Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

Alexander P.L. Martindale; Benjamin Ng; Victoria Ngai; Aditya U. Kale; Lavinia Ferrante di Ruffano; Robert M. Golub; Gary S. Collins; David Moher; Melissa D. McCradden; Lauren Oakden-Rayner; Samantha Cruz Rivera; Melanie Calvert; Christopher J. Kelly; Cecilia S. Lee; Christopher Yau; An Wen Chan; Pearse A. Keane; Andrew L. Beam; Alastair K. Denniston; Xiaoxuan Liu

doi:10.1038/s41467-024-45355-3

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

Alexander P.L. Martindale, Benjamin Ng, Victoria Ngai, Aditya U. Kale, Lavinia Ferrante di Ruffano, Robert M. Golub, Gary S. Collins, David Moher, Melissa D. McCradden, Lauren Oakden-Rayner, Samantha Cruz Rivera, Melanie Calvert, Christopher J. Kelly, Cecilia S. Lee, Christopher Yau, An Wen Chan, Pearse A. Keane, Andrew L. Beam, Alastair K. Denniston, Xiaoxuan Liu^*

^*Corresponding author for this work

Medicine, General Medicine Division

Research output: Contribution to journal › Article › peer-review

6 Scopus citations

Abstract

The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77–94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

Original language	English (US)
Article number	1619
Journal	Nature communications
Volume	15
Issue number	1
DOIs	https://doi.org/10.1038/s41467-024-45355-3
State	Published - Dec 2024

Funding

Several authors (X.L., D.M., A.D., C.K., L.F.R., C.L., A.W.C., M.C., P.K., G.S.C., R.G., L.O.R., M.M., C.Y., S.C.R., A.B.) were involved in the development of CONSORT-AI. MC receives funding from the NIHR, UK Research and Innovation (UKRI), NIHR BRC, the NIHR Surgical Reconstruction and Microbiology Research Centre, NIHR ARC West Midlands, NIHR Birmingham-Oxford Blood and Transplant Research Unit (BTRU) in Precision Transplant and Cellular Therapeutics, UKSPINE, European Regional Development Fund \u2013 Demand Hub and Health Data Research UK at the University of Birmingham and University Hospitals Birmingham NHS Foundation Trust, Innovate UK (part of UKRI), Macmillan Cancer Support, UCB Pharma, GSK and Gilead. M.C. has received personal fees from Astellas, Aparito Ltd, CIS Oncology, Takeda, Merck, Daiichi Sankyo, Glaukos, GSK and the Patient-Centred Outcomes Research Institute (PCORI) outside the submitted work. X.L. and A.D. have received funding from the NHS AI Lab, The Health Foundation, NIHR, NIHR BRC, MHRA and NICE, outside the submitted work. A.D. and M.C. are supported by the NIHR Birmingham Biomedical Research Centre. The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care. C.K. is an employee of Google, UK. L.F.R. is an employee of York Health Economics Consortium (YHEC). The remaining authors declare no competing interests.

ASJC Scopus subject areas

General Chemistry
General Biochemistry, Genetics and Molecular Biology
General Physics and Astronomy

Access to Document

10.1038/s41467-024-45355-3

Cite this

Martindale, A. P. L., Ng, B., Ngai, V., Kale, A. U., Ferrante di Ruffano, L., Golub, R. M., Collins, G. S., Moher, D., McCradden, M. D., Oakden-Rayner, L., Rivera, S. C., Calvert, M., Kelly, C. J., Lee, C. S., Yau, C., Chan, A. W., Keane, P. A., Beam, A. L., Denniston, A. K., & Liu, X. (2024). Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines. Nature communications, 15(1), Article 1619. https://doi.org/10.1038/s41467-024-45355-3

@article{b789685ca18f43c4945ef31de6ee9e4f,

title = "Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines",

abstract = "The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77–94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.",

author = "Martindale, {Alexander P.L.} and Benjamin Ng and Victoria Ngai and Kale, {Aditya U.} and {Ferrante di Ruffano}, Lavinia and Golub, {Robert M.} and Collins, {Gary S.} and David Moher and McCradden, {Melissa D.} and Lauren Oakden-Rayner and Rivera, {Samantha Cruz} and Melanie Calvert and Kelly, {Christopher J.} and Lee, {Cecilia S.} and Christopher Yau and Chan, {An Wen} and Keane, {Pearse A.} and Beam, {Andrew L.} and Denniston, {Alastair K.} and Xiaoxuan Liu",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2024.",

year = "2024",

month = dec,

doi = "10.1038/s41467-024-45355-3",

language = "English (US)",

volume = "15",

journal = "Nature communications",

issn = "2041-1723",

publisher = "Nature Research",

number = "1",

}

Martindale, APL, Ng, B, Ngai, V, Kale, AU, Ferrante di Ruffano, L, Golub, RM, Collins, GS, Moher, D, McCradden, MD, Oakden-Rayner, L, Rivera, SC, Calvert, M, Kelly, CJ, Lee, CS, Yau, C, Chan, AW, Keane, PA, Beam, AL, Denniston, AK & Liu, X 2024, 'Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines', Nature communications, vol. 15, no. 1, 1619. https://doi.org/10.1038/s41467-024-45355-3

TY - JOUR

T1 - Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

AU - Martindale, Alexander P.L.

AU - Ng, Benjamin

AU - Ngai, Victoria

AU - Kale, Aditya U.

AU - Ferrante di Ruffano, Lavinia

AU - Golub, Robert M.

AU - Collins, Gary S.

AU - Moher, David

AU - McCradden, Melissa D.

AU - Oakden-Rayner, Lauren

AU - Rivera, Samantha Cruz

AU - Calvert, Melanie

AU - Kelly, Christopher J.

AU - Lee, Cecilia S.

AU - Yau, Christopher

AU - Chan, An Wen

AU - Keane, Pearse A.

AU - Beam, Andrew L.

AU - Denniston, Alastair K.

AU - Liu, Xiaoxuan

PY - 2024/12

Y1 - 2024/12

N2 - The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77–94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

AB - The Consolidated Standards of Reporting Trials extension for Artificial Intelligence interventions (CONSORT-AI) was published in September 2020. Since its publication, several randomised controlled trials (RCTs) of AI interventions have been published but their completeness and transparency of reporting is unknown. This systematic review assesses the completeness of reporting of AI RCTs following publication of CONSORT-AI and provides a comprehensive summary of RCTs published in recent years. 65 RCTs were identified, mostly conducted in China (37%) and USA (18%). Median concordance with CONSORT-AI reporting was 90% (IQR 77–94%), although only 10 RCTs explicitly reported its use. Several items were consistently under-reported, including algorithm version, accessibility of the AI intervention or code, and references to a study protocol. Only 3 of 52 included journals explicitly endorsed or mandated CONSORT-AI. Despite a generally high concordance amongst recent AI RCTs, some AI-specific considerations remain systematically poorly reported. Further encouragement of CONSORT-AI adoption by journals and funders may enable more complete adoption of the full CONSORT-AI guidelines.

UR - http://www.scopus.com/inward/record.url?scp=85185652372&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85185652372&partnerID=8YFLogxK

U2 - 10.1038/s41467-024-45355-3

DO - 10.1038/s41467-024-45355-3

M3 - Article

C2 - 38388497

AN - SCOPUS:85185652372

SN - 2041-1723

VL - 15

JO - Nature communications

JF - Nature communications

IS - 1

M1 - 1619

ER -

Concordance of randomised controlled trials for artificial intelligence interventions with the CONSORT-AI reporting guidelines

Abstract

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this