Graphical Access to Medical Expert Systems: III. Design of a Knowledge Acquisition Environment*)

Joan D. Walton; M. A. Musen; D. M. Combs; C. D. Lane; E. H. Shortliffe; L. M. Fagan

doi:10.1055/s-0038-1635497

Methods of Information in Medicine, Table of Contents

Methods Inf Med 1987; 26(03): 78-88
DOI: 10.1055/s-0038-1635497

Original Article

Schattauer GmbH

Graphical Access to Medical Expert Systems: III. Design of a Knowledge Acquisition Environment*)

Grafischer Zugriff zu medizinischen Expertensystemen: III. Entwurf einer Wissenserfassungs-Stelle

Authors

Joan D. Walton

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)
M. A. Musen

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)
D. M. Combs

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)
C. D. Lane

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)
E. H. Shortliffe

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)
L. M. Fagan

¹(From the Medical Computer Science Group, Knowledge Systems Laboratory, Departments of Medicine and Computer Science, Stanford University School of Medicine)

Abstract

Summary

Knowledge acquisition for expert systems typically is a tedious, iterative process involving long hours of consultation between the domain experts and the computer scientists who serve as knowledge engineers. For well-understood domains, however, it may be possible to facilitate the knowledge acquisition process by allowing domain experts to develop and edit a knowledge base directly. Administration of protocol-directed cancer chemotherapy is such a well-understood application area, and a knowledge acquisition system, called OPAL, has been developed for eliciting chemotherapy-protocol knowledge directly from expert oncologists. OPAL’s knowledge acquisition approach is based on the interactive graphics environment available on current generation workstations. The use of graphics improves the interface by reducing typing, avoiding natural language interpretations, and allowing flexibility in entry sequence. The knowledge in OPAL is displayed using an arrangement of hierarchically related, graphical forms. The position of a particular form in the hierarchy defines the context of the knowledge contained in the form. Intelligent editing programs such as OPAL can streamline the knowledge engineering process for highly structured domains requiring repetitive knowledge entry.

Wissenserfassung für Expertensysteme ist immer ein mühsamer, iterativer Prozeß, der stundenlange Konsultationen zwischen den Gebietsexperten und den Computerwissenschaft-lern, die als Wissensingenieure agieren, mit sich bringt. Auf bestimmten Gebieten kann es jedoch möglich sein, den Wissenserfassungsprozeß zu erleichtern, indem man Gebietsexperten gestattet, eine Wissensbank unmittelbar zu entwickeln und zu bearbeiten. Die Verwaltung einer protokollorientierten Krebschemotherapie ist ein solches fest umgrenztes Anwendungsgebiet, und ein Wissenserfassungssystem, OPAL genannt, wurde entwickelt, um Wissen über das Chemotherapieprotokoll unmittelbar von Experten aus der Onkologie zu erfahren. Die Methode der Wissenserfassung in OPAL basiert auf den interaktiven grafischen Möglichkeiten, die bei derzeitigen Arbeitsstationen gegeben sind. Der Gebrauch der Grafik verbessert das Interface, indem er Schreibarbeit reduziert, Interpretationen natürlicher Sprache vermeidet und Flexibilität in der Eingabesequenz ermöglichen. Das bekannte Wissen wird in OPAL unter Benutzung einer Anordnung hierarchisch verwandter grafischer Formen dargeboten. Die Stellung einer bestimmten Form in der Hierarchie definiert den Kontext des in der Form enthaltenen Wissens. Intelligente Ausgabeprogramme wie OPAL können den Prozeß der Wissensbearbeitung für hochstrukturierte Gebiete, die wiederholte Wissenseingabe erfordern, den Gegebenheiten anpassen.

Key-Words

Knowledge Acquisition - Knowledge Engineering - Expert Systems - Human-Computer Interaction - Visual Programming

Schlüssel-Wörter

Wissenserfahrung - Wissensbearbeitung - Expertensysteme - Mensch - Computer-Wechselbeziehung - visuelles Programmieren

Full Text

References

REFERENCES
1 Bennett J. S. ROGET: A knowledge-based system for acquiring the conceptual structure of a diagnostic expert system. J. Automated Reasoning 1985; 1: 49-74.
2 Boose J. H. A knowledge acquisition program for expert systems based on personal construct psychology. Int. J. Man-Machine Studies 1985; 23: 495-525.
3 Buchanan B. G, Barstow D, Bechtal R, Bennett J, Clancey W, Kulikowski C, Mitchell T, Waterman D. A. Constructing an expert system. In Hayes-Roth F, Waterman D. A, Lenat D. B. (Eds) Building Expert Systems. Reading, M.A: Addison-Wesley; 1983: 127-167.
4 Buchanan B. G, Shortliffe E. H. Rule-Based Expert Systems: The MYCIN Experiments of the Stanford Heuristic Programming Project. Reading, M.A: Addison-Wesley; 1984
5 Combs D. M, Musen M. A, Fagan L. M, Shortliffe E. H. Graphical specification of procedural and inferential knowledge. Proceed. AAMSI Congress 86, American Association for Medical Systems and Informatics, Anaheim, CA, May. 1986: 298-302.
6 Davis R. Interactive transfer of expertise: Acquisition of new inference rules. Artif. Intel 1979; 12: 121-157.
7 Foley J. D, Wallace V. L. The art of natural graphic man – machine conversation. Proceed. IEEE 1974; 62: 462-471.
8 Hannan J. J, Politakis P. ESSA: An approach to acquiring decision rules for diagnostic expert systems. Second Conf. Artif. Intell. Appl. Miami, F. L: IEEE Computer Society Press; 1985: 520-525.
9 Hickam D. H, Shortliffe E. H, Bi-schoff M. B, Scott A. C, Jacobs C. D. A study of the treatment advice of a computer-based cancer chemotherapy advisor. Ann. intern. Med 1985; 101: 928-936.
10 Hutchins E. L, Hollan J. D, Norman D. L. Direct manipulation interfaces. In Norman D. A, Draper S. W. (Eds) User Centered System Design. 87-124. Hillsdale, N. J: Lawrence Erlbaum Ass; 1986
11 Kelly G. A. The Psychology of Personal Constructs. New York: Norton; 1955
12 Lane C. D, Walton J. D, Shortliffe E. H. Graphical access to medical expert systems: IIDesign of an interface for physicians. Meth. Inform. Med 1986; 25: 143-150.
13 Maars N. J. I, Miller P. L. Knowledge acquisition and verification tools for medical expert systems. Med. Decision Making 1987; 7: 6-11.
14 Marcus S, McDermott J, Wang T. Knowledge Acquisition for Constructive Systems. Proceed. Ninth Int. Joint Conf. Artif. Intell 1985; 637-639.
15 Musen M. A, Combs D. M, Walton J. D, Shortliffe E. H, Fagan L. M. OPAL: Toward the computer-aided design of oncology advice systems. In Miller P. L. Ed. Topics in Medical Artificial Intelligence. New York: Springer; 1987
16 Musen M. A, Fagan L. M, Combs D. M, Shortliffe E. H. Facilitating knowledge entry for an oncology therapy advisor using a model of the application area. Proceed. MEDINFO 86, Fifth World Congress on Medical Informatics, Washington, DC, Oct. 1986: 46-50.
17 Musen M. A, Fagan L. M, Shortliffe E. H. Graphical specification of procedural knowledge for an expert system. In Hendler J. (Ed) Expert Systems: The User Interface. Norwood, N. J: Ablex Publ. Corp; 1987: 15-38.
18 Musen M. A, Langlotz C. P, Fagan L. M, Shortliffe E. H. Rationale for knowledge base redesign in a medical advice system. Proceed. AAMSI Congress 85, American Association for Medical Systems and Informatics, May. 1985: 197-201.
19 Musen M. A, Rohn J. A, Fagan L. M, Shortliffe E. H. Knowledge engineering for a clinical trial advice system: Uncovering errors in protocol specification. Proceed. AAMSI Congress 86, American Association for Medical Systems and Informatics, Anaheim, CA, May. 1986: 24-27.
20 Phillips B, Messick S. L, Freiling M. J, Alexander J. H. INKA: The INGLISH knowledge acquisition interface for electronic instrument troubleshooting systems. Second Conf. Artif. Intell. Appl. Miami, FL: IEEE Computer Society Press; 1985: 676-681.
21 Politakis P, Weiss S. M. Using empirical analysis to refine expert system knowledge bases. Artif. Intell 1984; 22: 23-48.
22 Schneiderman B. Direct manipulation: A step beyond programming languages. Computer 16 No 1983; 8: 57-69.
23 Shortliffe E. H, Scott A. C, Bischoff M. B, van Melle W, Jacobs C. D. ONCOCIN: An expert system for oncology protocol management. Proceed. Seventh Int. Joint Conf. Artif. Intell., Vancouver, BC. 1981: 876-881.
24 Tsuji S, Shortliffe E. H. Graphical access to medical expert systems: I. Design of a knowledge engineer’s interface. Meth. Inform. Med 1986; 25: 62-70.
25 Tuhrim S, Reggia J. A. Feasibility of physician-developed expert systems. Med. Decision Making 1986; 6: 23-26.
26 Weiss S. M, Kulikowski C. A. EXPERT: A system for developing consultation models. Proceed. Tokyo, Japan: Sixth Int. Joint Conf. Artif. Intell; 1979: 942-947.