PMID- 15684131
OWN - NLM
STAT- MEDLINE
DCOM- 20050614
LR  - 20191210
IS  - 1067-5027 (Print)
IS  - 1527-974X (Electronic)
IS  - 1067-5027 (Linking)
VI  - 12
IP  - 3
DP  - 2005 May-Jun
TI  - Improved identification of noun phrases in clinical radiology reports using a 
      high-performance statistical natural language parser augmented with the UMLS 
      specialist lexicon.
PG  - 275-85
AB  - OBJECTIVE: The aim of this study was to develop and evaluate a method of 
      extracting noun phrases with full phrase structures from a set of clinical 
      radiology reports using natural language processing (NLP) and to investigate the 
      effects of using the UMLS(R) Specialist Lexicon to improve noun phrase 
      identification within clinical radiology documents. DESIGN: The noun phrase 
      identification (NPI) module is composed of a sentence boundary detector, a 
      statistical natural language parser trained on a nonmedical domain, and a noun 
      phrase (NP) tagger. The NPI module processed a set of 100 XML-represented 
      clinical radiology reports in Health Level 7 (HL7)(R) Clinical Document 
      Architecture (CDA)-compatible format. Computed output was compared with manual 
      markups made by four physicians and one author for maximal (longest) NP and those 
      made by one author for base (simple) NP, respectively. An extended lexicon of 
      biomedical terms was created from the UMLS Specialist Lexicon and used to improve 
      NPI performance. RESULTS: The test set was 50 randomly selected reports. The 
      sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall 
      maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS 
      Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and 
      recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% 
      and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%. 
      CONCLUSION: The sentence boundary detector performs excellently. After the 
      adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI 
      performance on radiology reports increased to levels comparable to the parser's 
      native performance in its newswire training domain and to that reported by other 
      researchers in the general nonmedical domain.
FAU - Huang, Yang
AU  - Huang Y
AD  - Stanford Medical Informatics, MSOB X215, 251 Campus Drive, Stanford, CA 
      94305-5479, USA. huangy@stanford.edu
FAU - Lowe, Henry J
AU  - Lowe HJ
FAU - Klein, Dan
AU  - Klein D
FAU - Cucina, Russell J
AU  - Cucina RJ
LA  - eng
PT  - Journal Article
DEP - 20050131
PL  - England
TA  - J Am Med Inform Assoc
JT  - Journal of the American Medical Informatics Association : JAMIA
JID - 9430800
SB  - IM
MH  - Abstracting and Indexing/*methods
MH  - Artificial Intelligence
MH  - Forms and Records Control
MH  - Humans
MH  - Medical Records Systems, Computerized/*classification/standards
MH  - *Natural Language Processing
MH  - Programming Languages
MH  - *Radiology Information Systems
MH  - *Unified Medical Language System
PMC - PMC1090458
EDAT- 2005/02/03 09:00
MHDA- 2005/06/15 09:00
PMCR- 2006/05/03
CRDT- 2005/02/03 09:00
PHST- 2005/02/03 09:00 [pubmed]
PHST- 2005/06/15 09:00 [medline]
PHST- 2005/02/03 09:00 [entrez]
PHST- 2006/05/03 00:00 [pmc-release]
AID - M1695 [pii]
AID - 206 [pii]
AID - 10.1197/jamia.M1695 [doi]
PST - ppublish
SO  - J Am Med Inform Assoc. 2005 May-Jun;12(3):275-85. doi: 10.1197/jamia.M1695. Epub 
      2005 Jan 31.