Natural Language Processing and Semantical Representation of Medical Texts

Abstract:

For medical records, the challenge for the present decade is Natural Language Processing (NLP) of texts, and the construction of an adequate Knowledge Representation. This article describes the components of an NLP system, which is currently being developed in the Geneva Hospital, and within the European Community’s AIM programme. They are: a Natural Language Analyser, a Conceptual Graphs Builder, a Data Base Storage component, a Query Processor, a Natural Language Generator and, in addition, a Translator, a Diagnosis Encoding System and a Literature Indexing System. Taking advantage of a closed domain of knowledge, defined around a medical specialty, a method called proximity processing has been developed. In this situation no parser of the initial text is needed, and the system is based on semantical information of near words in sentences. The benefits are: easy implementation, portability between languages, robustness towards badly-formed sentences, and a sound representation using conceptual graphs.

Key-Words

Natural Language - Knowledge Representation - Patient Database - Literature Indexing - Medical Nomenclature

• REFERENCES

• 1 Scherrer JR, Coté RA, Mandil SH. Computerised Natural Medical Language Processing for Knowledge Representation. Amsterdam: Elsevier Science Publ; 1989
• 2 Lindberg DAB, Humphreys BL. The UMLS knowledge sources: Tools for building better user interfaces. In: Miller RA. (ed). Proceedings of the 14th SCAMC. New York: IEEE Computer Society Press; 1990: 121-5.
• 3 Borst FR, Chevrolet JC, Unger PF, Scherrer JR. How to promote high level medical standards of care in a teaching hospital. In: Hansen R. et al. (eds). Proceedings of Medical Informatics Europe 1988. Springer Verlag; 1988: 133-6.
• 4 Safran C, Porter D, Lighfoot J. et al. ClinQuery: A system for online searching of data in a teaching hospital. Ann Int Med 1989; 110: 113-9.
• 5 Sager N, Friedman C, Lymann M. Medical Language Processing: Computer Management of Narrative Data. New York: Addi-son-Wesley Publ Comp; 1987
• 6 Sager N, Lyman M, Tick LJ. et al. Adapting a medical language processor from English to French. In: Barber B. et al. (eds). MEDINFO 89. Amsterdam: North-Holland; 1989: 795-9.
• 7 Morel-Guillemaz AM, Baud RH, Scherrer JR. Proximity processing of medical texts. In: O’Moore R. et al. (eds). Proceedings of MIE 1990. Berlin: Springer Verlag; 1990: 625-30.
• 8 Karlsson F. Constraint grammar as a framework for parsing running text. COLLING. 90: 168-73.
• 9 Miller RA, Masarie Jr FE. Quick Medical Reference (QMR): An evolving microcomputer-based diagnostic decision-support program for general internal medicine. In: Proceedings of the 13th SCAMC. New York: IEEE Comp Soc Press; 1989: 947-8.
• 10 Hripcsak G, Clayton PD, Pryor TA, Haug P, Wigertz PB, Van der Lei J. The Arden Syntax for medical logic modules. In: Miller RA. (ed). Proceedings of the 14th SCAMC. Washington DC: IEEE Comp Soc Press; 1990: 200-4.
• 11 Baud RH. Medical informatics and declarative programming. In: Blum BI, Timmers T. (eds). Software Engineering in Medical Informatics. . Amsterdam: Elsevier Science Publ; 1991: 209-16.
• 12 Sowa JF. Conceptual Structures: Information Processing in Mind and Machine. New York: Addison-Wesley Publ Comp; 1984
• 13 Fargues J. Graphes conceptuels et comprehension du langage naturel. Semantica. 1989
• 14 Baud RH, Rassinoux AM, Scherrer JR. Knowledge representation of discharge summaries. In: Proceedings of AIME 91. Berllin: Springer Verlag; 1991: 173-82.
• 15 Stefanneli M. the GAMES-team. GAMES: A general architecture for medical expert systems. In: Proceedings of the AIM EUROFORUM. Sevilla; 1990: 199-206.
• 16 Nogier JF. Generation Automatique de Langage et Graphes Conceptuels. Paris: Hermes Editor; 1991
• 17 Scherrer JR. Medical languages: Use, definition and processing in Ward Information Systems (WIS). In: Adlassnig KP. et al. (eds) Proceedings of MIE 91. Berlin: Springer Verlag; 1991: 19-27.