View in EDS HTML Full Text PDF Full Text

Using a large language model (ChatGPT) to assess risk of bias in randomized controlled trials of medical interventions: protocol for a pilot study of interrater agreement with human reviewers.

Saved in:
Bibliographic Details
Title: Using a large language model (ChatGPT) to assess risk of bias in randomized controlled trials of medical interventions: protocol for a pilot study of interrater agreement with human reviewers.
Authors: Rose CJ; Center for Epidemic Interventions Research, Norwegian Institute of Public Health, Oslo, Norway. cjro@fhi.no.; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway. cjro@fhi.no., Bidonde J; Division of Health Services, Norwegian Institute of Public Health, Oslo, Norway.; School of Rehabilitation Science, University of Saskatchewan, Saskatoon, Canada.; The Norwegian Medical Products Agency, Oslo, Norway., Ringsten M; Cochrane Sweden, Lund University, Skåne University Hospital, Lund, Sweden., Glanville J; Glanville.info, York, UK., Berg RC; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.; Arctic University of Tromsø, Tromsø, Norway., Cooper C; Bristol Medical School, University of Bristol, Bristol, UK., Muller AE; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway., Bergsund HB; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway., Meneses-Echavez JF; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.; Facultad de Cultura Física, Deporte y Recreación, Universidad Santo Tomás, Bogotá, Colombia., Potrebny T; Section for Evidence-Based Practice, Western Norway University of Applied Sciences, Bergen, Norway.
Source: BMC medical research methodology [BMC Med Res Methodol] 2025 Jul 31; Vol. 25 (1), pp. 182. Date of Electronic Publication: 2025 Jul 31.
Publication Type: Journal Article
Journal Info: Publisher: BioMed Central Country of Publication: England NLM ID: 100968545 Publication Model: Electronic Cited Medium: Internet ISSN: 1471-2288 (Electronic) Linking ISSN: 14712288 NLM ISO Abbreviation: BMC Med Res Methodol Subsets: MEDLINE
Database: MEDLINE Ultimate
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: mdl
DbLabel: MEDLINE Ultimate
An: 40745627
AccessLevel: 2
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Using a large language model (ChatGPT) to assess risk of bias in randomized controlled trials of medical interventions: protocol for a pilot study of interrater agreement with human reviewers.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Rose+CJ%22">Rose CJ</searchLink>; Center for Epidemic Interventions Research, Norwegian Institute of Public Health, Oslo, Norway. cjro@fhi.no.; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway. cjro@fhi.no.<br /><searchLink fieldCode="AU" term="%22Bidonde+J%22">Bidonde J</searchLink>; Division of Health Services, Norwegian Institute of Public Health, Oslo, Norway.; School of Rehabilitation Science, University of Saskatchewan, Saskatoon, Canada.; The Norwegian Medical Products Agency, Oslo, Norway.<br /><searchLink fieldCode="AU" term="%22Ringsten+M%22">Ringsten M</searchLink>; Cochrane Sweden, Lund University, Skåne University Hospital, Lund, Sweden.<br /><searchLink fieldCode="AU" term="%22Glanville+J%22">Glanville J</searchLink>; Glanville.info, York, UK.<br /><searchLink fieldCode="AU" term="%22Berg+RC%22">Berg RC</searchLink>; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.; Arctic University of Tromsø, Tromsø, Norway.<br /><searchLink fieldCode="AU" term="%22Cooper+C%22">Cooper C</searchLink>; Bristol Medical School, University of Bristol, Bristol, UK.<br /><searchLink fieldCode="AU" term="%22Muller+AE%22">Muller AE</searchLink>; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.<br /><searchLink fieldCode="AU" term="%22Bergsund+HB%22">Bergsund HB</searchLink>; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.<br /><searchLink fieldCode="AU" term="%22Meneses-Echavez+JF%22">Meneses-Echavez JF</searchLink>; Cluster for Reviews and Health Technology Assessments, Norwegian Institute of Public Health, Oslo, Norway.; Facultad de Cultura Física, Deporte y Recreación, Universidad Santo Tomás, Bogotá, Colombia.<br /><searchLink fieldCode="AU" term="%22Potrebny+T%22">Potrebny T</searchLink>; Section for Evidence-Based Practice, Western Norway University of Applied Sciences, Bergen, Norway.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22100968545%22">BMC medical research methodology</searchLink> [BMC Med Res Methodol] 2025 Jul 31; Vol. 25 (1), pp. 182. <i>Date of Electronic Publication: </i>2025 Jul 31.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22BioMed+Central%22">BioMed Central </searchLink><i>Country of Publication: </i>England <i>NLM ID: </i>100968545 <i>Publication Model: </i>Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>1471-2288 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2214712288%22">14712288 </searchLink><i>NLM ISO Abbreviation: </i>BMC Med Res Methodol <i>Subsets: </i>MEDLINE
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=mdl&AN=40745627
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1186/s12874-025-02631-0
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 182
    Titles:
      – TitleFull: Using a large language model (ChatGPT) to assess risk of bias in randomized controlled trials of medical interventions: protocol for a pilot study of interrater agreement with human reviewers.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Rose CJ
      – PersonEntity:
          Name:
            NameFull: Bidonde J
      – PersonEntity:
          Name:
            NameFull: Ringsten M
      – PersonEntity:
          Name:
            NameFull: Glanville J
      – PersonEntity:
          Name:
            NameFull: Berg RC
      – PersonEntity:
          Name:
            NameFull: Cooper C
      – PersonEntity:
          Name:
            NameFull: Muller AE
      – PersonEntity:
          Name:
            NameFull: Bergsund HB
      – PersonEntity:
          Name:
            NameFull: Meneses-Echavez JF
      – PersonEntity:
          Name:
            NameFull: Potrebny T
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 31
              M: 07
              Text: 2025 Jul 31
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-electronic
              Value: 1471-2288
          Numbering:
            – Type: volume
              Value: 25
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: BMC medical research methodology
              Type: main
ResultId 1