Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Implementation and evaluation of a negation tagger in a pipeline-based system for information extract from pathology reports.

Mitchell, Kevin J and Becich, Michael J and Berman, Jules J and Chapman, Wendy W and Gilbertson, John and Gupta, Dilip and Harrison, James and Legowski, Elizabeth and Crowley, Rebecca S (2004) Implementation and evaluation of a negation tagger in a pipeline-based system for information extract from pathology reports. Studies in health technology and informatics, 107 (Pt 1). 663 - 667. ISSN 0926-9630

[img] Plain Text (licence)
Available under License : See the attached license file.

Download (1kB)

Abstract

We have developed a pipeline-based system for automated annotation of Surgical Pathology Reports with UMLS terms that builds on GATE--an open-source architecture for language engineering. The system includes a module for detecting and annotating negated concepts, which implements the NegEx algorithm--an algorithm originally described for use in discharge summaries and radiology reports. We describe the implementation of the system, and early evaluation of the Negation Tagger. Our results are encouraging. In the key Final Diagnosis section, with almost no modification of the algorithm or phrase lists, the system performs with precision of 0.84 and recall of 0.80 against a gold-standard corpus of negation annotations, created by modified Delphi technique by a panel of pathologists. Further work will focus on refining the Negation Tagger and UMLS Tagger and adding additional processing resources for annotating free-text pathology reports.


Share

Citation/Export:
Social Networking:
Share |

Details

Item Type: Article
Status: Published
Creators/Authors:
CreatorsEmailPitt UsernameORCID
Mitchell, Kevin J
Becich, Michael J
Berman, Jules J
Chapman, Wendy W
Gilbertson, John
Gupta, Dilip
Harrison, James
Legowski, Elizabeth
Crowley, Rebecca S
Date: 2004
Date Type: Publication
Journal or Publication Title: Studies in health technology and informatics
Volume: 107
Number: Pt 1
Page Range: 663 - 667
Schools and Programs: School of Medicine > Biomedical Informatics
Refereed: Yes
ISSN: 0926-9630
Article Type: Research Article
MeSH Headings: Algorithms; Clinical Laboratory Information Systems; Humans; Information Storage and Retrieval; Internet; Medical Records Systems, Computerized; Natural Language Processing; Pathology, Surgical; Software; Specimen Handling; Unified Medical Language System
PubMed ID: 15360896
Date Deposited: 05 Oct 2012 19:01
Last Modified: 01 Nov 2017 14:03
URI: http://d-scholarship.pitt.edu/id/eprint/15615

Metrics

Monthly Views for the past 3 years

Plum Analytics


Actions (login required)

View Item View Item