Reporting guidelines are recommendations to help write up research clearly.
Your research will be used by people from different disciplines and backgrounds for decades to come. Reporting guidelines are community-created recommendations for describing what you did and what you found so that everyone can understand, repeat, apply, and synthesise your work. Although they recommend information to include in your manuscript, they don’t dictate how to order that information.
Most reporting guidelines consist of the full guidance (sometimes called an Explanation and Elaboration document) and a checklist. The full guidance provides detailed explanations and examples for each item, and the checklist allows you to demonstrate adherence to editors.
You can use reporting guidelines throughout your research process. However you use reporting guidelines, please cite them.
Writing manuscripts
Write confidently using a reporting guideline to quickly turn a blank page into a thorough and impactful manuscript.
Checking
Use a reporting checklist to demonstrate to an editor or peer reviewer that you have included everything. Many journals require completed checklists at submission.
Writing applications
Reporting guidelines can help you write funding applications, ethics applications, and protocols, but they won’t make design decisions for you!
Reporting guidelines are neither design nor quality appraisal tools.
Although reporting guidelines recommend information to include when writing up research, they do not mandate how to design research. Similarly, when reviewing literature, although you can use reporting guidelines to assess whether a manuscript is well reported, you cannot use them to appraise whether that study is well designed.
Key information
Reporting guideline acronym
TRIPOD+AI
Provided for
Reporting of studies that develop or evaluate the performance of a prediction model
Relevant URLs (full-text if available)
Read the full-text of TRIPOD+AI
Complete an interactive TRIPOD+AI checklist, which you can upload when submitting your paper to a journal.
PubMed ID
Downloads
Download the TRIPOD+AI checklist (PDF).
Download the TRIPOD+AI Expanded Checklist (PDF) (Explanation & Elaboration Light)
Download the TRIPOD+AI for Abstracts checklist
Bibliographic reference
Commonly used reporting guidelines
| STROBE | Observational Studies |
| PRISMA | Systematic reviews of trials |
| PRISMA-P | Systematic review protocols |
| CONSORT | Randomised trials |
| SPIRIT | Randomised trial protocols |
| SRQR | Qualitative Research |
| CARE | Case Reports |
| STARD | Diagnostic studies |
| TRIPOD+AI | Prediction Models |
| ARRIVE | Animal Research |
| SQUIRE | Quality Improvement |
| CHEERS | Economic Evaluations |
| Search all |
Collins GS, Moons KGM, Dhiman P, Riley RD, Beam AL, Van Calster B, Ghassemi M, Liu X, Reitsma JB, van Smeden M, Boulesteix AL, Camaradou JC, Celi LA, Denaxas S, Denniston AK, Glocker B, Golub RM, Harvey H, Heinze G, Hoffman MM, Kengne AP, Lam E, Lee N, Loder EW, Maier-Hein L, Mateen BA, McCradden MD, Oakden-Rayner L, Ordish J, Parnell R, Rose S, Singh K, Wynants L, Logullo P. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. PMID: 38626948 full text
Explanation and Elaboration
Please continue to use the TRIPOD 2015 E&E paper until the TRIPOD+AI E&E paper is available:
Moons KG, Altman DG, Reitsma JB, Ioannidis JP, Macaskill P, Steyerberg EW, Vickers AJ, Ransohoff DF, Collins GS. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): Explanation and Elaboration. Ann Intern Med. 2015;162(1):W1-W73. PMID: 25560730 full text
Additional information
Language
English
Availability in additional languages
TRIPOD+AI
The TRIPOD+AI statement and reporting checklist are also available in the following languagues
TRIPOD+AI Checklist (Chinese) Word
TRIPOD+AI Abstracts (Chinese) Word
TRIPOD+AI Checklist (Croatian) PDF
TRIPOD+AI Checklist (Japanese) PDF
TRIPOD 2015
The TRIPOD 2015 statement and reporting checklist are also available in the following languages:
TRIPOD 2015 Checklist (Chinese) Word
TRIPOD 2015 E&E (Japanese) Word
TRIPOD 2015 Checklist (Japanese) Word| PDF
TRIPOD 2015 E&E (Russian) PDF
Study design
- Artificial intelligence/Machine learning studies
- Diagnostic and prognostic studies
- Observational studies
Clinical area
- No clinical specialty specified
Applies to the whole report or to individual sections of the report?
- Whole report
Reporting guideline website URL
Previous versions of this guideline / Guideline history
TRIPOD 2015
Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement.
Ann Intern Med. 2015;162(1):55-63. PMID: 25560714 full text
Br J Cancer. 2015 Jan 6. PMID: 25562432 full text
Circulation. 2015 Jan 13;131(2):211-9. PMID: 25561516 full text
BMJ 2015; 350:g7594. PMID: 25569120 full text
J Clin Epidemiol. 2015 Feb;68(2):134-43. PMID: 25579640 full text
Eur Urol. 2014 Dec 9. PMID: 25572824 full text
BMC Med. 2015 Jan 6;13(1):1. PMID: 25563062 full text
Eur J Clin Invest. 2015;45(2):204-214. PMID: 25623047 full text
Br J Surg. 2015;102(3):148-158. PMID: 25627261 full text
BJOG. 2015;122(3):434-443. PMID: 25623578 full text
Diabet Med. 2015;32(2):146-154. PMID: 25600898 full text \
Other
Read the protocol for the development of TRIPOD+AI.
Additional Information
What is TRIPOD/TRIPOD+AI?
TRIPOD stands for Transparent Reporting Items for studies of Prognosis Or Diagnosis. It is an international, consensus-based reporting guideline for studies that develop or evaluate clinical prediction models.
The original TRIPOD Statement was published in 2015 and focused mainly on models built with regression methods. TRIPOD+AI, published in 2024, is the updated version. It covers prediction models built with regression or machine learning methods (such as random forests or deep learning), using one harmonised checklist. The “+” signals that regression and machine learning are covered together. The “AI” matches the terminology of other reporting guidelines for AI-related studies. TRIPOD+AI replaces the 2015 checklist, which should no longer be used.
What is a prediction model?
A prediction model combines information from several predictors (for example age, blood pressure or imaging features) to estimate an individual’s probability of having a condition now (diagnostic models) or of developing an outcome in the future (prognostic models).
Prediction models support clinical decisions such as referring patients for further testing, starting treatment or lifestyle changes, or monitoring disease progression.
Aims and use of TRIPOD+AI
TRIPOD+AI aims to help authors give a complete, accurate and transparent account of why a prediction model study was done, what was done, and what was found. This supports appraisal by peer reviewers and editors, independent evaluation and implementation of models, and, ultimately, trust from the clinicians, patients and policy makers who may rely on them.
Adherence assessment
An adherence assessment form for measuring adherence to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement has been developed.
Heus P, Damen JAAG, Pajouheshnia R, Scholten RJPM, Reitsma JB, Collins GS, Altman DG, Moons KGM, Hooft L.Uniformity in measuring adherence to reporting guidelines: the example of TRIPOD for assessing completeness of reporting of prediction model studies. BMJ Open. 2019;9(4):e025611. PMID: 31023756
The adherence assessment forms are available from: https://www.tripod-statement.org/adherence/