Using a Neural Network to Learn General
Knowledge in a Case-Based System

Eliseo Reategui1, John A. Campbell1 and Shirley Borghetti2

1 Department of Computer Science, University College London
Gower St, London WC1E 6BT, UK
(e-mail: e.reategui, jac@cs.ucl.ac.uk)
2 Department of Transplants, The Heart Institute of So Paulo
Av. Dr. Eneas Carvalho de Aguiar 44
05403-000 So Paulo, SP - Brazil
(e-mail: dcl_edimar@pinatubo.incor.usp.br)


Abstract. This paper presents a new approach for learning general
knowledge in a diagnostic case-based system through the use of a neural 
network. We take advantage of the self-adapting nature of the neural 
network to discover the most relevant features and combination of
features for each diagnosis considered. The knowledge acquired by the
network is interpreted and mapped into symbolic diagnosis descriptors,
which are kept and used by the case-based system to guide its reasoning
process, to retrieve cases from a case library and to build explanations.
The neural network used in the learning process was the Combinatorial
Neural Model, a network that has been combined with other symbolic
approaches previously. The paper presents the method used to interpret
the knowledge learned in the neural network, as well as the guidelines
followed by the reasoning process of the CBR system. An initial experiment 
in clinical psychology is also reported, where the case-based model
introduced here was used to learn and represent the psychological proffle
of patients in evaluation for heart transplant.
References

1.	L. Becker and K. Jazayeri. A connectionist approach to case-based reasoning. In
K. J. Hammond, editor, Proceedings of the Case-Based Reasoning Workshop, pages
213217, Pensacola Beach, Florida, 1989. Morgan Kaufmann.
2.	S. A. Borghetti-Maio. Quality of life after cardiomyoplasty. Journal of heart and
lung transplantation, 13(6), 1994.
3.	3. Dinsmore. Thunder in the gap. In J. Dinsmore, editor, The connectionist and
the symbolic paradigm: closing the gap. Lawrence Eribaum Associates, Hillsdale,
NJ, 1992.
4.	J. A. Hendler. Marker-passing over microfeatures: towards a hybrid symbolic/connectionist 
model. Cognitive Science, 13:79106, 1989.
5.	J. Kolodner. Maintaining organization in a dynamic long-term memory. Cognitive
Science, 7:243280, 1983.
6.	P. Koton. Reasoning about evidence in causal explanations. In Proceedings of the
AAAI, pages 256261, St. Paul, Minnesota, August 1988. Cambridge, MA: AAAI
Press.
7.	B. F. Leo and E. B. Reategui. A hybrid connectionist expert system to solve
classificational problems. In Proceedings of Computers in Cardiology, London, UK,
1993.
8.	B. F. Leo and A. F. Rocha. Proposed methodology for knowledge acquisition: a
study on congenital heart disease diagnosis. Methods of Information in Medicine,
29:3040, 1990.
9.	D. T. Lunde. Psychiatric complications of heart transplant. American Journal of
Psychiatry, 126(3):117129, 1969.
10.	R. J. Machado and A. F. Rocha. The combinatorial neural network: a connectionist 
model for knowledge based systems. In B. Bouchon-Meunier, R. R. Yager, and
L. A. Zadeh, editors, Uncertainty in knowledge bases. Springer Verlag, 1990.
11.	R. J. Machado and A. F. Rocha. A hybrid architecture for fuzzy connectionist
expert systems. In A. Kandel and G. Langholz, editors, Hybrid architectures for
intelligent systems, pages 135152. CRC Press, Boca Raton, 1992.
12.	M. Malek and V. Rialle. A case-based reasoning system applied to neuropathy
diagnosis. In M. Keane, J. P. Haton, and M. Manago, editors, Proceedings of the
European Workshop on Case-Based Reasoning, Chantilly, France, 1994.
13.	P. Myllymaki and H. Tirri. Massively parallel case-based reasoning with probabilistic 
similarity metrics. In K-D. Althoff, K. Richter, and S. Wess, editors, Proceedings 
of the First European Workshop on Case-Based Reasoning, pages 4853,
Kaiserslautern, November 1993.
14.	M. E. Olbrich and J. L. Levenson. Psychosocial evaluation of heart transplant
candidates: an international survey of process, criteria and outcomes. Journal of
heart and lung transplantation, 10(6):948955, 1991.
15.	B. W. Porter, R. Bareiss, and R. C. Holte. Concept learning and heuristic classification 
in weak theory domains. Artificial Intelligence, 45(1-2):229263, September
1990.
16.	E. B. Reategui and J. Campbell. A classification system for credit card transactions. 
In M. Keane, J. P. Haton, and M. Manago, editors, Proceedings of the
European Workshop on Case-Based Reasoning, Chantilly, France, 1994.
17.	E. B. Reategui and B. F. Leo. Integrating neural networks with the formalism
of frames. In S. Grossberg, editor, Proceedings of the World Congress on Neural
Networks, Portland, Oregon, 1993. Lawrence Erlbaum Associates.
18.	D. E Rumelhart, G. E. Hinton, and J. L. McClelland. Learning internal representations 
by error propagation. In D. E Rumeihart, J. L. McClelland, and The
PDP Research Group, editors, Parallel Distributed Processing: explorations in the
microstructures of cognition, volume 1. MIT Press, Cambridge, MA, 1986.
