Representing Clinical Narratives Using Conceptual Graphs

Abstract:

The analysis of medical narratives and the generation of natural language expressions are strongly dependent on the existence of an adequate representation language. Such a language has to be expressive enough in order to handle the complexity of human reasoning in the domain. Sowa’s Conceptual Graphs (CG) are an answer, and this paper presents a multilingual implementation, using French, English and German. Current developments demonstrate the feasibility of an approach to natural Language Understanding where semantic aspects are dominant, in contrast, to syntax driven methods. The basic idea is to aggregate blocks of words according to semantic compatibility rules, following a method called Proximity Processing. The CG representation is gradually built, starting from single words in a semantic lexicon, to finally give a complete representation of the sentence under the form of a single CG. The process is dependent on specific rules of the medical domain, and for this reason is largely controlled by the declarative knowledge of the medical Linguistic Knowlege Base.

Keywords:

Natural Language Processing - Knowledge Representation - Conceptual Graph - Medical Record

• References

• 1 Ritchie GD. The lexicon. In: Whitelock P. et al, eds. Linguistic Theory and Computer Applications. London: Academic Press; 1987: 225-56.
• 2 Rector AL, Nowlan WA, Kay S. Conceptual knowledge: the core of medical information systems. In: Lun KC, Degoulet P, Piemme TE, Rienhoff O. eds. MEDINFO 92. Amsterdam: Elsevier Science Publ; 1992: 1420-6.
• 3 Rector AL, Nowlan WA, Glowinski A. Goals for concept representation in the GALEN project. In: Safran C. eds. Seventeenth Annual Symposium on Computer Applications in Medical Care. Proceedings. New York: McGraw-Hill; 1993: 414-8.
• 4 GALEN: The GRAIL kernel, Version 1. GALEN Deliverable no 6. Spring 1993. The GALEN Consortium. Available from Rector AL University of Manchester; UK.:
• 5 McCray AT, Hole WT. The scope and structure of the first version of the UMLS semantic network. In: Miller RA. eds. Fourteenth Annual Symposium on Computer Applications in Medical Care. Los Alamitos CA: IEEE Computer Society Press; 1990: 126-30.
• 6 Humphreys BL, Lindberg DAB. The Unified Medical Language System PROJECT: A distributed experiment in improving access to biomedical information. In: Lun KC, Degoulet P, Piemme TE, Rienhoff O. eds. MEDINFO 92. Amsterdam: Elsevier Science Publ; 1992: 1496-500.
• 7 Baud RH, Lovis C, Alpay L. Modelling for natural language understanding. In: Safran C. ed. Seventeenth Annual Symposium on Computer Applications in Medical Care. New York: McGraw-Hill; 1993: 289-93.
• 8 Gazdar G, Mellish C. Natural Language Processing in PROLOG: an Introduction to Computational Linguistics. Addison-Wesley Publ Comp; 1989
• 9 Allen J. Natural Language Understanding. Benjamin/Cummings Publ Comp; 1987
• 10 Rassinoux A-M. Extraction et représentation de la connaissance tirée des textes medicaux. Ph D thesis University of Geneva, Faculté des Sciences; 1994
• 11 Baud RH, Rassinoux A-M, Scherrer J-R. Natural language processing and semantical representation of medical texts. Meth Inform Med 1992; 31: 117-25.
• 12 Sowa JF. Conceptual Structures: Information Processing in Mind and Machine. Reading MA: Addison-Wesley Publ Comp; 1984
• 13 Woods W A. What’s important about knowledge representation?. IEEE Computer 1983; 22-7.
• 14 Shastri L. Why semantic networks?. In: Sowa JF. ed. Principle of Semantic Networks: Explorations in the Representation of Knowledge. San Mateo, CA: Morgan Kaufmann Publ; 1991: 109-36.
• 15 Rassinoux A-M, Baud RH, Scherrer J-R. Proximity processing of medical texts. In: O’Moore R, Bengtsson S, Bryant JR, Bryden JS. eds. Medical Informatics Europe ’90. Berlin: Springer-Verlag; 1990: 625-30.
• 16 Rassinoux A-M, Baud RH, Scherrer J-R. Analysis of medical Texts using Proximity Processing and Conceptual Graph Representation. AISB Quarterly 82. University of sussex; Brighton, UK: Special issue of AI in Med 1992: 11-5.
• 17 Steiner O. A natural language processing system to analyse medical texts in German (Diplomarbeit). Universitat Heidelberg/Fachhochschule Heilbronn Studiengang Medizinische Informatik; 1994
• 18 Lenat DB, Guha RV, Pittman K, Pratt D, Shepherd M. Cyc: toward programming with common sense. Comm ACM 1990; 33: 30-49.
• 19 Lenat DB, Guha RV. Building Large Knowledge-Based Systems: Representation and Inference in the Cyc Project. Addison-Wesley Publ; 1989
• 20 Rassinoux A-M, Baud RH, Scherrer J-R. Conceptual graphs model extension for knowledge representation of medical texts. In: Lun KC, Degoulet P, Piemme TE, Rienhoff O. eds. MEDINFO 92. Amsterdam: Elsevier Science Publ; 1992: 1368-74.
• 21 Rector AL, Solomon WD, Nowlan W A, Rush TW. A terminology server for medical language and medical information systems. International Medical Informatics Association WG 6 working conference. Vevey, Switzerland; 1994
• 22 Wagner JC, Rassinoux A-M, Baud RH, Scherrer J-R. Generating noun phrases from a medical knowledge representation. MIE 94. Lisbon: 1994: 218-23.