KI-94 pp 53-68 | Cite as

Interpreting Clinical Questions — Medical Text Analysis Supports Image Presentation

  • Martin Schröder
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Abstract

Medicine is a domain where natural language documents play an important role. They contain a lot of useful information that is not directly accessable by formal procedures. Only with the help of a semantically oriented natural language analysis the contents of the documents can be made explicit in a structured way. In this paper we describe the linguistic and knowledge-based processing of german clinical questions by the text analysis system METEXA. The results are used to support the selection of images in the Cooperative Clinical Workstation, a reporting workstation for radiology. Depending on categories of clinical questions, the workstation can automatically present images that the radiologist needs for reporting. The METEXA system performs lexical, morphological, syntactic, and semantic processing. The semantics of an utterance is represented by a Conceptual Graph. In a further processing phase, the clinical questions are classified by a rule-based resolution procedure.

This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Bernauer, J., and Goldberg, H.: Compositional classification based on Conceptual Graphs. In: Andreassen, S. et al. (eds.): Artificial Intelligence in Medicine. IOS Press, 1993, pp. 348–359.Google Scholar
  2. Baud, R. H., Rassinoux, A.-M., and Scherrer, J.-R.: Natural Language Processing and Semantical Representation of Medical Texts. Methods of Information in Medicine 31, pp. 117–125, 1992.Google Scholar
  3. Borst, F., Lyman, M., Nhan, N.T., Tick, L.J., Sager, N., and. Scherrer, J.-R.: TEXTINFO: A tool for automatic determination of patient clinical profiles using text analysis. In: Clayton, P.D. (ed.): Assessing the Value of Medical Informatics. Fifteenth Annual Symposium on Computer Applications in Medical Care. McGraw-Hill, New York, 1991, pp. 63–67.Google Scholar
  4. Cavazza, M., Dore, L., and Zweigenbaum, P.: Model-based natural language understanding in medicine. In: Lun, K.C. et al. (eds.): Proceedings of MEDINFO 92, Elsevier Science Publ. ( North Holland ), pp. 1356–1361.Google Scholar
  5. Campbell, K.E., and Musen, M.A.: Representation of clinical data using SNOMED III and Conceptual Graphs. In: The 16th Annual Symposium on Computer Application in Medical Care. Washington D.C., 1992.Google Scholar
  6. Ellis, G.: Managing large databases of complex medical knowledge using Conceptual Graphs. In: Hovenga, J.S., and Whymark, G.K. (eds.): Proceedings of the National Health Conference. Health Informatics Society of Australia. Brisbane, Queensland, Australia, ISBN 0-646-14746-3. August 1993.Google Scholar
  7. Ingenerf, J.: Benutzeranpaßbare semantische Sprachanalyse und Begriffsrepräsentation für die medizinische Dokumentation. Sankt Augustin: Infix, 1993 (DISKI 43), ISBN 3-929037-43-2.Google Scholar
  8. Matsumoto, Yuji; Tanaka, Hozumi; Hirakawa, Hideki; Miyoshi, Hideo; and Yasukawa, Hideki: BUP: A bottom-up parser embedded in Prolog. New Generation Computing, 1, pp. 145–158, 1983.MATHCrossRefGoogle Scholar
  9. Pazienza, M. T. and Velardi, P.: A structured representation of word-senses for semantic analysis. Proceedings of the European ACL 1987, pp. 249–257.Google Scholar
  10. Pietrzyk, P. M.: Literal meaning of sentences from medical free text. In: Reichert, A., et al. (eds.): Proceedings of MIE 93, Eleventh International Congress of the European Federation for Medical Informatics. Freund Publishing House Ltd., London, 1993, pp. 64–67.Google Scholar
  11. Sager, N., Friedman, C., and Lyman, M. S.: Medical Language Processing: Computer Management of Narrative Data. Addison-Wesley, Reading (MA ), 1987.Google Scholar
  12. Sager, N., Lyman, N., Nhan, N.T., Tick, L.J., Borst, F., and Scherrer, J.-R.: Clinical knowledge bases from natural language patient documents. In: Lun, K.C. et al. (eds.): Proceedings of MEDINFO 92, Elsevier Science Publ. ( North Holland ), pp. 1375–1381.Google Scholar
  13. Schröder, M.: Knowledge-based Processing of Medical Language: A Language Engineering Approach. In: Proceedings of the 16th German AI-Conference (GWAI-92Springer Lecture Notes on AI, Vol. 671, Springer-Verlag, 1992, pp. 221–234.Google Scholar
  14. Schröder, M.: Knowledge-based analysis of radiological reports using Conceptual Graphs. In: Pfeiffer, H.D., and Nagle, T.E. (eds.): Conceptual Structures: Theory and Implementation. Lecture Notes in Artificial Intelligence 754. Springer-Verlag, Berlin, 1993a (Proceedings of the 7th Annual Workshop on Conceptual Graphs, Las Cruces, New Mexico (USA), July 1992, pp. 213–222 ).Google Scholar
  15. Schröder, M.: Sprachverarbeitung in der Medizin — Anwendungen und Methoden. Künstliche Intelligenz KI 3/1993b (September), pp. 50–56.Google Scholar
  16. Schröder, M.: Erwartungsgestützte Analyse medizinischer Befundungstexte — Ein wissensbasiertes Modell zur Sprachverarbeitung, „infix“-Verlag, Sankt Augustin, DISKI 54, ISBN 3-929037-54-8, 1994. (Dissertation, Universität Hamburg, Fachbereich Informatik, 1993.)Google Scholar
  17. Sowa, J.F.: Conceptual Structures: Information Processing in Mind and Machine. Addison-Wesley, Reading (MA ), 1984.MATHGoogle Scholar
  18. Sowa, J.F.: Towards the expressive power of natural language. In: Sowa, J.F. (ed.): Principles of Semantic Networks: Explorations in the Representation of Knowledge. Morgan Kaufmann Publishers, San Mateo (CA), 1991, pp. 157–189.Google Scholar
  19. Wendler, Th., Mönnich, K.J., and Schmidt, J.: Digital Image Workstations. In: Osteaux, M. (ed.): Hospital Integrated Picture Archiving and Communication Systems — A Second Generation PACS Concept. Springer-Verlag, Berlin, 1992a, pp. 173 - 210.Google Scholar
  20. Wendler, Th., Grewer, R., Mönnich, K.J., Schmidt, J., and Svensson, H.: Cooperative Image Workstation Based oa Explicit Models of Diagnostic Information Requirements. Journal of Digital Imaging, Vol 5, No 4, November 1992b, pp. 230–241.CrossRefGoogle Scholar
  21. Zweigenbaum, P., and Consortium MENELAS: MENELAS: an access system for medical records using natural language. Computer Methods and Programs in Biomedicine, 1994 (to appear).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Martin Schröder
    • 1
  1. 1.Department Technical SystemsPhilips Research LaboratoriesGermany

Personalised recommendations