Automatic annotation of medical reports using SNOMED-CT: a flexible approach based on medical knowledge databases

De Meyere, Damien;Klein, Thierry;François, Thomas;Debongnie, Jean-Claude;Fairon, Cédrick;et.al.
(2015) 7th Language & Technology Conference: Human Language Technologies as a Challenge for Computer Science and Linguistics — Location: Poznań, Poland (27.November.2015)

Files

LTC2015_de_meyere.pdf
  • Restricted Access
  • Adobe PDF
  • 180.41 KB
Request a copy

Details

Authors
Show more
Abstract
This paper presents a rule-based method for the detection and normalization of medical entities using SNOMED-CT which, although based on knowledge stored in terminological resources, allows some flexibility in order to account for the language variation typical of medical texts. Our system is based on the software Unitex and is one of the few to code French medical texts with SNOMED-CT concept identifiers. Our evaluation quantifies the benefits of such a flexible approach, but also emphasizes terminological resource shortcomings for the processing of medical reports written in French. Finally, our methodology is an interesting alternative to supervised training, as the extraction rules require limited development.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

De Meyere, D., Klein, T., François, T., Debongnie, J.-C., Radulescu, C., Mbengo, N., Ouro Koura, M., Coppieters ’t Wallant, Y., & Fairon, C. (2015). Automatic annotation of medical reports using SNOMED-CT: a flexible approach based on medical knowledge databases. In Zygmunt Vetulani & Joseph Mariani (ed.), Proceedings of the 7th Language & Technology Conference (p. p. 519-523). Fundacja Uniwersytetu im. A. Mickiewicza. https://hdl.handle.net/2078.5/221437