Combining Medical Records with Case-Based
Reasoning in a Mixed Paradigm Design -- TROPIX
Architecture & Implementation

A. Sunny Ochi-Okorie, C.Eng., MNSE, MIEE
Visiting Scholar (Senior Lecturer- 1FUTO),
Center for Advanced Computer Studies (CACS),
The University of Southwestern Louisiana,
2 Rex Street, P0 Box 44330, Lafayette, LA 70504-4330; Email: aso@cacs.usl.edu


Abstract

The design architecture, case representation of actual medical cases, and the implementation of
TROPIX, a tropical disease diagnosis and therapy tool are presented. TROPIX is intended to be
bundled with laptop computers for rural health centers and semi-urban hospitals in developing
countries. Our model uses the ideal domain knowledge to build a decision matrix, DM from
disease features against which new cases are measured using the MVF (Matched Vector
Functions) algorithms. The result of the diagnosis stage provided by the MVF procedure and
other parameters of the features are then used for CBR case retrievals, verification, and case
validation. The final stage in the design yields the selection of 1 or 2 competing cases presented
for reuse and perhaps for subsequent repair and adaptation.
The solution for the new case solved is either one or more actions, a therapy plan or
recommendations. The design demonstrates how we can integrate domain knowledge and
(medical) records with CBR, statistical pattern recognition, and abductive reasoning to build a
knowledge based system.
7.	References

1.	Allen, J., Patterson, D., et al, Integration of Case Based Retrieval with a Relational
Database System in Aircraft Technical Support, in LNAI 1010 -Veloso M. & Aamodt A.,
(Eds.) CBR R & D, First Intl Conf., ICCBR-95, Portugal, Proceedings, pp. 1-10, 1995.
2.	Berger, J. ROENTGEN: Radiation Therapy and Case-Based Reasoning , pp. 171-177,
Proc. of the Tenth Conf. on AI for Applications, IEEE Computer Society Press, 1994
3.	Flaubert, B.S. and Esae, T.D., Expert Systems as a useful tool for tropical diseases
diagnosis: the case of malaria, Health Informatics in Africa (HELINA-L) 93, Ile-Ife,
Nigeria; Conf. Proceedings, Elsevier Science Publishers, Amsterdam, The Netherlands.
4.	Joly, S. and Le Calve, G., Similarity Functions in Van Cutsem, B. (Ed.), Classification
and Dissimilarity Analysis, LN in Statistics, Springer-Verlag, New York, 1994.
5.	Mishkoff, H.C., Understanding Artificial Intelligence, Texas Instrument Inc., Dallas, TX,
p3:17-25; 1986.
6.	Myllymki, Petri and Tirri, Henry, Massively Parallel Case-Based Reasoning with
Probabilistic Similarity Metrics, pp. 144-154 in Topics in Case-Based Reasoning, Ed.
Stetan Wess, et al, Vol. 837, LNAI, Springer Verlag, 1994.
7.	Ochi-Okorie, A.S. Disease Diagnosis Validation in TROPIX Using CBR, Accepted to
appear in The Journal of Artificial Intelligence in Medicine, Elsevier, January, 1998.
8.	Ochi-Okorie, A.S., and Dr. J. Osondu, Musing With Case Pre-Classifiers As Diagnosis
Predictors in a CBR System, Jan. 1997, Technical Report, TR-97-2-00l, The Center for
Adv. Computer Studies, The Univ. Of Southwestern Louisiana, Lafayette, LA., USA.
9.	Opiyo, E.T.O., Case-Based Reasoning for Expertise Relocation in Support of Rural
Health Workers in Developing Countries, in LNAI 1010 -Veloso M. & Aamodt A., (Eds.)
CBR R & D, First Intl Conf., ICCBR-95, Portugal, Proceedings, pp. 77-86, 1995.
10.	Ostroff, J.H., Dawson, C.R., et 4 An Expert Advisory System for Primary Eye Care in
Developing Countries, in Expert Systems in Government Symposium, ed. K. N. Karma,
IEEE Computer Society, pp. 490- 495, 1985.
11.	Reggia, J. A., Abductive Inference, in Expert Systems in Government Symposium, ed. K.
N. Karna, IEEE Computer Society, pp. 484-489, 1985.
12.	World Bank, World Development Report 1993: Investing in Health, Oxford University
Press,1993.
