Academic Journal
Προβολή σε EDS

Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis.
Συγγραφείς: O'Rourke J; Parkinson School of Health Sciences and Public Health, Loyola University Chicago, IL, USA., Byrne M; Mayo Clinic-Office of the Chief Technology Officer, Rochester, MN, USA., Schroers G; Marcella Niehoff School of Nursing, Loyola University Chicago, IL, USA.
Πηγή: Western journal of nursing research [West J Nurs Res] 2026 Aug; Vol. 48 (8), pp. 887-894. Date of Electronic Publication: 2026 Jun 10.
Τύπος έκδοσης: Journal Article; Comparative Study
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Sage Publications Country of Publication: United States NLM ID: 7905435 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1552-8456 (Electronic) Linking ISSN: 01939459 NLM ISO Abbreviation: West J Nurs Res Subsets: MEDLINE
Imprint Name(s): Publication: Beverly Hills, CA : Sage Publications
Original Publication: [Anaheim, Calif.] Phillips-Allen.
Ιατρικοί όροι (MeSH): Artificial Intelligence*/trends , Artificial Intelligence*/standards , Information Storage and Retrieval*/methods , Information Storage and Retrieval*/standards, Humans ; Generative Artificial Intelligence ; Large Language Models
Περίληψη: Background: Artificial intelligence (AI), particularly generative and large language models, is being used in nursing education, practice, and scholarly writing. Generative AI applications have been specifically examined for their use in conducting literature reviews with evidence supporting reduced production time of scholarly work. However, there has been limited investigation of their levels of accuracy with identifying references for a literature review.
Objective: The purpose of this study was to compare human-generated citations of literature reviews with AI literature-review generated citations.
Methods: Using a comparative exploratory design, references from 4 human-written literature reviews, 2 published and 2 unpublished, on 4 different topics, were compared to references derived from 2 AI literature applications, Consensus and Elicit. Three prompting strategies were utilized, including prompts generated using ChatGPT-4. Agreement between the AI and human references was evaluated.
Results: The percent of agreement between AI and human generated reference lists ranged from 0% to 63.6%. The Consensus application had a greater overall mean rate of match (21.3%) as compared to Elicit (3.7%). The use of a ChatGPT-4 prompt did not significantly impact results, and there were no differences based on published or unpublished literature reviews.
Conclusion: The 2 literature-based applications examined in this study offered a glimpse of their potential use and limitations. The use of an AI literature review application may support but not replace human work.
Competing Interests: Declaration of Conflicting InterestsThe authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Contributed Indexing: Keywords: artificial intelligence; large language models; literature search; nursing; nursing research
Entry Date(s): Date Created: 20260610 Date Completed: 20260713 Latest Revision: 20260713
Update Code: 20260713
DOI: 10.1177/01939459261451723
PMID: 42267644
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:cmedm&genre=article&issn=15528456&ISBN=&volume=48&issue=8&date=20260801&spage=887&pages=887-894&title=Western journal of nursing research&atitle=Artificial%20Intelligence%20Applications%20Versus%20Manual%20Methods%20For%20Literature%20Retrieval%3A%20A%20Comparative%20Analysis.&aulast=O%27Rourke%20J&id=DOI:10.1177/01939459261451723
    Name: Full Text Finder (for New FTF UI) (ns324271)
    Category: fullText
    Text: Full Text Finder
    MouseOverText: Full Text Finder
Header DbId: cmedm
DbLabel: MEDLINE
An: 42267644
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22O'Rourke+J%22">O'Rourke J</searchLink>; Parkinson School of Health Sciences and Public Health, Loyola University Chicago, IL, USA.<br /><searchLink fieldCode="AU" term="%22Byrne+M%22">Byrne M</searchLink>; Mayo Clinic-Office of the Chief Technology Officer, Rochester, MN, USA.<br /><searchLink fieldCode="AU" term="%22Schroers+G%22">Schroers G</searchLink>; Marcella Niehoff School of Nursing, Loyola University Chicago, IL, USA.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%227905435%22">Western journal of nursing research</searchLink> [West J Nurs Res] 2026 Aug; Vol. 48 (8), pp. 887-894. <i>Date of Electronic Publication: </i>2026 Jun 10.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article; Comparative Study
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Sage+Publications%22">Sage Publications </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>7905435 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1552-8456 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2201939459%22">01939459 </searchLink><i>NLM ISO Abbreviation: </i>West J Nurs Res <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Publication</i>: Beverly Hills, CA : Sage Publications<br /><i>Original Publication</i>: [Anaheim, Calif.] Phillips-Allen.
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink>/<searchLink fieldCode="MM" term="%22Artificial+Intelligence+trends%22">trends</searchLink> <br /><searchLink fieldCode="MM" term="%22Artificial+Intelligence%22">Artificial Intelligence*</searchLink>/<searchLink fieldCode="MM" term="%22Artificial+Intelligence+standards%22">standards</searchLink> <br /><searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval%22">Information Storage and Retrieval*</searchLink>/<searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval+methods%22">methods</searchLink> <br /><searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval%22">Information Storage and Retrieval*</searchLink>/<searchLink fieldCode="MM" term="%22Information+Storage+and+Retrieval+standards%22">standards</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Generative+Artificial+Intelligence%22">Generative Artificial Intelligence</searchLink> ; <searchLink fieldCode="MH" term="%22Large+Language+Models%22">Large Language Models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Background: Artificial intelligence (AI), particularly generative and large language models, is being used in nursing education, practice, and scholarly writing. Generative AI applications have been specifically examined for their use in conducting literature reviews with evidence supporting reduced production time of scholarly work. However, there has been limited investigation of their levels of accuracy with identifying references for a literature review.<br />Objective: The purpose of this study was to compare human-generated citations of literature reviews with AI literature-review generated citations.<br />Methods: Using a comparative exploratory design, references from 4 human-written literature reviews, 2 published and 2 unpublished, on 4 different topics, were compared to references derived from 2 AI literature applications, Consensus and Elicit. Three prompting strategies were utilized, including prompts generated using ChatGPT-4. Agreement between the AI and human references was evaluated.<br />Results: The percent of agreement between AI and human generated reference lists ranged from 0% to 63.6%. The Consensus application had a greater overall mean rate of match (21.3%) as compared to Elicit (3.7%). The use of a ChatGPT-4 prompt did not significantly impact results, and there were no differences based on published or unpublished literature reviews.<br />Conclusion: The 2 literature-based applications examined in this study offered a glimpse of their potential use and limitations. The use of an AI literature review application may support but not replace human work.
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Declaration of Conflicting InterestsThe authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>artificial intelligence; large language models; literature search; nursing; nursing research
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260610 <i>Date Completed: </i>20260713 <i>Latest Revision: </i>20260713
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260713
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1177/01939459261451723
– Name: AN
  Label: PMID
  Group: ID
  Data: 42267644
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42267644
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1177/01939459261451723
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 887
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Generative Artificial Intelligence
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Artificial Intelligence trends
        Type: general
      – SubjectFull: Artificial Intelligence standards
        Type: general
      – SubjectFull: Information Storage and Retrieval methods
        Type: general
      – SubjectFull: Information Storage and Retrieval standards
        Type: general
    Titles:
      – TitleFull: Artificial Intelligence Applications Versus Manual Methods For Literature Retrieval: A Comparative Analysis.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: O'Rourke J
      – PersonEntity:
          Name:
            NameFull: Byrne M
      – PersonEntity:
          Name:
            NameFull: Schroers G
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 08
              Text: 2026 Aug
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 1552-8456
          Numbering:
            – Type: volume
              Value: 48
            – Type: issue
              Value: 8
          Titles:
            – TitleFull: Western journal of nursing research
              Type: main
ResultId 1