Educational Systems


We have begun investigating educational tutoring systems, with a particular interest in the medical domain. Our observation of medical oral exams indicates that examiners generally present a student with the stub of a case and then flesh out the details as the student responds with bedside questions, requests for tests, etc. Moreover, if the student is handling the case well, the examiner often generates test results and case details that make the diagnosis more complex. On the other hand, when the student is having difficulty with the case, the examiner often simplifies the details to permit the student to work with a simplified diagnosis.

Our desire is to develop an educational system that can similarly tailor cases to the student's ability and that allows for the full range of interaction that occurs in human precepting. As a first step, we have developed a system for automatically generating patient cases from the knowledge base of a decision-support system. We are now expanding this work to generate cases of varying degrees of difficulty and will then investigate how these cases might be dynamically tailored to the individual medical student's success in diagnosing and recommending treatment.

Webber, Bonnie, Sandra Carberry, John R. Claarke, Abigail Gertner, Terrence Haarvey, Ron Ryman, and Richard Washington. Exploiting Multiple Goals and Intentions in Decision Support for the Management of Multiple Trauma: A Review of the TraumAID Project. Artificial Intelligence Journal , 105(1-2), pp. 263-293, 1998.

Carberry, Sandra and John R. Clarke M.D. TraumaCASE: Exploiting the Knowledge Base of an Existing Decision Support System to Automatically Construct Medical Cases. Proceedings of the Tenth International Symposium on Methodologies for Intelligent Systems, pp. 456-466, 1997.

Carberry, Sandra and John R. Clarke M.D. Generating Clinical Exercises of Varying Difficulty. Proceedings of the Seventh International Conference on User Modeling, pp. 273-275, 1997.

Carberry, Sandra and John Clarke, M.D. and Abigail Gertner. Automatic Construction of Medical Cases for Training and Testing Using the Knowledge Base of an Existing Decision Support System, Proceedings of the 1996 AAAI Spring Symposium on AI in Medicine, pages 16-20, 1996. (postscript paper)