Explanation Oriented Retrieval
This paper is based on the observation that the nearest neighbour in a case-based prediction system may not be the best case to explain a prediction. This observation is based on the notion of a decision surface (i.e. class boundary) and the idea that cases located between the target case and the decision surface are more convincing as support for explanation. This motivates the idea of explanation utility, a metric that may be different to the similarity metric used for nearest neighbour retrieval. In this paper we present an explanation utility framework and present detailed examples of how it is used in two medical decision-support tasks. These examples show how this notion of explanation utility sometimes select cases other than the nearest neighbour for use in explanation and how these cases are more convincing as explanations.
KeywordsDecision Boundary Utility Measure Oral Hypoglycaemic Agent Explanation Case Target Case
Unable to display preview. Download preview PDF.
- 1.Armengol, E., Palaudàries, A., Plaza, E.: Individual Prognosis of Diabetes Longterm Risks: A CBR Approach. Methods of Information in Medicine. Special issue on prognostic models in Medicine 40, 46–51 (2001)Google Scholar
- 2.Aleven, V., Ashley, K.D.: Automated Generation of Examples for a Tutorial in Case-Based Argumentation. In: Frasson, C., McCalla, G.I., Gauthier, G. (eds.) ITS 1992. LNCS, vol. 608, pp. 575–584. Springer, Heidelberg (1992)Google Scholar
- 5.Coyle, L., Doyle, D., Cunningham, P.: Representing Similarity for CBR in XML. To appear in 7th European Conference in Case-Based Reasoning (2004)Google Scholar
- 7.Doyle, D., Loughrey, J., Nugent, C., Coyle, L., Cunningham, P.: FIONN: A Framework for Developing CBR Systems, to appear in Expert UpdateGoogle Scholar
- 8.Evans-Romaine, K., Marling, C.: Prescribing Exercise Regimens for Cardiac and Pulmonary Disease Patients with CBR. In: Workshop on CBR in the Health Sciences at 5th International Conference on Case-Based Reasoning (ICCBR 2003), Trondheim, Norway, June 24, pp. 45–62 (2003)Google Scholar
- 9.Kass, A.M., Leake, D.B.: Case-Based Reasoning Applied to Constructing Explanations. In: Kolodner, J. (ed.) Proceedings of 1988 Workshop on Case-Based Reasoning, pp. 190–208. Morgan Kaufmann, San Mateo (1988)Google Scholar
- 10.Leake, D.B.: CBR in Context: The Present and Future. In: Leake, D.B. (ed.) Case-Based Reasoning: Experiences, Lessons and Future Directions, pp. 3–30. MIT Press, Cambridge (1996)Google Scholar
- 11.Lenz, M., Burkhard, H.-D.: Case Retrieval Nets: Basic ideas and extensions. In: Görz, G., Hölldobler, S. (eds.) KI 1996. LNCS, vol. 1137, pp. 227–239. Springer, Heidelberg (1996)Google Scholar
- 13.McSherry, D.: Explanation in Case-Based Reasoning: an Evidential Approach. In: Procceedings 8th UK Workshop on Case-Based Reasoning, pp. 47–55 (2003)Google Scholar
- 16.Rahman, Y., Knape, T., Gargan, M., Power, G., Hederman, L., Wade, V., Nolan, J.J., Grimson, J.: e-Clinic: An electronic triage system in Diabetes Management through leveraging Information and Communication Technologies. Accepted for MedInfo 2004Google Scholar