View in EDS PDF Full Text

Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study.

Saved in:
Bibliographic Details
Title: Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study.
Authors: Chen, Eileen1 eileen.0415@livemail.tw, Bullard, Julia2 julia.bullard@ubc.ca, Giustini, Dean3 dean.giustini@ubc.ca
Source: Journal of the Medical Library Association. Jul2023, Vol. 111 Issue 3, p684-694. 11p.
Subjects: Computer software, Pilot projects, Medicine, Online information services, Data quality, Hypertension, Subject headings, Serial publications, National Library of Medicine (U.S.), Genetic testing, Comparative grammar, Sex distribution, Citation analysis, Medical emergencies, Nursing practice, Automation, Information retrieval, Job satisfaction, MEDLINE, Periodical articles, Librarians, Information storage & retrieval systems, Genetic counseling, Medical literature, Abstracting & indexing services, Impact factor (Citation analysis)
Abstract: Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. Conclusion: NLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. [ABSTRACT FROM AUTHOR]
Copyright of Journal of the Medical Library Association is the property of University of Pittsburgh, University Library System and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 170713796
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Chen%2C+Eileen%22">Chen, Eileen</searchLink><relatesTo>1</relatesTo><i> eileen.0415@livemail.tw</i><br /><searchLink fieldCode="AR" term="%22Bullard%2C+Julia%22">Bullard, Julia</searchLink><relatesTo>2</relatesTo><i> julia.bullard@ubc.ca</i><br /><searchLink fieldCode="AR" term="%22Giustini%2C+Dean%22">Giustini, Dean</searchLink><relatesTo>3</relatesTo><i> dean.giustini@ubc.ca</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+the+Medical+Library+Association%22">Journal of the Medical Library Association</searchLink>. Jul2023, Vol. 111 Issue 3, p684-694. 11p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Computer+software%22">Computer software</searchLink><br /><searchLink fieldCode="DE" term="%22Pilot+projects%22">Pilot projects</searchLink><br /><searchLink fieldCode="DE" term="%22Medicine%22">Medicine</searchLink><br /><searchLink fieldCode="DE" term="%22Online+information+services%22">Online information services</searchLink><br /><searchLink fieldCode="DE" term="%22Data+quality%22">Data quality</searchLink><br /><searchLink fieldCode="DE" term="%22Hypertension%22">Hypertension</searchLink><br /><searchLink fieldCode="DE" term="%22Subject+headings%22">Subject headings</searchLink><br /><searchLink fieldCode="DE" term="%22Serial+publications%22">Serial publications</searchLink><br /><searchLink fieldCode="DE" term="%22National+Library+of+Medicine+%28U%2ES%2E%29%22">National Library of Medicine (U.S.)</searchLink><br /><searchLink fieldCode="DE" term="%22Genetic+testing%22">Genetic testing</searchLink><br /><searchLink fieldCode="DE" term="%22Comparative+grammar%22">Comparative grammar</searchLink><br /><searchLink fieldCode="DE" term="%22Sex+distribution%22">Sex distribution</searchLink><br /><searchLink fieldCode="DE" term="%22Citation+analysis%22">Citation analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+emergencies%22">Medical emergencies</searchLink><br /><searchLink fieldCode="DE" term="%22Nursing+practice%22">Nursing practice</searchLink><br /><searchLink fieldCode="DE" term="%22Automation%22">Automation</searchLink><br /><searchLink fieldCode="DE" term="%22Information+retrieval%22">Information retrieval</searchLink><br /><searchLink fieldCode="DE" term="%22Job+satisfaction%22">Job satisfaction</searchLink><br /><searchLink fieldCode="DE" term="%22MEDLINE%22">MEDLINE</searchLink><br /><searchLink fieldCode="DE" term="%22Periodical+articles%22">Periodical articles</searchLink><br /><searchLink fieldCode="DE" term="%22Librarians%22">Librarians</searchLink><br /><searchLink fieldCode="DE" term="%22Information+storage+%26+retrieval+systems%22">Information storage & retrieval systems</searchLink><br /><searchLink fieldCode="DE" term="%22Genetic+counseling%22">Genetic counseling</searchLink><br /><searchLink fieldCode="DE" term="%22Medical+literature%22">Medical literature</searchLink><br /><searchLink fieldCode="DE" term="%22Abstracting+%26+indexing+services%22">Abstracting & indexing services</searchLink><br /><searchLink fieldCode="DE" term="%22Impact+factor+%28Citation+analysis%29%22">Impact factor (Citation analysis)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Objective: In 2002, the National Library of Medicine (NLM) introduced semi-automated indexing of Medline using the Medical Text Indexer (MTI). In 2021, NLM announced that it would fully automate its indexing in Medline with an improved MTI by mid-2022. This pilot study examines indexing using a sample of records in Medline from 2000, and how an early, public version of MTI's outputs compares to records created by human indexers. Methods: This pilot study examines twenty Medline records from 2000, a year before the MTI was introduced as a MeSH term recommender. We identified twenty higher- and lower-impact biomedical journals based on Journal Impact Factor (JIF) and examined the indexing of papers by feeding their PubMed records into the Interactive MTI tool. Results: In the sample, we found key differences between automated and human-indexed Medline records: MTI assigned more terms and used them more accurately for citations in the higher JIF group, and MTI tended to rank the Male check tag more highly than the Female check tag and to omit Aged check tags. Sometimes MTI chose more specific terms than human indexers but was inconsistent in applying specificity principles. Conclusion: NLM's transition to fully automated indexing of the biomedical literature could introduce or perpetuate inconsistencies and biases in Medline. Librarians and searchers should assess changes to index terms, and their impact on PubMed's mapping features for a range of topics. Future research should evaluate automated indexing as it pertains to finding clinical information effectively, and in performing systematic searches. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of the Medical Library Association is the property of University of Pittsburgh, University Library System and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=170713796
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.5195/jmla.2023.1588
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 684
    Subjects:
      – SubjectFull: Computer software
        Type: general
      – SubjectFull: Pilot projects
        Type: general
      – SubjectFull: Medicine
        Type: general
      – SubjectFull: Online information services
        Type: general
      – SubjectFull: Data quality
        Type: general
      – SubjectFull: Hypertension
        Type: general
      – SubjectFull: Subject headings
        Type: general
      – SubjectFull: Serial publications
        Type: general
      – SubjectFull: National Library of Medicine (U.S.)
        Type: general
      – SubjectFull: Genetic testing
        Type: general
      – SubjectFull: Comparative grammar
        Type: general
      – SubjectFull: Sex distribution
        Type: general
      – SubjectFull: Citation analysis
        Type: general
      – SubjectFull: Medical emergencies
        Type: general
      – SubjectFull: Nursing practice
        Type: general
      – SubjectFull: Automation
        Type: general
      – SubjectFull: Information retrieval
        Type: general
      – SubjectFull: Job satisfaction
        Type: general
      – SubjectFull: MEDLINE
        Type: general
      – SubjectFull: Periodical articles
        Type: general
      – SubjectFull: Librarians
        Type: general
      – SubjectFull: Information storage & retrieval systems
        Type: general
      – SubjectFull: Genetic counseling
        Type: general
      – SubjectFull: Medical literature
        Type: general
      – SubjectFull: Abstracting & indexing services
        Type: general
      – SubjectFull: Impact factor (Citation analysis)
        Type: general
    Titles:
      – TitleFull: Automated indexing using NLM's Medical Text Indexer (MTI) compared to human indexing in Medline: a pilot study.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Chen, Eileen
      – PersonEntity:
          Name:
            NameFull: Bullard, Julia
      – PersonEntity:
          Name:
            NameFull: Giustini, Dean
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 07
              Text: Jul2023
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-print
              Value: 15365050
          Numbering:
            – Type: volume
              Value: 111
            – Type: issue
              Value: 3
          Titles:
            – TitleFull: Journal of the Medical Library Association
              Type: main
ResultId 1