AI technologies: Conditions for further impact

  • Jean-Raoul Scherrer
Keynote Lectures
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1211)

Abstract

This paper deals with the impact of some AI technologies expected in the medical domain in the next few years. Many promises have been made already in the past from different research groups, but few have come to fruition. The innate difficulties associated with the explored field, or an underestimation of necessary resources, are the most common causes for delay (up to 200% or more). We will concentrate in this paper on three topics which will lead to clinical applications before the end of the century: Imaging technologies enhanced by expert systems which are already in use today in a few hospitals; Natural Language Processing which is now producing some early results; Knowledge browsers on the Internet that necessitate intelligent processes. For these three situations, this paper presents state-of-the-art prototypes and results which have given a «proof of concept». Moreover, it evaluates the potential for use in clinics, as well as for taking a position on the software market.

The author and his team would like to emphasise a clear message to researchers: that the main progress of AI techniques in the future will come from field experiments; that only in such a context will theories, principles and algorithms provide their best contributions to the advance of AI technologies. The suggestion: « Come down from the mountains and create pragmatic applications » is certainly a call to be more efficient.

Keywords

Natural Language Processing Medical Domain Intelligent Process Software Market Main Progress 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Ligier Y, Ratib O, Logean M, Girard C. OSIRIS: A Medical Image Manipulation System. M.D. Computing Journal, July–August 94, Vol. 11. No. 4, pp 212–218. URL: http://expasy.hcuge.ch/UIN/Google Scholar
  2. [2]
    Appel RD, Bairoch A, Hochstrasser DF. A New Generation of Information Retrieval Tools for Biologists: The Example of the EXPASY WWW Server. Trends in Biomedical Sciences. TiBS June 1994 (222), Vol.19, No.6, pp. 258–260. URL: http://expasy.hcuge.ch/Google Scholar
  3. [3]
    Baud RH, Rassinoux AM, Wagner JC, Lovis C, Juge C, Alpay LL, Michel PA, Degoulet P, Scherrer JR. Representing Clinical Narratives Using Conceptual Graphs. Meth. Inform. Med. 1995; 34: pp.176–86.Google Scholar
  4. [4]
    Lovis C, Gaspoz JM, Baud RH, Michel PA, Scherrer JR. Natural Language Processing and Clinical Support to Improve the Quality of Reimbursement Claim Databases. Proceedings SCAMC 1996, Special Issue of JAMIA, 1996.Google Scholar
  5. [5]
    Boyer C, Baujard V, Aurel S, Selby M, Appel RD. HON: Automated Database of Health and Medical Information. MEDNET 96: European Congress on the Internet in Medicine, Brighton, UK, Oct. 14–17, 1996. URL: http://www.hon.ch/Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jean-Raoul Scherrer
    • 1
  1. 1.Switzerland Division of Medical InformaticsGeneva State University HospitalSwitzerland

Personalised recommendations