Integrating Rule-Based and Case-Based Decision
Making in Diabetic Patient Management*

Riccardo Bellazzi1, Stefania Montani1, Luigi Portinale2, Alberto Riva1

1 Dipartimento di Informatica e Sistemistica
Universith di Pavia, Pavia (Italy)
2 Dipartimento di Scienze e Tecnologie Avanzate,
Universit del Piemonte Orientale A. Avogadro, Alessandria, (Italy)


Abstract. The integration of rule-based and case-based reasoning is
particularly useful in medical applications, where both general rules aud
specific patient cases are usually available. In the present paper we aim at
presenting a decision support tool for Insulin Dependent Diabetes Mellitus 
management relying on such a kind of integration. This multimodal
reasoning system airirs at providing physicians with a simitable solution to
the problem of therapy planning by exploiting, in the most flexible way,
the strengths of the two selected methods. In particular, the integration is
pursued without considering one of the modality as the most prominent
reasoning method, but exploiting complementarity in all possible ways.
In fact, while rules provide suggestions on the basis of a situation detection 
mechanism that relies on structured prior knowledge, CBR may be
used to specialize and dynamically adapt the rules on the basis of the
patients characteristics armd of the accumulated experience. On the other
hand, if a particular patient class is not sufficiently covered by cases, the
use of rules may be exploited to try to learn suitable situations, in order
to improve the competence of the case-based component. Such a work
will be integrated in the EU funded project T-IDDM architecture, and
has been preliminary tested on a set of cases generated by a diabetic
patient simulator.
References

1.	D. Aha and J. Daniels (eds.). Proc. AAAI Workshop on CBR Integrations. AAAI
Press, 1998.
2.	R.. Bellazzi, S. Montani, and L. Portinale. Retrieval in a prototype-based case
library: a case study in diabetes therapy revision. In Proc. 4th EWCBR, LNAI
1488, pages 6475. Springer Verlag, 1998.
3.	I. Bichindaritz, E. Kansu, and K.M. Sullivan. Case-based reasoning in CARE-PARTNER: 
gathering evidence for evidence-based medical practice. In Springer
Varlag, editor, Proc. 4th EWCBR, LNAI 1488, pages 334345, 1998.
4.	P.P. Bonissone and S. Dutta. Integrating case-based and rule-based reasoning: the
possibilistic connection. In Proc. 6th Conf. on Uncertainty in Artificial Intelligence,
Cambridge, MA, 1990.
5.	L.K. Branting and B.W. Porter. Rules and precedents as complementary warrants.
In Proc. 9th National Conference on Artificial Intelligence (AAAI 91), Anaheim,
1991.
6.	C. Cobelli, G. Nucci, and S. Del Prato. A physiological simulation model of the
glucoseinsulin system in type 1 diabetes. Diabetes Natrition and Metabolism, 11,
1998.
7.	The Diabetes Control and Complication Trial Research Group. The effect of intensive 
treatment of diabetes on the development and progression of long-term
complications in insulindependent diabetes mellitus. The New England Journal
of Medicine, 329:977986, 1993.
8.	P. Domningos and M. Pazzani. On the optimality of the simple Bayesian classifier
under zero-one loss. Machine Learning, 29:103130, 1997.
9.	E. Freuder (ed.). AAAI Spring Symposium on Multi-modal Reasoning. AAAI
Press, 1998.
10.	J.L. Kolodner. Case-Based Reasoning. Morgan Kaufmann, 1993.
11.	P. Koton. Integrating causal and case-based reasoning for clinical problem solving.
In Proc of the AAAI Symposium on Artificial Intelligence in Medicine, pages 5354,
Stanford, 1988.
12.	C. Larizza, R. Bellazzi, and A. Riva. Temporal abstractions for diabetic patients
management. In LNAI 1211, pages 319330. Springer Verlag, 1997.
13.	D. Macchion and D.P. Vo. A hybrid KBS for technical diagnosis learning and
assistance. In Lecture Notes in Artificial Intelligence 837, pages 301312. Springer
Verlag, 1993.
14.	S. Montani, R. Bellazzi, C Larizza, A. Riva, G. dAnnunzio, S. Fiocchi, R. Loiini,
and M. Stefanelli. Protocol-based reasoning in diabetic patient management. International 
Journal of Medical Info rmatics, 53:6177, 1999.
15.	S. Montani, R. Bellazzi, L. Portinale, S. Fiocchi, and M. Stefanelli. A case-based
retrieval system for diabetic patients therapy. In Proceedings of IDAMAP 98 workshop, 
ECAI 98, pages 6470, Brighton, 1998.
16.	L. Portinale, P. Torasso, and D. Magro. Selecting most adaptable diagnostic solutions 
through Pivoting-Based Retrieval. In Proc. 2nd ICCBR, LNAI 1266, pages
393402. Springer Verlag, 1997.
17.	M. Ramoni and P. Sebastiani. The use of exogenous knowledge to learn bayesian
networks for incomplete databases. In Advances in data Analysis, LNCS, pages
537548. Springer Verlag, 1997.
18.	E.L. Rissland and D.B. Skalak. Combining case-based and nile-based reasoning: a
heuristic approach. In Proc. 11th IJCAI, pages 524530, Detroit, 1989.
19.	A. Riva, R. Bellazzi, and M. Stefanelli. web-based system for the intelligent management 
of diabetic patients. MD Computing, 14:360364, 1997.
20.	R.. Schmidt and L. Gierl. Experiences with prototype designs and retrieval methods
in medical Case-Based Reasoning systems. In Proc. 4th EWCBR, LNAI 1488,
pages 370381. Springer Verlag, 1998.
21.	J. Surma and K. Vanhoff. Integrating rules and cases for the classification task.
In Proc. 1st ICCBR, LNAI 1010, pages 325334. Springer Verlag, 1995.
22.	D.R. Wilson and T.R. Martinez. Improved heterogeneous distance functions. Journal 
of Artificial Intelligence Research, 6:134, 1997.
