Abstract
This tutorial paper has been written for biologists, physicians or beginners in fuzzy sets theory and applications. This field is introduced in the framework of medical diagnosis problems. The paper describes and illustrates with practical examples, a general methodology of special interest in the processing of borderline cases, that allows a graded assignment of diagnoses to patients. A pattern of medical knowledge consists of a tableau with linguistic entries or of fuzzy propositions. Relationships between symptoms and diagnoses are interpreted as labels of fuzzy sets. It is shown how possibility measures (soft matching) can be used and combined to derive diagnoses after measurements on collected data.
The concepts and methods are illustrated in a biomedical application on inflammatory protein variations. In the case of poor diagnostic classifications, it is introduced appropriate ponderations, acting on the characterizations of proteins, in order to decrease their relative influence. As a consequence, when pattern matching is achieved, the final ranking of inflammatory syndromes assigned to a given patient might change to better fit the actual classification. Defuzzification of results (i.e. diagnostic groups assigned to patients) is performed as a non fuzzy sets partition issued from a “separating power”, and not as the center of gravity method commonly employed in fuzzy control.
It is then introduced a model of fuzzy connectionist expert system, in which an artificial neural network is designed to build the knowledge base of an expert system, from training examples (this model can also be used for specifications of rules in fuzzy logic control). Two types of weights are associated with the connections: primary linguistic weights, interpreted as labels of fuzzy sets, and secondary numerical weights. Cell activation is computed through MIN-MAX fuzzy equations of the weights. Learning consists in finding the (numerical) weights and the network topology. This feedforward network is described and illustrated in the same biomedical domain as in the first part.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J.L. Beaumont, L.A. Carlson, G.R. Cooper, Z. Fejfar, D.S. Fredrikson and T. Strasser, “Classification of Hyperlipidemias and Hyperlipoproteinemias,”Bull. W.H.O.43 (1970), pp. 891–915.
D.S. Fredrickson, R.I. Levy and R.S. Lee, “Fat transport in lipoproteins,”N. Engl. J. Med.276 (1967), pp. 32–44, 94–103, 148–156, 215–226, 273–281.
R.M. French“Guide to Diagnostic Procedures,”Mc Graw-HillNew-York (1975).
E. Sanchez and R. Bartolin“Fuzzy Inference and Medical Diagnosis, a Case Study,”Proc. of the First Annual Meeting of the Biomedical Fuzzy Systems AssociationKurashiki, Japan (1989), inJ. of the Biom. Fuzzy Syst. Ass. Vol.l N.1(1990), pp. 4–21.
L.A. Zadeh, “Fuzzy Sets as a Basis for a Theory of Possibility,”Fuzzy Sets and Systems1 (1978), pp. 3–28.
E. Sanchez, “Soft Queries in Knowledge Systems,” Proc. of the Second IFSA World CongressTokyo (1987), pp. 597–599.
E. Sanchez, “Importance in Knowledge Systems,” Information SystemsVol. 14, N°6 (1989), pp. 455–464.
E.Sanchez,“Handling Requests in Intelligent Retrieval,”inContributions on Approximate Reasoning and Artificial IntelligenceM. Delgado and J.L.Verdegay, eds.(to appear)
C. Dujet, “Valuation et Séparation dans les Ensembles Flous,”Structures de l’Information 18 - Publications du CNRS(1980), pp. 95–105.
M. Cayrol, H. Farreny and H. Prade, “Fuzzy Pattern Matching,”Kybernetes 11(1982), pp. 103–116.
E. Sanchez, “On Truth-qualification in Natural Languages,”Proc. Int. Conf. on Cybernetics and SocietyTokyo (1978), pp. 1233–1236.
E. Sanchez, “Mesures de Possibilité, qualifications de Vérité et Classification de Formes Linguistiques en Médecine,”inActes Table Ronde C.NR.S.Lyon (1980).
R. Bartolin, “Aide au Diagnostic Médical par Mesures de Comparaisons Floues et Pouvoir Séparateur. Approche Linguistique des Profils Protéiques Inflammatoires Biologiques,”Thèse d’Etat en Bilogie HumaineMarseille (1987).
L.A. Zadeh, “Interpolative Reasoning Based on Fuzzy Logic and its Application to Control and Systems Analysis,” invited lecture, abstract in theProc. of the Int. Conf. on Fuzzy Logic & Neural NetworksIizuka, Japan (1990).
E. Sanchez, “Connectionism, Artificial Intelligence and Fuzzy Control,” invited lecture, abstract in theProc. of the Second Annual Meeting of the Biomedical Fuzzy Systems AssociationKawasaki Medical School, Kurashiki, Japan (1990).
A.G. Barto, R.S. Sutton and C.W. Anderson, “Neuronlike Adaptive Elements that Can Solve Difficult Learning Control Problems,” IEEE Trans. S.M.C.vol. 13, N°5 (1983) pp.834–846.
C.C. Lee(1989), “A Self-learning Rule-based Controller Employing Approximate Reasoning and Neural Net Concepts,”Memo U.C. BerkeleyN°UCB/ERL, M89/84 (1989), to appear in theInt. J. of Intelligent Systems.
C.C. Lee, “Intelligent Control Based on Fuzzy Logic and Neural Network Theory,” Proc. of the Int. Conf. on Fuzzy Logic & Neural NetworksIizuka, Japan (1990) pp.759–764.
S.I. Gallant S.I. (1988), “Connectionist Expert Systems,”Com. of the ACMvol. 31, N°2 (1988) pp.152–169.
M. Frydenberg and S.I. Gallant S.I. (1987), “Fuzziness and Expert System Generation,” Lect. Notes in Computer Science(B. Bouchon and R.R. Yager, Eds), Springer-Verlag, vol. 286 (1987) pp.137–143.
B. Kosko, “Fuzzy Associative Memories,” inFuzzy Expert Systems(A. Kandel, Ed.), Addison-Wesley, Reading, Mass. (1986).
M. Togai, “Fuzzy Neural Net Processor and its Programming Environment,”Preprints of the 1988 first joint technology workshop on neural networks and fuzzy logicNASA, Johnson Space Center, Houston, TX (1988).
H. Takagi and I. Hayashi, “Artificial_Neural_Network-Driven Fuzzy Reasoning,” Proc. of the Int. workshop on fuzzy systems applicationsKyushu Institute of Technology, Iizuka, Japan (1988) pp.217–218.
R.R. Yager, “On the Interface of Fuzzy Sets and Neural Networks,” Proc. of the Int. workshop on fuzzy systems applicationsKyushu Institute of Technology, Iizuka, Japan (1988) pp. 215–216.
D.L. Hudson, M.E. Cohen and M.F. Anderson, “Determination of Testing Efficacy in Carcinoma of the Lung Using a Neural Network Model,”in Computer applications in medical care(LA. Greens, Ed.), vol. 12 (1988) pp.251–255.
S.S. Chen, “Knowledge Acquisition on Neural Networks,”Lect. Notes in Computer Sciences(B. Bouchon, L. Saitta and R.R. Yager, Eds.), Springer-Verlag, vol. 313 (1988) pp.281–289.
T. Yamakawa and S. Tomoda,“A Fuzzy Neuron and its Application to Pattern Recognition,” Proc. of the Third IFSA Congress SeattleWA (1989) pp.30–38.
K. Yoshida, Y. Hayashi and A. Imura A. (1989), “A Connectionist Expert System for Diagnosing Hepatobiliary Disorders,” Proc. of MEDINFO89, Beijing and Singapore (1989) pp. 116–120.
J. Yen, “Using Fuzzy Logic to Integrate Neural Networks and Knowledge-based Systems,” Proc. of the Neural networks and fuzzy logic workshopNASA, Johnson Space Center, Houston, TX (1990).
E. Sanchez, “Fuzzy Connectionist Expert Systems,”Proc. of the Int. Conf. on Fuzzy Logic & Neural Networkslizuka, Japan (1990) pp.31–35.
E. Sanchez, “Resolution of Composite Fuzzy Relation Equations,” Information and Controlvol. 30, N°1 (1976) pp.38–48.
A. Di Nola, W. Pedrycz, E. Sanchez and S. Sessa, “Fuzzy Relation Equations and their Applications to Knowledge Engineering,”Kluwer Acad. Pub.Dordrecht (1989).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media New York
About this chapter
Cite this chapter
Sanchez, E. (1992). Fuzzy Logic Knowledge Systems and Artificial Neural Networks in Medicine and Biology. In: Yager, R.R., Zadeh, L.A. (eds) An Introduction to Fuzzy Logic Applications in Intelligent Systems. The Springer International Series in Engineering and Computer Science, vol 165. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3640-6_11
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3640-6_11
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6619-5
Online ISBN: 978-1-4615-3640-6
eBook Packages: Springer Book Archive