Explanatory Power for Medical Expert Systems: Studies in the Representation of Causal Relationships for Clinical Consultations^[*]

This paper reports on experiments designed to identify and implement mechanisms for enhancing the explanation capabilities of reasoning programs for medical consultation. The goals of an explanation system are discussed, as is the additional knowledge needed to meet these goals in a medical domain. We have focussed on the generation of explanations that are appropriate for different types of system users. This task requires a knowledge of what is complex and what is important; it is further strengthened by a classification of the associations or causal mechanisms inherent in the inference rules. A causal representation can also be used to aid in refining a comprehensive knowledge base so that the reasoning and explanations are more adequate. We describe a prototype system which reasons from causal inference rules and generates explanations that are appropriate for the user.

Diese Arbeit berichtet über Experimente, die dazu dienten, Methoden zur Verbesserung der Aussagekraft von Grundlagenprogrammen für medizinische Beratungen zu erkennen und anzuwenden. Diese Programme benutzen eine Codierung der medizinischen Information in einem Spezialbereich, um mittels logischer Folgerungen die möglichen Ursachen eingetragener Symptome auszugeben. Die Ziele des Erklärungssystems werden im Zusammenhang mit dem zusätzlichen Wissen, das zur Lösung dieser Aufgabe im medizinischen Bereich benötigt wird, diskutiert. Wir haben uns darauf konzentriert, solche Erklärungen zu erzeugen, die für die unterschiedlichen Systembenutzer geeignet sind. Diese Aufgabe benötigt eine Kenntnis davon, was komplex und was wichtig ist in den Beratungen, und wird von einer Klassifizierung der ursächlichen Verbindungen, welche den Regeln für die Folgerungen unterliegen, unterstützt. Das Folgerungsnetz kann auch benutzt werden, um die Entwicklung eines Systems für die Erkennung von Zusammenhängen zu unterstützen, kann aber nicht genug Informationen enthalten, um neue Folgerungen aus dem bestehenden Wissen abzuleiten. Wir beschreiben den Prototyp eines solchen Systems, das aus dem Folgerungsnetz Schlüsse ableitet und dem Benutzer geeignete Erklärungen darbietet.

Key-Words

Medical Decision Making - Consultation Systems - Explanation - Artificial Intelligence - Expert Systems

Schlüssel-Wörter

Medizinische Entscheidungsfindung - Konsultationssystem - Erklärung - künstliche Intelligenz - Experten-System

^* This work was supported by Contract NR 049—479 from the Office of Naval Research and by a grant from the Henry J. Kaiser Family Foundation. Dr. Shortliffe is recipient of research career development award LM00048 from the National Library of Medicine. The computing was undertaken on the SUMEX-AIM machine, a shared national resource funded by the Biotechnology Resources Program of the NIH under grant RR-00785.

• References

• 1 Carbonell J. R. AI in CAI: An Artificial-Intelligence Approach to Computer-Assisted Instruction. IEEE Transactions on Man-Machine Systems. MMS 1970; 11: 190-202.
• 2 Clancey W. J. Tutoring Rules for Guiding. A Case Method Dialogue. Int. J. Man-Machine Studs 1979; 11: 25-49.
• 3 Clancey W. J. The Epistemology of a Rule-Based Expert System. To appear in Artificial Intelligence 1983
• 4 Davis K, King J. An Overview of Production Systems. In Elcock E. W, Michie D. (Eds): Machine Representation of Knowledge New York: Wiley; 1976
• 5 Davis R. Application of Meta-Level Knowledge to the Construction, Maintenance, and Use of Large Knowledge Bases. Doctoral Dissertation. Memo STAN-CS-76-552, HPP-76-7, Stanford University, July 1976
• 6 Duda R. O, Hart P. E, Barrett P, Gaschnig J, Konolige K, Reboh R, Slocum J. Development of the PROSPECTOR System for Mineral Exploration. Final Report, SRO Projects 5821 and 6415, SRI International, Menlo Park, Calif (October 1978).
• 7 Feigenbaum E. A. The Art of Artificial Intelligence: Themes and Case Studies of Knowledge Engineering. In AFIPS Conference Proceedings of the National Computer Conference Vol. 47 Montvale, N. J.: AFIPS Press; 1978: 227ff.
• 8 Goldstein I. Developing a Computational Representation of Problem Solving Skills. AI Memo 495, Artificial Intelligence Center, Massachusetts Institute of Technology, October 1978
• 9 Gorry G. A. Computer-Assisted Clinical Decision Making. Meth. Inform. Med 1973; 12: 45-51.
• 10 Leaper D. J, Horrocks J. C, Staniland J. R, deDom-bal F. T. Computer-Assisted Diagnosis of Abdominal Pain Using Estimates Provided by Clinicians. Brit. med. J 1972; IV: 350-354.
• 11 Linde C. The Organization of Discourse. In Shopen T, Williams J. M. (Eds): Style and Variables in English. Cambridge, MA.: Winthrop Press; 1978
• 12 Linde C, Goguen J. A. Structure of Planning Discourse. J. Soc. Biol. Struct 1978; 1: 219-251.
• 13 Patil R. S, Szolovits P, Schwartz W. B. Causal Understanding of Patient Illness in Medical Diagnosis. Proceedings of the 7th International Joint Conference on Artificial Intelligence. Vancouver, British Columbia: August 1981: 893-899.
• 14 Pauker S. G, Gorry G. A, Kassirer J. P, Schwartz W. B. Toward the Simulation of Clinical Cognition: Taking a Present Illness by Computer. Amer. J. Med 1976; 60: 981-995.
• 15 Pople H. Heuristic Methods for Imposing Structure on Ill-Structured Problems: The Structuring of Medical Diagnostics. In Szolovits P. (Eds): Artificial Intelligence in Medicine. AAAS Symposium Series, Westview Press forthcoming 1982
• 16 Rieger C. An Organization of Knowledge for Problem Solving and Language Comprehension. Artif. Intell 1976; 7: 89-127.
• 17 Scott A. C, Clancey W. J, Davis R, Shortliffe E. H. Explanation Capabilities of Production-Based Consulta- tion Systems. Amer. J. Comput. Linguist. Microfiche 62 1977
• 18 Shortliffe E. H, Buchanan B. G. A Model of Inexact Reasoning in Medicine. Math. Biosci 1975; 23: 351-379.
• 19 Shortliffe E. H, Buchanan B. G, Feigenbaum E. A. Knowledge Engineering for Medical Decision Making: A Review of Computer-Based Clinical Decision Aids. Proceed. IEEE 1979; 67: 1207-1224.
• 20 Shortliffe E. H, Davis R, Axline S. G, Buchanan B. G, Green C. C, Cohen S. N. Computer-Based Consultations in Clinical Therapeutics: Explanation and Rule Acquisition Capabilities of the MYCIN System. Comput. biomed. Res 1975; 8: 303-320.
• 21 Shortliffe E. H. Computer-Based Medical Consultations: MYCIN. New York: Elsevier/North-Holland; 1976
• 22 Shortliffe E. H. Consultation Systems for Physicians : The Role of Artificial Intelligence Techniques. In Proceedings of the Third National Conference of the Canadian Society for Computational Studies of Intelligence, Victoria, British Columbia, May 1980. Webber B, Nilsson N. (Eds): Readings in Artificial Intelligence Menlo Park, Ca.: Tioga Press; 1981
• 23 Swartout W. R. Explaining and Justifying in Expert Consulting Programs. Proceedings of the 7th International Joint Conference on Artificial Intelligence. Vancouver, British Columbia: August 1981
• 24 Szolovits P, Pauker S. G. Categorical and Probabilistic Reasoning in Medical Diagnosis. Artif. Intell 1978; 11: 115-144.
• 25 Weiner J. L. BLAH: A System which Explains its Reasoning. Artif. Intell 1980; 15: 19-48.
• 26 Weiner J. L. The Structure of Natural Explanation: Theory and Application. Systems Development Corp. SP-4305 1979
• 27 Weiss S. M, Kulikowski C. A, Amarel S, Safir A. A Model-Based Method for Computer-Aided Medical Decision-Making. Artif. Intell 1978; 11: 145-172.
• 28 Yu V. L, Fagan L. M, Wraith S. M, Clancey W. J, Scott A. C, Hannigan J, Blum R. L, Buchanan B. G, Cohen S. N. Antimicrobial Selection by a Computer: A Blinded Evaluation by Infectious Disease Experts. J. Amer. Med. Ass 1979; 242: 1279-1282.