This Article Full Text Full Text (PDF) 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 Cooper, G. F. Articles by Miller, R. A. Search for Related Content PubMed PubMed Citation Articles by Cooper, G. F. Articles by Miller, R. A.

An Experiment Comparing Lexical and Statistical Methods for Extracting MeSH Terms from Clinical Free Text

Affiliations of the authors: Center for Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA (GFC); Division of Biomedical Informatics, Vanderbilt University, Nashville, TN (RAM).

Correspondence and reprints: Gregory F. Cooper, MD, PhD, University of Pittsburgh, Center for Biomedical Informatics, Suite 8084 Forbes Tower, 200 Lothrop Street, Pittsburgh, PA 15213-2582. e-mail: <gfc{at}cbmi.upmc.edu>.

Abstract Objective: A primary goal of the University of Pittsburgh's 1990-94 UMLS-sponsored effort was to develop and evaluate PostDoc (a lexical indexing system) and Pindex (a statistical indexing system) comparatively, and then in combination as a hybrid system. Each system takes as input a portion of the free text from a narrative part of a patient's electronic medical record and returns a list of suggested MeSH terms to use in formulating a Medline search that includes concepts in the text. This paper describes the systems and reports an evaluation. The intent is for this evaluation to serve as a step toward the eventual realization of systems that assist healthcare personnel in using the electronic medical record to construct patient-specific searches of Medline.

Design: The authors tested the performances of PostDoc, Pindex, and a hybrid system, using text taken from randomly selected clinical records, which were stratified to include six radiology reports, six pathology reports, and six discharge summaries. They identified concepts in the clinical records that might conceivably be used in performing a patient-specific Medline search. Each system was given the free text of each record as an input. The extent to which a system-derived list of MeSH terms captured the relevant concepts in these documents was determined based on blinded assessments by the authors.

Results: PostDoc output a mean of approximately 19 MeSH terms per report, which included about 40% of the relevant report concepts. Pindex output a mean of approximately 57 terms per report and captured about 45% of the relevant report concepts. A hybrid system captured approximately 66% of the relevant concepts and output about 71 terms per report.

Conclusion: The outputs of PostDoc and Pindex are complementary in capturing MeSH terms from clinical free text. The results suggest possible approaches to reduce the number of terms output while maintaining the percentage of terms captured, including the use of UMLS semantic types to constrain the output list to contain only clinically relevant MeSH terms.

This article has been cited by other articles:

				S. Sohn, W. Kim, D. C. Comeau, and W. J. Wilbur Optimal Training Sets for Bayesian Prediction of MeSH(R) Assignment J. Am. Med. Inform. Assoc., July 1, 2008; 15(4): 546 - 553. [Abstract] [Full Text] [PDF]

				C. A. Sneiderman, D. Demner-Fushman, M. Fiszman, N. C. Ide, and T. C. Rindflesch Knowledge-based Methods to Help Clinicians Find Answers in MEDLINE J. Am. Med. Inform. Assoc., November 1, 2007; 14(6): 772 - 780. [Abstract] [Full Text] [PDF]

				A. Turchin, I. S. Kohane, and M. L. Pendergrass Identification of Patients With Diabetes From the Text of Physician Notes in the Electronic Medical Record Diabetes Care, July 1, 2005; 28(7): 1794 - 1795. [Full Text] [PDF]

				Y. Huang, H. J. Lowe, D. Klein, and R. J. Cucina Improved Identification of Noun Phrases in Clinical Radiology Reports Using a High-Performance Statistical Natural Language Parser Augmented with the UMLS Specialist Lexicon J. Am. Med. Inform. Assoc., May 1, 2005; 12(3): 275 - 285. [Abstract] [Full Text] [PDF]

				C. Friedman, L. Shagina, Y. Lussier, and G. Hripcsak Automated Encoding of Clinical Documents Based on Natural Language Processing J. Am. Med. Inform. Assoc., September 1, 2004; 11(5): 392 - 402. [Abstract] [Full Text] [PDF]

				J. C. Denny, J. D. Smithers, R. A. Miller, and A. Spickard III "Understanding" Medical School Curriculum Content Using KnowledgeMap J. Am. Med. Inform. Assoc., July 1, 2003; 10(4): 351 - 362. [Abstract] [Full Text] [PDF]

				G. Hripcsak and A. Wilcox Reference Standards, Judges, and Comparison Subjects: Roles for Experts in Evaluating System Performance J. Am. Med. Inform. Assoc., January 1, 2002; 9(1): 1 - 15. [Abstract] [Full Text] [PDF]

				W. Kim and W. J. Wilbur Corpus-based Statistical Screening for Phrase Identification J. Am. Med. Inform. Assoc., September 1, 2000; 7(5): 499 - 511. [Abstract] [Full Text]

				D. B. Aronow, F. Fangfang, and W. B. Croft Ad Hoc Classification of Radiology Reports J. Am. Med. Inform. Assoc., September 1, 1999; 6(5): 393 - 411. [Abstract] [Full Text] [PDF]

				A. O'Rourke, A. Booth, and N. Ford Another fine MeSH: clinical medicine meets information science Journal of Information Science, August 1, 1999; 25(4): 275 - 281. [Abstract] [PDF]

				G. Hripcsak, G. J. Kuperman, C. Friedman, and D. F. Heitjan A Reliability Study for Evaluating Information Extraction from Radiology Reports J. Am. Med. Inform. Assoc., March 1, 1999; 6(2): 143 - 150. [Abstract] [Full Text] [PDF]

				E. E. Westberg and R. A. Miller The Basis for Using the Internet to Support the Information Needs of Primary Care J. Am. Med. Inform. Assoc., January 1, 1999; 6(1): 6 - 25. [Abstract] [Full Text] [PDF]

				A. T. McCray and R. A. Miller Making the Conceptual Connections: The UMLS after a Decade of Research and Development J. Am. Med. Inform. Assoc., January 1, 1998; 5(1): 129 - 130. [Full Text]