INTERNIST-I, An Experimental Computer-Based Diagnostic Consultant for General Internal Medicine

  • Randolph A. Miller
  • Harry E. PopleJr.
  • Jack D. Myers
Part of the Computers and Medicine book series (C+M)


INTERNIST-I is an experimental computer program capable of making multiple and complex diagnoses in internal medicine. It differs from most other programs for computer-assisted diagnosis in the generality of its approach and the size and diversity of its knowledge base. To document the strengths and weaknesses of the program we performed a systematic evaluation of the capabilities of INTERNIST-I. Its performance on a series of 19 clinicopathological exercises (Case Records of the Massachusetts General Hospital) published in the Journal appeared qualitatively similar to that of the hospital clinicians but inferior to that of the case discussants. The evaluation demonstrated that the present form of the program is not sufficiently reliable for clinical applications. Specific deficiencies that must be overcome include the program’s inability to reason anatomically or temporally, its inability to construct differential diagnoses spanning multiple problem areas, its occasional attribution of findings to improper causes, and its inability to explain its “thinking.” (N Engl J Med. 1982; 307:468–76.


Hepatic Encephalopathy Primary Biliary Cirrhosis General Internal Medicine Problem Area Ascitic Fluid 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Wardle A, Wardle L. Computer aided diagnosis—a review of research.Methods Inf Med. 1978; 17:15–28.PubMedGoogle Scholar
  2. [2]
    Wagner G, Tautu P, Wolber U. Problems of medical diagnosis—a bibliography.Methods Inf Med. 1978; 17:55–74.PubMedGoogle Scholar
  3. [3]
    Shortliffe EH, Buchanan BG, Feigenbaum EA. Knowledge engineering for medical decision making: a review of computer-based clinical decision aids.Proc IEEE. 1979; 67:1207–24.CrossRefGoogle Scholar
  4. [4]
    de Dombal FT, Leaper DJ, Staniland JR, McCann AP, Horrocks JC. Computer-aided diagnosis of abdominal pain.Br Med J. 1972; 2:9–13.PubMedCrossRefGoogle Scholar
  5. [5]
    Yu VL, Fagan LM, Wraith SM, et al. Antimicrobial selection by computer. JAMA. 1979; 242:1279–82.PubMedCrossRefGoogle Scholar
  6. [6]
    Pople HE, Myers JD, Miller RA. DIALOG: a model of diagnostic logic for internal medicine. In: Proceedings of the Fourth International Joint Conference on Artificial Intelligence. Cambridge, Mass.: MIT Artificial Intelligence Laboratory Publications, 1975:848–55.Google Scholar
  7. Myers JD, Pople HE, Miller RA. INTERNIST: can artificial intelligence help? In: Connelly, Benson, Burke, Fenderson, eds. Clinical decisions and laboratory use. Minneapolis: University of Minnesota Press, 1982:251–69.Google Scholar
  8. [8]
    Pople HE. Heuristic methods for imposing structure on ill-structured problems: the structuring of medical diagnostics. In: Szolovits P, ed. Artificial intelligence in medicine, AAAS Symposium Series, Boulder, Colo.: West- view Press, 1982:119–85.Google Scholar
  9. [9]
    Winston PH. Artificial intelligence. Reading, Mass.: Addison-Wesley, 1977.Google Scholar
  10. [10]
    Nilsson NJ. Principles of artificial intelligence. Palo Alto: Tioga Publishing Co., 1980.Google Scholar
  11. [11]
    Case Records of the Massachusetts General Hospital (Case 30-1969).N Engl J Med. 1969; 281:206–13.Google Scholar
  12. [12]
    Feinstein AR. Clinical biostatistics XXXIX: the haze of Bayes, the aerial palaces of decision analysis, and the computerized Ouija board.Clin Pharmacol Ther. 1977;21:482–96.PubMedGoogle Scholar

Copyright information

© Springer-Verlag New York Inc. 1985

Authors and Affiliations

  • Randolph A. Miller
  • Harry E. PopleJr.
  • Jack D. Myers

There are no affiliations available

Personalised recommendations