MEDICAL LANGUAGE PROCESSING - APPLICATIONS TO PATIENT DATA REPRESENTATION AND AUTOMATIC ENCODING

A linguistic approach is presented to develop a representation of pati ent data. Semantic categories developed for computer processing of nar rative clinical reports are shown to be similar to the Medical Concept s used manually to extract data from narrative in Exercises of the Com puter-based Patient Record Institute. Clinical statement types compose d of these categories are used in the Linguistic String Project (LSP) medical language processing (MLP) system to convert narrative informat ion into relational database tables of patient information. A procedur e for mapping the output of the LSP MLP system into SNOMED Internation al codes was developed. Preliminary results and further requirements a re discussed.