The automatic conversion of free text into a medical ontology can allow computational access to important information currently locked within clinical notes and patient reports. This system introduces a new method for automatically identifying medical concepts from the SNOMED Clinical Terminology in free text in near real time. The system presented consists of 3 modules; an Augmented Lexicon, term compositor and negation detector. The Augmented Lexicon indexes the SNOMED-CT terms, the term compositor finds qualification relationships between concepts and the negation detector identifies negative concepts. The system delivers the services through a variety of interfaces including direct programming access and web-based access. It is currently in use in a hospital environment to capture patient data response with SNOMED-CT codes in real time at the point of care. No strict evaluation has been done on the system to date, however preliminary results indicate performance within acceptable time and accuracy limits.
|Cite as: Patrick, J., Wang, Y. and Budd, P. (2007). An Automated System for Conversion of Clinical Notes into SNOMED Clinical Terminology. In Proc. Australasian Workshop on Health Knowledge Management and Discovery (HKMD 2007), Ballarat, Australia. CRPIT, 68. Roddick, J. F. and Warren, J. R., Eds. ACS. 219-226. |
(local if available)