Heuristic determination of relevant diagnostic procedures in a medical expert system for gynecology

Steven L. Small, Eberhard K. Muechler

Research output: Contribution to journalArticlepeer-review


Many professions including medicine have standard operating procedures for the performance of their tasks. In the construction of expert systems, knowledge engineers have exploited this fact in devising heuristic rules that mimic the standard practice among such personnel (i.e., experts). This article suggests that the expert system designer should not stop at the level of the standard operating procedure heuristic but should instead investigate the reasons that the standard procedures have become standard. Because the experts in a field often do not understand the reasons for the standard operating procedures of their profession, this effort not only rewards the system designer but the expert as well. Because medical training does not always emphasize the logical reasoning underlying certain standard operating procedures, the ability to perform this reasoning is especially important in medicine. Further, a medical expert system for consultation or education would make a valuable impact by incorporating such knowledge and inference rules. This article investigates the development of a computerized medical expert system that applies the principles of artificial intelligence by limiting the number of questions and tests to find the solution for an ill-defined complex problem. Finally, we describe a logic program that tests the basic ideas.

Original languageEnglish (US)
Pages (from-to)17-24
Number of pages8
JournalAmerican journal of obstetrics and gynecology
Issue number1
StatePublished - Jul 1989
Externally publishedYes


  • Artificial intelligence
  • diagnostic reasoning in gynecology
  • medical expert system

ASJC Scopus subject areas

  • Obstetrics and Gynecology


Dive into the research topics of 'Heuristic determination of relevant diagnostic procedures in a medical expert system for gynecology'. Together they form a unique fingerprint.

Cite this