Explaining Medical Model Exceptions - Computational Intelligence in Healthcare: Advanced Methodologies - page 274

Additionally a method to impute missing values was developed. This method com-
bines general domain independent techniques with expert knowledge, which is deliv-
ered as formulae for specific situations (treated as cases) and can be used for later
similar situations too. The expert knowledge is gained within a conversational process
between the medical expert, ISOR, and the system developer. Since the time of the
expert is valuable, he/she is only consulted when absolutely necessary.
In ISOR, all main CBR steps are performed: retrieval, adaptation, and revision. Re-
trieval (of usually a list of solutions) occurs by the help of keywords. Adaptation (just
like part of the imputation process of missing data) is an interactive process between
ISOR, a medical expert, and the system developer. In contrast to many CBR systems,
in ISOR revision plays an important role.
In principle, the active incorporation of a medical expert into the decision making
process seems to be a promising idea. Already in our previous work [12], a successful
Case-Based Reasoning system was developed that performed a dialog with a medical
expert user to investigate therapy inefficacy.
Since CBR seems to be appropriate for medical applications (see section 2.1) and
many medical CBR systems have already been developed, it stands to reason to
combine both ideas, namely to build systems that are both, case-oriented and
dialog-oriented.
Acknowledgements
We thank Professor Alexander Rumyantsev from the Pavlov State Medical University
for his close co-operation. Furthermore we thank Professor Aleksey Smirnov, director
of the Institute for Nephrology of St-Petersburg Medical University and Natalia
Korosteleva, researcher at the same Institute, for collecting and managing the data.
References
1. Schank, R.C., Leake, D.B.: Creativity and learning in a case-based explainer. Artificial In-
telligence 40, 353-385 (1989)
2. Kolodner, J.: Case-Based Reasoning. Morgan Kaufmann Publishers, San Mateo (1989)
3. Aamodt, A., Plaza, E.: Case-Based Reasoning: foundation issues. Methodological varia-
tion and system approaches. AI Commun. 7(1), 39-59 (1994)
4. Stottler, R.H., Henke, A.L., King, J.A.: Rapid retrieval algorithms for case-based reason-
ing. In: Proc of 11th Int Joint Conference on Artificial Intelligence, pp. 233-237. Morgan
Kaufmann, San Mateo (1989)
5. Lenz, M., Auriol, E., Manago, M.: Diagnosis and decision support. In: Lenz, M., et al.
(eds.) Case-Based Reasoning Technology. LNCS (LNAI), vol. 1400, pp. 51-90. Springer,
Heidelberg (1998)
6. Broder, A.: Strategies for efficient incremental nearest neighbor search. Pattern Recogni-
tion 23, 171-178 (1990)
7. Wilke, W., Smyth, B., Cunningham, P.: Using Configuration Techniques for Adaptation.
In: Lenz, M., Bartsch-Spörl, B., Burkhard, H.-D., Wess, S. (eds.) Case-Based Reasoning
Technology, From Foundations to Applications, pp. 139-168. Springer, Heidelberg (1998)