamic solution graph. Student interaction with the solution graph is filtered through an instructional layer, which is created by a second set of abstract problem-solving methods and pedagogic ontologies, in response to the current state of the student model. We outline the advantages and limitations of this general approach, and describe it's implementation in SlideTutor - a developing Intelligent Tutoring System in Dermatopathology.
pmid:14728159 pmcid:PMC1479898 fatcat:xvaxxtpfubf45eej4urskhfjzm