PDF herunterladen
Methods Inf Med 1985; 24(02): 57-64
DOI: 10.1055/s-0038-1635358
Original Article
Schattauer GmbH

An Overview of Medical Expert Systems

Ein Überblick über medizinische Expertensysteme
P. H. de Vries
1   (From the University Hospital Groningen, Medical Decision Making Group)
,
P. F. de Vries Robbé
1   (From the University Hospital Groningen, Medical Decision Making Group)
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
20. Februar 2018 (online)

    Lizenzen und Reprints

Summary

Expert systems are an important extension of the research on medical decision making. Their relation to other research in this area is shortly discussed. Fourteen medical expert systems are examined from different perspectives. After a discussion of their goal, domain, and history, the classification of expert systems along the procedural-declarative continuum provides the basis for the analysis of their knowledge representations.

As a result of this analysis, types of knowledge are identified that serve as a frame of reference for the comparison of the systems. Subsequently, the central role of these knowledge types in one of the most important tasks of expert systems, explaining, is emphasized. After the knowledge representation, two other components of expert systems are discussed that heavily depend on it: the knowledge acquisition and the man-machine interface. As a conclusion, the status quo of the research on expert systems is outlined and some developments are extrapolated. These developments show a tendency toward the integration of different knowledge types in one system.

Expertensysteme sind eine wichtige neue Entwicklung in der Erforschung medizinischer Entscheidungsprozesse. Ihre Beziehung zu anderer Forschung auf diesem Gebiet wird kurz besprochen. Vierzehn medizinische Expertensysteme werden unter verschiedenen Gesichtspunkten betrachtet. Nach einer Diskussion über Ziel, Anwendungsbereiche und Geschichte wird eine Klassifikation von Expertensystemen nach einem prozessural-deklarativen Konti-nuum gegeben, das die Basis für die Analyse von Wissensrepräsentationen bildet. Als Resultat dieser Analyse werden Wissenstypen identifiziert, die als Bezugsrahmen für den Vergleich von Systemen dienen. Anschließend wird die zentrale Rolle bei einer der wichtigsten Aufgaben der Expertsysteme betont, nämlich: Erklären. Nach der Wissensrepräsentation werden zwei weitere Komponenten der Expertensysteme besprochen, die damit weitgehend zusammenhängen: die Wissensaneignung und die Mensch-Maschine-Interaktion. Als Schlußfolgerung wird die Lage der Forschung über Expertensysteme skizziert, und es werden einige Entwicklungen extrapoliert. Diese zeigen eine Tendenz in Richtung Integration verschiedener Wissenstypen im gleichen System.

Key-Words:

Computer-aided Diagnosis - Diagnostic Models - Expert Systems - Knowledge Representation - Explanations

Schlüssel-Wörter:

Computer-unterstützte Diagnose - diagnostische Modelle - Expertensysteme - Wissensrepräsentation - Erklärungen
 

  • REFERENCES

  • 1 Aikins J. S. Prototypcial Knowledge for Expert Systems. Artif. Intel 1983; 20: 163-210.
    CrossrefPubMedSuche in Google Scholar
  • 2 Blum R. L. Discovery, Confirmation and Incorporation of Causal Relationships from a Large Time-oriented Clinical Data Base: The RX Project. Comput. biomed. Res 1982; 15: 164-187.
    CrossrefPubMedSuche in Google Scholar
  • 3 Brachman R. J, Smith B. C. Special Issue on Knowledge Representation. SIGART Newsl. No 1980; 70: 1-138.
    PubMedSuche in Google Scholar
  • 4 Bylander T, Mittal S, Chandrasekaran B. CSRL: A Language for Expert Systems for Diagnosis. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI). 1983: 218-221.
    Suche in Google Scholar
  • 5 Chandrasekaran B, Mittal S. Conceptual Representation of Medical Knowledge for Diagnosis by Computer: MDX and Related Systems.
    PubMed
  • 6 Clancey W. J. The Epistemology of a Rule-based Expert System: A Framework for Explanation. Artif. Intel 1983; 20: 215-251.
    CrossrefPubMedSuche in Google Scholar
  • 7 Clancey W. J, Letsinger R. NEOMYCIN: Reconfigurating a Rule-based Expert System for Application to Teaching. Draft. Stanford, CA: Stanford University; 1983
    Suche in Google Scholar
  • 8 Clancey W. J, Shortliffe E. F. L. Medical Artificial Intelligence Programs. Draft. Stanford, CA: Stanford University; 1983
    Suche in Google Scholar
  • 9 Davis R. Meta-level Knowledge: Overview and Applications. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI). 1977: 920-927.
    Suche in Google Scholar
  • 10 Davis R. Diagnosis via Causal Reasoning: Paths of Interaction and the Locality Principle. Proceedings of the American Ass. for Artificial Intelligence. 1983
    Suche in Google Scholar
  • 11 Davis R, Buchanan B, Shortliffe E. Production Rules as a Representation for a Knowledge-based Consultation Program. Artif. Inteln S 1977; 15-45.
    PubMedSuche in Google Scholar
  • 12 Fieschi M, Joubert M, Fieschi D, Roux M. SPHINX – A System for Computer-aided Diagnosis. Meth. Inform. Med 1982; 21: 143-148.
    PubMedSuche in Google Scholar
  • 13 Forbus K. D. Qualitative Process Theory. A. I. Memo 664 A. Cambridge, MA: M. I. T; 1982
    Suche in Google Scholar
  • 14 Groth T. Pathophysiological Models as Information Processing Elements in Clinical Decision Making. In. Lindberg D. A. B, Kaihara S. (Eds) Medinfo 80. Amsterdam: North-Holland; 1980: 819-823.
    Suche in Google Scholar
  • 15 Kingsland L. C, Lindberg D. A. B, Sharp G. C. AI/RHEUM: A Consultant System for Rheumatology. J. med. Syst 1983; 7: 221-227.
    CrossrefPubMedSuche in Google Scholar
  • 16 Kuipers B. Commonsense Reasoning about Causality: Deriving Behaviour from Structure. TUWPICS-18. Medford, MA: Tufts University; 1982
    Suche in Google Scholar
  • 17 Kuipers B, Kassirer J. P. Causal Reasoning in Medicine: Analysis of a Protocol. TUWPICS-20. Medford, MA: Tufts University; 1983
    Suche in Google Scholar
  • 18 Kuipers B, Kassirer J. P. How to Discover a Knowledge Representation for Causal Reasoning by Studying an Expert Physician. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI) 1983; 49-56.
    PubMedSuche in Google Scholar
  • 19 Kulikowski C. A, Weiss S. M. Representation of Expert Knowledge for Consultation: The CASNET and EXPERT Projects. In. Szolovits P. (Edit.) Artificial Intelligence in Medicine. Boulder, CO: Westview Press; 1982: 21-55.
    Suche in Google Scholar
  • 20 Lindberg D. A. B, Sharp G. C, Kings-land L. C, Weiss S. M, Hayes S. P, Ueno H, Hazelwood S. E. Computer Based Rheumatology Consultant. In. Lind-berg D. A. B, Kaihara S. (Eds) Medin-fo 80. Amsterdam: North-Holland; 1980: 1311-1315.
    Suche in Google Scholar
  • 21 Melle W van. A Domain-independent Production-Rule System for Consultation Programs. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI) 1979; 923-925.
    PubMedSuche in Google Scholar
  • 22 Melle W, van Scott A. C, Bennet J. S, Peairs M. The EMYCIN Manual. STAN-CS. Stanford, CA: Stanford University; 1981: 81-885.
    Suche in Google Scholar
  • 23 Miller R. A, Pople H. E, Myers J. D. Internist-I: An Experimental Computer-based Diagnostic Consultant for General Internal Medicine. New Engl. J. Med 1982; 307: 468-476.
    CrossrefPubMedSuche in Google Scholar
  • 24 Newell A. The Knowledge Level. Artif. Intel 1982; 18: 87-127.
    CrossrefPubMedSuche in Google Scholar
  • 25 Patil R. S, Szolovits P, Schwartz W. B. Causal Understanding of Patient Illness in Medical Diagnosis. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI) 1981; 893-899.
    PubMedSuche in Google Scholar
  • 26 Patil R. S, Szolovits P, Schwartz W. B. Modeling Knowledge of the Patient in Acid-Base and Electrolyte Disorders. In. Szolovits P. (Edit.) Artificial Intelligence in Medicine. Boulder, CO: Westview Press; 1982: 191-226.
    Suche in Google Scholar
  • 27 Politakis P. G. Using Empirical Analysis to Refine Expert System Knowledge Bases. CBM-TR-139. New Brunswick: N. J Rutgers University; 1982
    Suche in Google Scholar
  • 28 Pople H. E. Heuristic Methods for Imposing Structure on Ill-structured Problems: The Structuring of Medical Diagnostics. In. Szolovits P. (Edit.) Artificial Intelligence in Medicine. Boulder, CO: Westview Press; 1982: 119-190.
    Suche in Google Scholar
  • 29 Shortliffe E. H, Buchanan B. G, Feigenbaum E. A. Knowledge Engineering for Medical Decision Making: A Review of Computer-based Clinical Decision Aids. Proc. IEEE 1979; 67: 1207-1224.
    CrossrefPubMedSuche in Google Scholar
  • 30 Shortliffe E. H, Scott A. C, Bischoff M. B, Campbell A. B, Melle W, van Jacobs C. D. ONCOCIN: An Expert System for Oncology Protocol Management. Proceedings of the Int. Joint Conference on Artificial Intelligence (IJCAI) 1981; 876-881.
    PubMedSuche in Google Scholar
  • 31 Swartout W. R. XPLAIN: A System for Creating and Explaining Expert Consulting Programs. Artif. Intel 1983; 21: 285-325.
    CrossrefPubMedSuche in Google Scholar
  • 32 Szolovits P. Artificial Intelligence and Clinical Problem Solving. MIT/LCS/TM-140. Cambridge, MA: M.I.T; 1979
    Suche in Google Scholar
  • 33 Szolovits P, Pauker S. G. Categorical and Probabilistic Reasoning in Medical Diagnosis. Artif. Intel 1978; 11: 115-144.
    CrossrefPubMedSuche in Google Scholar
  • 34 Vries Robbé P. E de. Medische besluit-vorming: Een aanzet tot formele genees-kunde. Diss. University of Groningen; 1978
    Suche in Google Scholar
  • 35 Weiss S. M, Kulikowski C. A, Amarel S, Safir A. A Model-based Method for Computer-aided Medical Decision-making. Artif. Intel 1978; 11: 145-172.
    CrossrefPubMedSuche in Google Scholar