AI & Society

, Volume 9, Issue 2–3, pp 138–160 | Cite as

Cognition and decision in biomedical artificial intelligence: From symbolic representation to emergence

  • Vincent RialleEmail author


This paper presents work in progress on artificial intelligence in medicine (AIM) within the larger context of cognitive science. It introduces and develops the notion ofemergence both as an inevitable evolution of artificial intelligence towards machine learning programs and as the result of a synergistic co-operation between the physician and the computer. From this perspective, the emergence of knowledge takes placein fine in the expert's mind and is enhanced both by computerised strategies of induction and deduction, and by software abilities to dialogue, co-operate and function as a cognitive extension of the physician's intellectual capabilities. The proposed methodology gives the expert a prominent role which consists, first, of faithfully enunciating the descriptive features of his medical knowledge, thus giving the computer a precise description of his own perception of basic medicine, and secondly, of painstakingly gathering patients into computerised case bases which simulate exhaustive long-term memory. The AI capacities for knowledge elaboration are then triggered, giving rise to mathematically optimal diagnoses, prognoses, or treatment protocols which the physician may then evaluate, accept, reject, or adapt at his convenience, and finally append to a knowledge base. The idea of emergence embraces many issues concerning the purpose and intent of artificial intelligence in medical practice. Particularly, we address the representation problem as it is raised by classical decisional knowledge-based systems, and develop the notions of classifiers and hybrid systems as possible answers to this problem. Finally, since the whole methodology touches the problem of technological investment in health care, now inherent in modern medical practice, some ethical considerations accompany the exposé.


Artificial intelligence Medical-informatics Medical information systems Medical decision making Machine-learning Cognitive science Expert systems 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Amy, B. (1989). Contextual cognitive machines. In Tiberghien, G (ed.)Advancees in cognitive sciences. Vol 2: Theory and applications. Ellis Horwood. New York.Google Scholar
  2. Amy, B. Giacometti, A., and Gut, A. (1990). Modèles connexionnistes de l'expertise. InProceed. NEURO NIMES '90. EC2. Nanterre, France. 99–119.Google Scholar
  3. Andler, D. (ed.), (1992)Introduction aux sciences cognitives. Gallimard. Paris.Google Scholar
  4. Barnett, G.O., Cimino, J.J., Hupp, J.A. and Hoffer, E.P. (1987). Dxplain: An evolving diagnostic decision support system. J Am.Med. Assoc.,3. 258.Google Scholar
  5. Barsalou, L.W. and Hale, C.R., (1993) Component of conceptual representations: from feautres lists to recursive frames. In Van Mechelen, I. et al. (ed.)Categories and Concepts. Academic Press, New York.Google Scholar
  6. Berner, E.S. Webster, G.D. Shugerman, A.A. Jackson, J.R. Algina, J., and Baker, A.L. (1994). Performance of four computer-based diagnostic systems.New England Journal of Medicine,330 (25). 1792–1796.CrossRefGoogle Scholar
  7. Beuscart, R., and Fieschi, M. (1992). Cognition et systèms experts medicaux.Le courrier du CNRS,79. 101.Google Scholar
  8. Brooks, R.A. (1991). Intelligence without representation.Artificial intelligences,47. 139–159.CrossRefGoogle Scholar
  9. CCE (1992). EPIRIT:Specific Search and technological development in the field of information technology-Results and Progress 1991–1992. Commission of the European Communities. Luxembourg.Google Scholar
  10. Changeux, J.-P., and Dahaene, S. (1989). Neuronal Models of Cognitive Functions.Cognition,33. 63–109.CrossRefGoogle Scholar
  11. Clancey, W.J. (1985). Heuristic Classification.Artificial Intelligence,27. 289–350.CrossRefGoogle Scholar
  12. Demongeot, J., Goles, E., and Tchuente, M. (ed.), (1985),Dynamical Systems and Cellular Automata. Academic Press, New York.zbMATHGoogle Scholar
  13. Demongeot, J., Hérve, T., Rialle, V. and Roche, C. (ed), (1988).Artificial Intelligence and Cognitive Sciences. Manchester University Press. New York.zbMATHGoogle Scholar
  14. Demongeot, J., Le Beuax, P., and Weil, G. (ed.), (1994).Informatisation de l'Unité de Soins du Futur. Springer-Verlag, Paris.Google Scholar
  15. Dennett, D.C. (1991).Consciousness explained. Little-Brown-and-Co. Boston.Google Scholar
  16. Feldman, J.A. (1989). Connectionist Representation of Concepts. In Pfeifer, R. et al. (ed.)Connectionism in perspective. North-Holland Publ. Amsterdam, The Netherlands. 24–45.Google Scholar
  17. Forrest, D. (ed.), (1991)Emergent Computation. MIT Press, Cambridge, Massachusetts.Google Scholar
  18. François, P. Robert, C., Cremilleux, B., Bucharles, C., and Demongoat, J. (1990). Variables processing in expert system building: Application to the aetiological diagnosis of infantile meningitis.Medical Informatics,15(2). 115–124.CrossRefGoogle Scholar
  19. Gallant, S.I. (1988) Connectionist expert systems.Communications of the ACM,2(31). 152–169.CrossRefGoogle Scholar
  20. Giacommeti, A., Iordanova, I., Amy, B., Vila, A., Reymond, F., Abaoub, L., Dahou, M., and Rialle, V. (1992). A Hybrid Approach to Computer Aided Diagnosis in Electromyography.14th Int Conf IEEE Engin Med Biol Soc,14. 1012–1013.Google Scholar
  21. Grémy, F. (1988). Persons and Computers in Medicine and Health.Methods of Information in Medicine,27. 3–9.Google Scholar
  22. Grémy, F. (1989). Human meaning of medical informatics: reflections on its future and trends.Medical Informatics,14(1). 1–11.CrossRefGoogle Scholar
  23. Hendler, J.A. (1989). On the need of hybrid systems.Connection Science (special issue on Hybrid Connectionist/Symbolic Systems),1(3).Google Scholar
  24. Henery, R.J. King, R., Sutherland., Mitchell, J.M.O., and Brazdil, P. (1991). Statlog: Comparative Testing of Statistical and machine Learning Algorithms. InESPIRIT-Information Processing and Software: Results and Progress of Selected Projects. DG XIII. C.E.E. Bruxelles. 398–411.Google Scholar
  25. Holland, J.H. (1986). Escaping brittleness: The Possibilities of General Purpose Learning Algorithmes Applied to Parallel Rule-Based Systems. In Michalski, R., Carbonel, J., and Mitchel, T. (ed.)Machine Learning. 2. Morgan-Kaufmann. Sen Mateo, CA. 594–623.Google Scholar
  26. Hopfield, J.J. (1982). Neural Networks and physical Systems with Emergent Collective Computational Abilities.Proceedings of the National Academy of Science,79. 2554–2558.MathSciNetCrossRefGoogle Scholar
  27. Iordanova, I., Rialle, V., and Vila, A. (1992). Use of Unsupervised Neural Networks for Classification Tasks in Electromyographgy. Proc.14th Int Conf IEEE Engin Med Biol Soc,14. 1014–1015.CrossRefGoogle Scholar
  28. Kulikovski, C.A. and Weiss, S.M. (1982). Representation of expert knowledge for consultation: The Casnet and Expert projects. In Szolovits, P. (ed.)Artificial Intelligence in Medicine. Westview Press. Colarado.Google Scholar
  29. Memmi, D. (1989). Connectionism and Artificial Intelligence. In Proceed.Neuro-Nimes '89. EC2. Nanterre, France. 17–34.Google Scholar
  30. Meunier, J.G. (1992). Le Probléme de la catégorisation dans la representation de connaissances.Intellectica, (13–14). 353–356.Google Scholar
  31. Meunier, J.G. (1993). Semiotic Primitives and conceptual representation of knowledge. In Jorna, R.J., Van Heusdenm, B., and Posner, R. (ed.)Sign, Search and Communication. Walter de Gruter. Berlin.Google Scholar
  32. Miller, R.A., Masarie, F.E., Myers, J.D. (1986). Quick Medical Reference (QMR for diagnostic assistance.MD Computing,3 35–48.Google Scholar
  33. MLT-Consortium (1993).MLT Project: Final Public Report. Commission of the European Community. Brussels.Google Scholar
  34. Orsier, B., Iordanova, I., Rialle, V., Giacometti, A., and Vila, A. (1994). Hybrid systems for expertise modelling: from concepts to a medical application in electromyography.Computers and Artificial Intelligence,13(5). 423–440.Google Scholar
  35. Patel, V.L. and Evans, D.A. (ed.), (1989).Cognitive Science in Medicine: Biomedical Modelling. MIT Press. Cambridge, Massachusets.Google Scholar
  36. Patel, V.L. and Groen, G.J. (1987). Knowledge based solution strategies in medical reasoning,.Cognitive Science,10(1). 91–126.CrossRefGoogle Scholar
  37. Perry, C. (1990). Knowledge bases in Medicine: a review.Bull. Med. Libr. Assoc.,78(3). 271–282.Google Scholar
  38. Pham, K.M., and Degoulet, P. (1991). MOSAIC: Medical Knowledge Processing Based on a Macro-Connectionist Approach to Neural Networks. InMEDINFO: Proc 6th Congress on Medical Informatics. Vol I. 82–86.Google Scholar
  39. Pinkas, G. (1992). Requested Unrestricted First-Order Logic Formulas in Connectionist Networks. In Sun, R., and Bookman, L. A. (ed.) Proc. of the AAAI-92Workshop «Integrating Neural and Symbolic Processes-The Cognitive Dimension”. San Jose, California, 23–30.Google Scholar
  40. Pollack, J.B. (1990) Recursive Distributed Representations.Artificial Intelligence 46. 77–105.CrossRefGoogle Scholar
  41. Posner, M. (ed), (1989).Foundation of Cognitive Science. MIT Press, Cambridge, MA.Google Scholar
  42. Rialle, V. (1988). Data Analysis as an aid to Learning and Knowledge Base Making in a medical field. In Deomongoat, J. et al. (ed.)Artificial Intelligence and Cognitive Sciences. Manchester University Press. New York. 375–386.Google Scholar
  43. Rialle, V. (1989). Pour une intégration des systèmes à bases de connaissance en practique clinique courante. InActes de Journées Francophones d'Informatique Médicale de Montpellier. Editions de l'Ecole Nationale de la Santé Publique, Rennes. 279–285.Google Scholar
  44. Rialle, V. (1994).Décision et Cognition en Biomédicine: Modèles et Intégration. Mémoire de Diplôme d'Habilitation à Diriger des Recherces-informatique. Université Joseph Fourier, Grenoble.Google Scholar
  45. Rialle, V. (1995). Vers la maîtrise informatique de la connaissance. In Joly, H. (ed.)Biomédicine 2000. Lavoiser, Paris. 52–75.Google Scholar
  46. Rialle, V., Ohayon, M., Amy, B., Bessière, P. (1991a) Medical Knowledge Modeling in a Symbolic-Connectionist Perspective. In Nagel, J.H., and Smith, W.M. (ed.) 3th An. Int. Conf. IEEE Engin. in Med. and Biol. Society. 13(3) IEEE. Piscataway, NJ. 1109–1110.Google Scholar
  47. Rialle, V., Pagnosis, D., Vermont, J., Augerat, P., and Giarardet, P. (1991b). Are expert systems able to assist intensive care?: Specific issues in the modeling of intensive care practice. In Pavé A., and Vansteenkiste, G.C. (ed.)Artificial intelligence in numerical and symbolic simulation Aléas, Lyon. 101–113.Google Scholar
  48. Rialle, V., and Payette, D. (ed.), (1994).Modèles de la cognition: vers une science de l'espirit LEKTON, 4(2). Départment de Philosophie. Université du Québec à Montréal.Google Scholar
  49. Rialle, V., and Stip, E. (1994). Modelisation cognitive en psychiatrie: des modèles symboliques aux modèles parallèles et distribués.Journal of Psychiatry and Neuroscience,19(3). 178–192.Google Scholar
  50. Rialle, V., Stip, E., and O'Connor, K. (1994). Computer Mediated Psychotherapy: Ethical issues and difficulties in Implementation.Humane Medicine,10(3). 185–192.Google Scholar
  51. Rialle, V., Vila, A., and Besnard, Y. (1991). Heterogeneous knowledge representation using a finite automaton and first order logic: A case study in Electromyography.Artificial Intelligence in Medicine,3(2). 65–74.CrossRefGoogle Scholar
  52. Riesbeck, C.K., and Schank, R.C. (1989).Inside Case-Based Reasoning. Lawrence Erlbaum. Hillsdale, New Jersey.Google Scholar
  53. Rosch, E. (1978). Principles of categorization. In Rosch, E., and Lloyd, B.B. (ed.)Cognition and Categorization. Lawrence Erlbaum. Hillsdale, New jersey.Google Scholar
  54. Rumelhart, D.E. McClelland, J.L., and PDP-Research-Group (ed.), (1986).Parallel Distributed Processing: Exploration in the Microstructure of Cognition. Vol 1: Foundations. MIT Press/Bradford Books. Cambridge, Massachusetts.Google Scholar
  55. Shortliffe, E.H. (1976).Computer-Based Medical Consultation: MYCIN. American-Elsevier. New York.Google Scholar
  56. Smolensky, P. (1986). Information Processing in Dynamical Systems: Foundation of Harmony Theory. In Rummelhart, D.E., McClelland, J.L., and PDP Reasearch-Group (ed.)Parallel Distributed Processing: Exploration in the Microstructure of Cognition. MIT Press. Cambridge, Massachusetts.Google Scholar
  57. Summer, W. (1994). A review of Iliad and Quick Medical Reference for primary care providers. Two diagnostic computer programs.Arch. Fam. Med. 2(1). 87–95.CrossRefGoogle Scholar
  58. Sun, R., and Bookman, L.A. (ed.), (1992). Proc. of the AAAI-92 Workshop “Integrating Neural and Symbolic Processes-The Cognitive Dimension”. San Jose, California.Google Scholar
  59. Thornton, C.J. (1992).Techniques in Computational Learning: An Introduction. Chapman & Hall. London.Google Scholar
  60. Tiberghien, G. (ed.), (1989).Advances in cognitive science. Vol. 2. Theory and applications. Ellis Horwood. Chichester.Google Scholar
  61. Touretzky, D.S. (1989). BolzCONS:Dynamic Symbol Structures in a Connectionist Network. Tech. Rep. No. CMU-CS-89-172, Carnegie Mellon University.Google Scholar
  62. Varela, F., Thompson, E., and Rosch, E. (1991).The Embodied Mind: Cognitive Science and Human Experience. MIT Press, Cambridge, M.A.Google Scholar
  63. Varela, F.J. and Bourgine, P. (ed.), (1992)Toward a Practice of Autonomous Systems. Proc. 1st Europ Conf Artificial Life. MIT Press. Cambridge, Massachusetts.Google Scholar
  64. Weiss, S.M., and Kulikowski, C.A. (1991).Computer Systems that Learn: Classficiation and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems, Morgan Kaufmann. San Mateo, California.Google Scholar
  65. Weizenbaum, J. (1976).Computer power and human reason-From judgement to calculation. Freeman. San Francisco, CA.Google Scholar

Copyright information

© Springer-Verlag London Limited 1995

Authors and Affiliations

  1. 1.Laboratoire TIMC-IMAG Faculté de Médecine de GrenobleCHU de Grenoble & Universite Joseph FourierGrenobleFrance

Personalised recommendations