Skip to main content
PMC home page
Proceedings of the AMIA Symposium logoLink to Proceedings of the AMIA Symposium
. 1998:46–52.

Modern architectures for intelligent systems: reusable ontologies and problem-solving methods.

M A Musen 1
PMCID: PMC2232188  PMID: 9929181

Abstract

When interest in intelligent systems for clinical medicine soared in the 1970s, workers in medical informatics became particularly attracted to rule-based systems. Although many successful rule-based applications were constructed, development and maintenance of large rule bases remained quite problematic. In the 1980s, an entire industry dedicated to the marketing of tools for creating rule-based systems rose and fell, as workers in medical informatics began to appreciate deeply why knowledge acquisition and maintenance for such systems are difficult problems. During this time period, investigators began to explore alternative programming abstractions that could be used to develop intelligent systems. The notions of "generic tasks" and of reusable problem-solving methods became extremely influential. By the 1990s, academic centers were experimenting with architectures for intelligent systems based on two classes of reusable components: (1) domain-independent problem-solving methods-standard algorithms for automating stereotypical tasks--and (2) domain ontologies that captured the essential concepts (and relationships among those concepts) in particular application areas. This paper will highlight how intelligent systems for diverse tasks can be efficiently automated using these kinds of building blocks. The creation of domain ontologies and problem-solving methods is the fundamental end product of basic research in medical informatics. Consequently, these concepts need more attention by our scientific community.

Full text

PDF
46

Selected References

These references are in PubMed. This may not be the complete list of references from this article.

  1. Hripcsak G., Ludemann P., Pryor T. A., Wigertz O. B., Clayton P. D. Rationale for the Arden Syntax. Comput Biomed Res. 1994 Aug;27(4):291–324. doi: 10.1006/cbmr.1994.1023. [DOI] [PubMed] [Google Scholar]
  2. McCray A. T., Nelson S. J. The representation of meaning in the UMLS. Methods Inf Med. 1995 Mar;34(1-2):193–201. [PubMed] [Google Scholar]
  3. Musen M. A. Dimensions of knowledge sharing and reuse. Comput Biomed Res. 1992 Oct;25(5):435–467. doi: 10.1016/0010-4809(92)90003-s. [DOI] [PubMed] [Google Scholar]
  4. Musen M. A., Gennari J. H., Eriksson H., Tu S. W., Puerta A. R. PROTEGE-II: computer support for development of intelligent systems from libraries of components. Medinfo. 1995;8(Pt 1):766–770. [PubMed] [Google Scholar]
  5. Musen M. A., Schreiber A. T. Architectures for intelligent systems based on reusable components. Artif Intell Med. 1995 Jun;7(3):189–199. doi: 10.1016/0933-3657(95)00003-o. [DOI] [PubMed] [Google Scholar]
  6. Musen M. A., Tu S. W., Das A. K., Shahar Y. EON: a component-based approach to automation of protocol-directed therapy. J Am Med Inform Assoc. 1996 Nov-Dec;3(6):367–388. doi: 10.1136/jamia.1996.97084511. [DOI] [PMC free article] [PubMed] [Google Scholar]
  7. Rector A. L., Bechhofer S., Goble C. A., Horrocks I., Nowlan W. A., Solomon W. D. The GRAIL concept modelling language for medical terminology. Artif Intell Med. 1997 Feb;9(2):139–171. doi: 10.1016/s0933-3657(96)00369-7. [DOI] [PubMed] [Google Scholar]
  8. van Bemmel J. H. Medical informatics, art or science? Methods Inf Med. 1996 Sep;35(3):157–201. [PubMed] [Google Scholar]

Articles from Proceedings of the AMIA Symposium are provided here courtesy of American Medical Informatics Association

RESOURCES