TY - JOUR
T1 - Selective automated indexing of findings and diagnoses in radiology reports
AU - Hersh, William
AU - Mailhot, Mark
AU - Arnott-Smith, Catherine
AU - Lowe, Henry
N1 - Funding Information:
This project was supported by National Library of Medicine Contract N01-LM-4-3507.
PY - 2001
Y1 - 2001
N2 - The recent improvements in capabilities of desktop computers and communications networks give impetus for the development of clinical image repositories that can be used for patient care and medical education. A challenge in the use of these systems is the accurate indexing of images for retrieval performance acceptable to users. This paper describes a series of experiments aiming to adapt the SAPHIRE system, which matches text to concepts in the UMLS Metathesaurus, for the automated indexing of image reports. A series of enhancements to the baseline system resulted in a recall of 63% but a precision of only 30% in detecting concepts. At this level of performance, such a system might be problematic for users in a purely automated indexing environment. However, if the ability to retrieve images in repositories based on content in their reports is desired by clinical users, and no other current systems offer this functionality, then follow-up research questions include whether these imperfect results would be useful in a completely or partially automated indexing environment and/or whether other approaches can improve upon them.
AB - The recent improvements in capabilities of desktop computers and communications networks give impetus for the development of clinical image repositories that can be used for patient care and medical education. A challenge in the use of these systems is the accurate indexing of images for retrieval performance acceptable to users. This paper describes a series of experiments aiming to adapt the SAPHIRE system, which matches text to concepts in the UMLS Metathesaurus, for the automated indexing of image reports. A series of enhancements to the baseline system resulted in a recall of 63% but a precision of only 30% in detecting concepts. At this level of performance, such a system might be problematic for users in a purely automated indexing environment. However, if the ability to retrieve images in repositories based on content in their reports is desired by clinical users, and no other current systems offer this functionality, then follow-up research questions include whether these imperfect results would be useful in a completely or partially automated indexing environment and/or whether other approaches can improve upon them.
KW - Automated indexing
KW - Evaluation
KW - Metathesaurus
KW - Natural language processing
KW - SAPHIRE
KW - Unified medical language system (UMLS)
UR - http://www.scopus.com/inward/record.url?scp=0035564683&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0035564683&partnerID=8YFLogxK
U2 - 10.1006/jbin.2001.1025
DO - 10.1006/jbin.2001.1025
M3 - Article
C2 - 11977808
AN - SCOPUS:0035564683
SN - 1532-0464
VL - 34
SP - 262
EP - 273
JO - Journal of Biomedical Informatics
JF - Journal of Biomedical Informatics
IS - 4
ER -