Download PDF
Methods Inf Med 1985; 24(02): 65-72
DOI: 10.1055/s-0038-1636675
Original Article
Schattauer GmbH

Knowledge Acquisition for Expert Systems: Experience in Leukaemia Diagnosis

Erfassung von Wissen für Expertensysteme -Erfahrungen bei der Leukämiediagnose
J. Fox
1   (From the Imperial Cancer Research Fund Laboratories, London)
,
C. D. Myers
1   (From the Imperial Cancer Research Fund Laboratories, London)
,
M. F. Greaves
1   (From the Imperial Cancer Research Fund Laboratories, London)
,
Susan Pegram
1   (From the Imperial Cancer Research Fund Laboratories, London)
› Author Affiliations
Further Information

Publication History

Publication Date:
20 February 2018 (online)

    Permissions and Reprints

Summary

EMYCIN was used to develop an expert system for the interpretation of immunological data obtained in the cell surface phenotyping of leukaemia. Access to a recognised expert, and a large quantity of data on the leukaemias, has facilitated a systematic study of knowledge acquisition and knowledge base refinement based on tape recorded commentaries made by the expert. System performance was analysed at six stages in its development, and ways in which it differed from that of the human diagnostician were identified. Among the most suggestive observations were differences in the way that “undiagnosable” patients were treated and a failure of the elicitation technique to reveal structural aspects of the task. The tools and techniques of knowledge engineering are a significant advance, but a better methodology for developing high quality knowledge bases is needed.

EMYCIN wurde benutzt, um ein Expertensystem für die Auswertung in der Zelloberflächen-typisierung bei Leukämie gewonnener immunologischer Daten zu entwickeln. Die Verfügbarkeit eines anerkannten Experten auf diesem Gebiet und einer großen Menge von Daten über Leukämien haben eine systematische Untersuchung über Wissenserfassung und Weiterentwicklung von Wissensbanken auf der Grundlage von bandgespeicherten Kommentaren des Experten erleichtert. Leistungsdaten für das System wurden auf sechs Stufen seiner Entwicklung bestimmt, und es wurde untersucht, wo die Leistung des Systems sich von derjenigen des menschlichen Diagnostikers unterschied. Unter den eindrucksvollsten Beobachtungen waren Unterschiede in der Behandlung »nicht diagnostizierbarer« Patienten und die Unfähigkeit der Analysetechnik, strukturelle Aspekte der Aufgabe aufzudecken. Die Werkzeuge der technischen Wissenserfassung stellen einen wesentlichen Fortschritt dar; aber eine bessere Methodik zur Entwicklung von Wissensbanken von hoher Qualität ist erforderlich.

Key-Words:

Diagnosis - Leukaemia - Expert Systems - Knowledge Engineering - Knowledge Acquisition

Schlüssel-Wörter:

Diagnose - Leukämie - Expertensysteme - Wissensverarbeitung - Wissenserfassung
 

  • REFERENCES

  • 1 Blum R. L. Discovery, Confirmation, and Incorporation of Causal Relationships from a Large Time-oriented Clinical Data Base: The RX Project. Comput. biomed. Res 15 1982; 164-187.
    CrossrefPubMedGoogle Scholar
  • 2 Buchanan B. G, Shortliffe E. H. Rule-based Expert Systems. Reading, Mass: Addison-Wesley; 1984
    Google Scholar
  • 3 Cohen P. R, Grinberg M. R. A Theory of Heuristic Reasoning about Uncertainty. Artif. Intel. Mag 4 1983; 17-24.
    PubMedGoogle Scholar
  • 4 Davis R. Interactive Transfer of Expertise. Artif. Intel 12 1979; 121-157.
    CrossrefPubMedGoogle Scholar
  • 5 Fox J. Doubts about Induction. Bulletin of SPL Insight (Forthcoming). Oxford, UK: SPL Inter-national, Abingdon; 1984
    Google Scholar
  • 6 Fox J. Inferences about Beliefs and Values. In Kowalski R. (Edit.) Proceedings of Alvey Workshop on Inference. London: Imperial College, Dep. of Industry, Forthcoming;
    Google Scholar
  • 7 Hayes-Roth F, Waterman D. A, Lenat D. B. Building Expert Systems. Reading, Mass: Addison-Wesley; 1983
    Google Scholar
  • 8 Michalski R. S, Chilausky R. L. Learning by Being Told and Learning from Examples: An Experimental Comparison of the two Methods of Knowledge Acquisition in the Context of Developing an Expert System for Soybean Disease Diagnosis. Policy Analysis Inform. Syst. 4 (1980) No. 2 (Special Issue on Knowledge Acquisition and Induction). 1980
    Google Scholar
  • 9 Mulsant B, Servan-Schreiber D. Knowledge Engineering: A Daily Activity on a Hospital Ward. Comput. biomed. Res 1984; 17: 71-91.
    CrossrefPubMedGoogle Scholar
  • 10 Shortliffe E. H. Computer-based medical consultations: MYCIN. New York: Elsevier; 1976
    Google Scholar
  • 11 Sowa J. F. Conceptual Structures: Information Proceedings in Mind and Machine. Reading, Mass: Addison-Wesley; 1984
    Google Scholar
  • 12 Suwa M, Scott A. C, Shortliffe E. H. An Approach to Verifying Completeness and Consistency in a Rule-based Expert System. Artif. Intel. Mag 3 1982; 16-21.
    PubMedGoogle Scholar
  • 13 Van Melle W. A Domain Independent System that Aids in Constructing Knowledge-based Consultation Programs. PhD Dissertation. (Stanford Rep. No. STAN-CS-80-820). Stanford, Calif: Stanford University, Computer Science Dep; 1980
    Google Scholar
  • 14 Welbank M. A Review of Knowledge Acquisition Techniques for Expert Systems. Martlesham Consultancy Services. British Telecom Research Labs, Mar-lesham Heath: Ipswich; 1983
    Google Scholar