Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 98 of the 99 references it cites were found in a registry or an index; 9 of the 27 sources its claims cite were checked for support.

TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods

Open access

Abstract

TRIPOD+AI updates reporting guidance for prediction-model studies using regression or machine learning methods to support complete and transparent reporting.

Overview

CoChat Summary

TL;DR

TRIPOD+AI updates TRIPOD 2015 to provide harmonised minimum reporting guidance for clinical prediction model studies using regression or machine learning, presenting a 27-item checklist with 52 subitems and a 13-item abstract checklist. It supersedes TRIPOD 2015 and adds emphasis on fairness, open science, and patient and public involvement.

Key findings

  • TRIPOD+AI comprises 27 main checklist items and 52 subitems, covering title, abstract, introduction, methods, open science, patient and public involvement, results, and discussion; the separate TRIPOD+AI for Abstracts checklist contains 13 items. It supersedes the TRIPOD 2015 checklist, which should no longer be used.
  • Development used literature reviews and consensus: an initial 65 candidate items were reduced to 59 for Delphi round 2; round 1 had 170 participants from 22 countries, round 2 had 200 participants from 27 countries, and the consensus meeting had 28 participants, with 17 items discussed and voted on in plenary.
  • New content includes fairness embedded throughout the checklist (items 3c, 5a, 7, 8a, 8b, 9c, 12f, 14, 20b, 23a, 25, 26), an open science section (funding, conflicts of interest, protocol, registration, data sharing, code sharing), a patient and public involvement item (item 19), and a model performance recommendation to report estimates for key subgroups.
  • The stated aim is to promote complete, accurate, and transparent reporting to facilitate study appraisal, model evaluation, replication, reproducibility, and implementation, and to reduce overinterpretation of findings.

Methods

  • Guideline development followed EQUATOR Network recommendations, with a steering group, a registered protocol, candidate item generation from TRIPOD 2015 and other reporting checklists/literature, a modified Delphi survey, a patient and public involvement and engagement meeting, and an online consensus meeting; reporting of consensus methods followed ACCORD.
  • Delphi participants rated items as “can be omitted,” “possibly include,” “desirable for inclusion,” or “essential for inclusion”; items with agreement of 70% or higher were carried to round 2, while lower-agreement items were excluded, merged, or rephrased. Round 1 invited 292 people and 170 completed; round 2 invited 395 people and 200 completed.
  • The consensus meeting was held online on 5 July 2022 with 28 participants attending part or all of the meeting, including one non-voting attendee; after discussion and voting on 17 highlighted items, the final TRIPOD+AI checklist was formed.

Limitations

  • The paper states that foundation and large language models such as ChatGPT were not considered at the time of guideline development; TRIPOD+AI is primarily aimed at non-generative models, and periodic updating will be needed to remain relevant to advances such as generative approaches.
  • The paper states that the patient and public involvement and engagement meeting was not planned in the study protocol and was the only deviation from the published protocol; the patient and public involvement item received 69% agreement in round 2, just below the 70% threshold, but the steering group retained it for consensus discussion.
  • Evident from the text: this is a consensus-based reporting guideline, not an empirical evaluation of whether TRIPOD+AI improves reporting quality, model performance, or clinical outcomes; no such outcome data are reported.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1136/bmj-2023-078378

Cites

98 of 98 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

6 Valid · 5 Not valid · 16 Not checked · 60 Own results and interpretations

6 more claims

Create a free account to see all 87 claims and to verify the 1 reference still open.

See all claims — free account
  • Probably not a substantial claim. 71
  • It may state two separate claims as one. 34
  • The quote only partly states this claim. 1

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

14 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

1 of 1

Citations

Cites

Show all 99 references

Research works printed but not linked: 1

  1. 10.1177/962280218784726 · doi:10.1177/962280218784726

Cited by

See all 4,718

Metadata

Authors
Collins, G. S., Moons, K. G. M., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., Ghassemi, M., Liu, X., Reitsma, J. B., van Smeden, M., Boulesteix, A.-L., Camaradou, J. C., Celi, L. A., Denaxas, S., Denniston, A. K., Glocker, B., Golub, R. M., Harvey, H., Heinze, G., Hoffman, M. M., Kengne, A. P., Lam, E., Lee, N., Loder, E. W., Maier-Hein, L., Mateen, B. A., McCradden, M. D., Oakden-Rayner, L., Ordish, J., Parnell, R., Rose, S., Singh, K., Wynants, L., & Logullo, P.
Affiliations
  • Centre for Statistics in Medicine, UK EQUATOR Centre, Nuffield Department of Orthopaedics, Rheumatology, and Musculoskeletal Sciences, University of Oxford, Oxford OX3 7LD, UK
  • Utrecht University (NL)
  • University of Oxford (GB)
  • National Institute for Health and Care Research (GB)
  • Harvard University (US)
  • Department of Development and Regeneration, KU Leuven, Leuven, Belgium
  • Massachusetts Institute of Technology (US)
  • University Hospitals Birmingham NHS Foundation Trust (GB)
  • Julius Centre for Health Sciences and Primary Care, University Medical Centre Utrecht, Utrecht University, Utrecht, Netherlands
  • Munich Center for Machine Learning (DE)
  • University of East Anglia (GB)
  • Beth Israel Deaconess Medical Center (US)
  • University College London (GB)
  • Imperial College London (GB)
  • Northwestern University (US)
  • Hardian Health, Haywards Heath, UK
  • Medical University of Vienna (AT)
  • University Health Network (CA)
  • University of Cape Town (ZA)
  • Health Data Research UK (GB)
  • National Institute for Health and Care Excellence (GB)
  • Brigham and Women's Hospital (US)
  • Department of Intelligent Medical Systems, German Cancer Research Centre, Heidelberg, Germany
  • The Alan Turing Institute (GB)
  • Hospital for Sick Children (CA)
  • Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia
  • Medicines and Healthcare products Regulatory Agency (GB)
  • The University of Adelaide (AU)
  • University of Michigan (US)
  • Maastricht University (NL)
Venue
BMJ
Publisher
BMJ
Published
2024-04-16
Volume
385
Pages
e078378
ISSN
1756-1833 (ISSN-L)
OpenAlex
W4394857110
Cited by
4,718
References
99
Citations by year
2026: 3480 · 2025: 1035 · 2024: 202
FWCI
1310.37
Type
journal article
Language
en
Open access
Locations
  • BMJ (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • University of Birmingham Research Portal (University of Birmingham) (publishedVersion, cc-by)
  • UCL Discovery (University College London) (submittedVersion, cc-by)
  • Open access LMU (Ludwid Maxmilian's Universitat Munchen) (submittedVersion, cc-by)
  • Lirias (submittedVersion, cc-by)
  • Research Publications (Maastricht University) (submittedVersion, cc-by)
  • Utrecht University Repository (Utrecht University) (submittedVersion, other-oa)
  • HighWire Press Open Archive (submittedVersion)
Funders
  • Cancer Research UK
  • Health Data Research UK
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods in Epidemiology
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
TRIPOD+AI, reporting guidelines, multivariable prediction models, clinical prediction model, machine learning, artificial intelligence, regression models, reporting checklist, tripod, transparency in research reporting
MeSH terms
Decision Support Techniques, Humans, Prognosis, Models, Statistical, Checklist

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. https://app.cochat.ai/papers/10.1136/bmj-2023-078378
The paper
Collins, G. S., Moons, K. G. M., Dhiman, P., Riley, R. D., Beam, A. L., Van Calster, B., Ghassemi, M., Liu, X., Reitsma, J. B., van Smeden, M., Boulesteix, A.-L., Camaradou, J. C., Celi, L. A., Denaxas, S., Denniston, A. K., Glocker, B., Golub, R. M., Harvey, H., Heinze, G., . . . Logullo, P. (2024). TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. https://doi.org/10.1136/bmj-2023-078378

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.