This Article Full Text Full Text (PDF) All Versions of this Article: M1695v1 12/3/275    most recent Submit a response Alert me when this article is cited Alert me when eLetters are posted Alert me if a correction is posted Services Similar articles in this journal Similar articles in PubMed Alert me to new issues of the journal Download to citation manager Citing Articles Citing Articles via HighWire Citing Articles via Google Scholar Google Scholar Articles by Huang, Y. Articles by Cucina, R. J. Search for Related Content PubMed PubMed Citation Articles by Huang, Y. Articles by Cucina, R. J.

Improved Identification of Noun Phrases in Clinical Radiology Reports Using a High-Performance Statistical Natural Language Parser Augmented with the UMLS Specialist Lexicon

Affiliations of the authors: Stanford Medical Informatics and Stanford Center for Clinical Informatics, Stanford University School of Medicine, Stanford, CA (YH, HJL); Computer Science Division, University of California at Berkeley, Berkeley, CA (DK); Department of Medicine, University of California, San Francisco, San Francisco, CA (RJC).

Correspondence and reprints: Yang Huang, MS, Stanford Medical Informatics, MSOB X215, 251 Campus Drive, Stanford, CA 94305-5479; e-mail: <huangy{at}stanford.edu>.

Received for publication: 09/09/04; accepted for publication: 12/28/04.

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® 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)® 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.

This article has been cited by other articles:

				O. Uzuner, Y. Luo, and P. Szolovits Evaluating the State-of-the-Art in Automatic De-identification J. Am. Med. Inform. Assoc., September 1, 2007; 14(5): 550 - 563. [Abstract] [Full Text] [PDF]

				Y. Huang and H. J. Lowe A Novel Hybrid Approach to Automated Negation Detection in Clinical Radiology Reports J. Am. Med. Inform. Assoc., May 1, 2007; 14(3): 304 - 311. [Abstract] [Full Text] [PDF]

				R. H. Dolin, L. Alschuler, S. Boyer, C. Beebe, F. M. Behlen, P. V. Biron, and A. Shabo (Shvo) HL7 Clinical Document Architecture, Release 2 J. Am. Med. Inform. Assoc., January 1, 2006; 13(1): 30 - 39. [Abstract] [Full Text] [PDF]