MEDICAL DICTIONARIES FOR PATIENT ENCODING-SYSTEMS - A METHODOLOGY

Medical language is highly compositional and makes extensive use of co mmon roots, especially Latino-Greek roots. Besideswords devoted to com mon sense, medical language presents some typical characteristics,espe cially on morphological and semantic aspects of word formation. Morpho logical decomposition and identification precedes semantic analysis. I t is only when these two prerequisites are fulfilled that an attempt t o grasp the meaning of a whole expression is made possible. The main a im of the proposed approach is that of coping with 'the lack of covera ge of the medical lexical knowledge', in order to help physicians find the correct international classification for diseases (ICD) codes for a written diagnosis. The proposed methodology allows the development of a powerful dynamic dictionary dedicated to natural language process ing in the field of diagnoses and narrative procedures. It describes t he design of an analyser that can profit fromh a dictionary. The metho ds used have proved to be efficient for various classifications, s wel l as for multiple languages, as the system presently supports French, German, English and Dutch for ICD-9 and ICD-10 classifications. (C) 19 98 Elsevier Science B.V. All rights reserved.