TY - JOUR
T1 - A term extraction tool for expanding content in the domain of functioning, disability, and health
T2 - Proof of concept
AU - Harris, Marcelline R.
AU - Savova, Guergana K.
AU - Johnson, Thomas M.
AU - Chute, Christopher G.
N1 - Funding Information:
This research for this paper was supported in part by Grant LM07453 from the National Library of Medicine (Harris PI). Our thanks to Lori Rhudy, a true clinical expert who spent many hours tagging text. Special thanks to Jim Buntrock, Sergey Pakhomov, Harold Solbrig, and members of the Division of Medical Informatics Research who provide valuable critique at Thursday seminars.
PY - 2003
Y1 - 2003
N2 - Among the challenges in developing terminology systems is providing complete content coverage of specialized subject fields. This paper reports on a term extraction tool designed for the development and expansion of terminology systems concerned with functioning, disability, and health. Content relevant to this domain is the emphasis of the foci and targets of many nursing terminologies. We extend previously published term extraction algorithms by applying two filters. The first filter is based on the raw frequency of the content words in the lexical string under consideration. The second filter applies the notion of a complete syntactic node to discover relevant noun or verb phrases. While we report on a limited corpus (30,607 words comprising 4103 terms from 60 dismissal note summaries), the recall, precision, and F-measures we observed are encouraging and suggest continued development and testing of the tool is merited.
AB - Among the challenges in developing terminology systems is providing complete content coverage of specialized subject fields. This paper reports on a term extraction tool designed for the development and expansion of terminology systems concerned with functioning, disability, and health. Content relevant to this domain is the emphasis of the foci and targets of many nursing terminologies. We extend previously published term extraction algorithms by applying two filters. The first filter is based on the raw frequency of the content words in the lexical string under consideration. The second filter applies the notion of a complete syntactic node to discover relevant noun or verb phrases. While we report on a limited corpus (30,607 words comprising 4103 terms from 60 dismissal note summaries), the recall, precision, and F-measures we observed are encouraging and suggest continued development and testing of the tool is merited.
KW - Functional status
KW - Functioning, disability, and health
KW - Nursing terminologies, ICF
KW - Term extraction
KW - Terminology tools
UR - http://www.scopus.com/inward/record.url?scp=0345172376&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0345172376&partnerID=8YFLogxK
U2 - 10.1016/j.jbi.2003.09.005
DO - 10.1016/j.jbi.2003.09.005
M3 - Article
C2 - 14643720
AN - SCOPUS:0345172376
SN - 1532-0464
VL - 36
SP - 250
EP - 259
JO - Journal of Biomedical Informatics
JF - Journal of Biomedical Informatics
IS - 4-5
ER -