Subscribe to RSS
DOI: 10.1055/s-0038-1635320
INTERNIST-1/CADUCEUS: Problems Facing Expert Consultant Programs[*]
INTERNIST-1/CADUCEUS: Probleme bei sog. ExpertensystemenAuthors
Publication History
Publication Date:
17 February 2018 (online)
Summary
INTERNIST-1 is an experimental computer program for consultation in general internal medicine. On a series of test cases, its performance has been shown to be similar to that of staff physicians at a university hospital. Despite INTERNIST-1âs apparent success in dealing with complex cases involving multiple diagnoses in the same patient, many shortcomings in both its knowledge representation schemes and its diagnostic algorithms still remain. Among the known problems are lack of anatomical and temporal reasoning, inadequate representation of degrees of severity of findings and illnesses, and failure to reason properly about causality. These drawbacks must be corrected before INTERNIST-1âs successor program, CADUCEUS, can be used. It is estimated that CADUCEUS will not be ready for release to the general medical community for five to ten years.
Broader problems faced by all medical diagnostic consultant systems are: design of an efficient human interface; development and completion of medical knowledge bases; expansion of diagnostic algorithms from simple heuristic rules to include a range of complex reasoning strategies, and development of a method for validating computer programs for clinical use.
INTERNIST-1 ist ein experimentelles Computerprogramm fĂŒr die Konsultation in der allgemeinen internistischen Medizin. In einer Reihe von TestlĂ€ufen hat sich gezeigt, daĂ seine Leistung derjenigen von KrankenhausĂ€rzten in UniversitĂ€tskliniken Ă€hnlich ist. Trotz des offensichtlichen Erfolges von INTERNIST-1 bei der Behandlung schwieriger FĂ€lle, bei denen es sich um Mehrfachdiagnosen beim gleichen Patienten handelte, weist das System doch noch viele MĂ€ngel, sowohl bei der PrĂ€sentation des Wissens als auch bei den diagnostischen Algorithmen, auf. Unter den bekannten Problemen sind Mangel an anatomischer und zeitlicher BeweisfĂŒhrung, inadĂ€quate Darstellung der Schweregrade der Befunde und Krankheiten und das Fehlen geeigneter SchluĂfolgerungen bezĂŒglich der KausalitĂ€t festzustellen. Diese Nachteile mĂŒssen korrigiert werden, ehe das INTERNIST-1-Nachfolgeprogramm CADUCEUS in Gebrauch genommen werden kann. SchĂ€tzungsweise wird CADUCEUS erst in fĂŒnf bis zehn Jahren zum allgemeinen medizinischen Gebrauch zur VerfĂŒgung stehen.
Weitere Probleme, denen sich alle medizinischen diagnostischen Expertensysteme gegenĂŒbergestellt sehen, sind: Entwurf einer effizienten menschlichen Schnittstelle, Entwicklung und VervollstĂ€ndigung medizinischer Wissensbanken, Erweiterung diagnostischer Algorithmen von einfachen heuristischen Regeln zum EinschluĂ einer Reihe komplexer Argumentationsstrategien und Entwicklung einer Methode zur Bewertung klinischer Computerprogramme.
Key-Words:
Computer-aided Diagnosis - Diagnostic Algorithms - Expert Systems - Internal Medicine - Medical DiagnosisSchlĂŒssel-Wörter:
ComputerunterstĂŒtzte Diagnose - diagnostische Algorithmen - Expertensysteme - Innere Medizin - medizinische Diagnose* The INTERNIST/CADUCEUS project has been funded through grants from the Division of Research Resources (R24 RR 01101) and the National Library of Medicine (R01 LM 03710 and R23 LM 03589) of the National Institutes of Health. This paper was presented in part at the IBM Scientific Center, Heidelberg, Fed. Rep. of Germany, on September 29,1983.
-
References
- 1 Beckley R. F., Bleich H. L.. Paper-Chase: A computer-based reprint storage and retrieval system. Comput. biomed. Res 1977; 10: 423-430.
- 2 Dombal F. T.de, Leaper D. J., Stani-land J. R., McCann A. P., Horrocks J. C. Computer-aided diagnosis of abdominal pain. Brit. med. J 1972; II 9-13.
- 3 Horowitz G. L., Bleich H. L.. Paper-Chase: A computer program to search the medical literature. New Engl. J. Med 1981; 305: 924-930.
- 4 Kraft R.-P. Report on the international MEDLARS workshop. 1981; Meth. Inform. Med 1982; 21: 91-93.
- 5 McShane D. J., Harlow A., Kraines R. G., Fries J. F.. TOD: A software system for the ARAMIS data bank. Computer 12, No 1979; 11: 34-40.
- 6 Miller R. A., Pople H. E., Myers J. D.. INTERNIST-1, an experimental computer-based diagnostic consultant for general internal medicine. New Engl. J. Med 1982; 307: 468-476.
- 7 Myers J. D., Pople H. E., Miller R. A.. INTERNIST: Can artificial intelligence help? In Connelly, D.P. et al. (Eds) Clinical Decisions and Laboratory Use, pp.. 251-269. Minneapolis: University of Minnesota Press; 1982
- 8 Pople H. E., Myers J. D., Miller R. A.. DIALOG: A model of diagnostic logic for internal medicine. In Proceedings of the Fourth International Joint Conference on Artificial Intelligence, pp. 848-855. Cambridge, Mass.: MIT Artificial Intelligence Laboratory Publ.; 1975
- 9 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, pp. 119-190. Boulder, Colo.: Westview Press; 1982
- 10 Rosati R. A., McNeer J. F., Starmer C. F., Mittler B. S., Morris J. J., Wallace A. G.. A new information system for medical practice. Arch. intern. Med 1975; 135: 1017-1024.
- 11 Rosati R. A., Lee K. L., Califf R. M., Pryor D. B., Harrell Jr. F. E.. Problems and advantages of an observational database approach to evaluating the effect of therapy on outcome. Circulation 65, Suppl. II 1982; 27-32.
- 12 Scully R. E., Mark E. J., McNeely B. U.. (Eds) Case Records of the Massachusetts General Hospital: Case 2-1982. New Engl. J. Med 1982; 306: 91-97.
- 13 Tagliacozzo R.. MEDLARS: Its utilization in research, education and practice. Meth. Inform. Med 1973; 12: 170-177.
- 14 Warner H. R.. A mathematical approach to medical diagnosis. J. Amer. med. Ass 1961; 177: 177-183.
- 15 Weyl S., Fries J., Wiederhold G., Germano F.. A modular self-describing clinical databank system. Comput. biomed. Res 1975; 8: 279-293.