TRIPOD+AI Checklist
Interactive reporting checklist for studies developing or evaluating a clinical prediction model using regression or machine learning (AI) methods.
TRIPOD 2015 items only
0%
Items Rated
0
Reported
0
Not Reported
0
N/A
0
Unrated
New or modified items only
0%
Items Rated
0
Reported
0
Not Reported
0
N/A
0
Unrated
Combined
0%
Items Rated
0
Reported
0
Not Reported
0
N/A
0
Unrated
About This Tool: The TRIPOD+AI Checklist
What is it for?
This tool is a web-based checklist implementing the TRIPOD+AI (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis – Artificial Intelligence) reporting guideline. Its purpose is to support the complete, accurate and transparent reporting of studies that develop or evaluate (validate) a clinical prediction model using any statistical or machine learning method. TRIPOD+AI is a single 27-item checklist (52 sub-items) that supersedes the TRIPOD 2015 statement, which should no longer be used. By using this checklist, authors, editors and reviewers can systematically evaluate whether a study transparently reports the elements needed to appraise a clinical prediction model.
How the item tags work
TRIPOD+AI is standalone, so there is no separate base guideline to check alongside it. Each item carries two tags. The first records its relationship to TRIPOD 2015: a New item was introduced by TRIPOD+AI, a Modified item existed in TRIPOD 2015 but has been reworded, and a Carried-over item is unchanged. The second records applicability: Development marks an item that applies when a model is developed, and Evaluation marks one that applies when a model is evaluated. Items that apply in both situations carry both tags. For studies that both develop and evaluate a model, all items apply. The new/modified/carried-over tags, and the dashboard breakdown built on them, are an editorial interpretation added here to aid navigation; they are not part of the official statement. Because TRIPOD+AI is a single harmonised checklist, the two groups are not standards to be met independently — the combined score is the one that reflects compliance, and the breakdown only shows whether gaps lie in long-standing expectations or in those introduced by the 2024 update.
This web tool is provided for educational and review purposes only and does not constitute formal editorial, regulatory, methodological, clinical, or legal advice. Please consult the original publications for the full official guidance.
Sources and attribution
Checklist item wording is reproduced from the TRIPOD+AI statement. Explanatory summaries have been independently rewritten and condensed for educational and review purposes, drawing on the TRIPOD+AI statement and the TRIPOD 2015 Explanation & Elaboration document for inherited items. Licensing terms for each source are noted below.
1. Collins, G.S., Moons, K.G.M., Dhiman, P. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024). doi:10.1136/bmj-2023-078378. Published under CC BY 4.0 — reproduction permitted with attribution. Checklist item wording is reproduced unaltered; explanatory summaries were written for this tool.
2. Moons, K.G.M., Altman, D.G., Reitsma, J.B. et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med 162, W1–W73 (2015). doi:10.7326/M14-0698. Superseded by TRIPOD+AI. Used here as background for the rewritten explanatory summaries. Items that TRIPOD+AI carried over from TRIPOD 2015 are reproduced from the TRIPOD+AI statement, not from this document, and so share its wording in places.
This checklist is not endorsed by the original authors.
What is it for?
This tool is a web-based checklist implementing the TRIPOD+AI (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis – Artificial Intelligence) reporting guideline. Its purpose is to support the complete, accurate and transparent reporting of studies that develop or evaluate (validate) a clinical prediction model using any statistical or machine learning method. TRIPOD+AI is a single 27-item checklist (52 sub-items) that supersedes the TRIPOD 2015 statement, which should no longer be used. By using this checklist, authors, editors and reviewers can systematically evaluate whether a study transparently reports the elements needed to appraise a clinical prediction model.
How the item tags work
TRIPOD+AI is standalone, so there is no separate base guideline to check alongside it. Each item carries two tags. The first records its relationship to TRIPOD 2015: a New item was introduced by TRIPOD+AI, a Modified item existed in TRIPOD 2015 but has been reworded, and a Carried-over item is unchanged. The second records applicability: Development marks an item that applies when a model is developed, and Evaluation marks one that applies when a model is evaluated. Items that apply in both situations carry both tags. For studies that both develop and evaluate a model, all items apply. The new/modified/carried-over tags, and the dashboard breakdown built on them, are an editorial interpretation added here to aid navigation; they are not part of the official statement. Because TRIPOD+AI is a single harmonised checklist, the two groups are not standards to be met independently — the combined score is the one that reflects compliance, and the breakdown only shows whether gaps lie in long-standing expectations or in those introduced by the 2024 update.
This web tool is provided for educational and review purposes only and does not constitute formal editorial, regulatory, methodological, clinical, or legal advice. Please consult the original publications for the full official guidance.
Sources and attribution
Checklist item wording is reproduced from the TRIPOD+AI statement. Explanatory summaries have been independently rewritten and condensed for educational and review purposes, drawing on the TRIPOD+AI statement and the TRIPOD 2015 Explanation & Elaboration document for inherited items. Licensing terms for each source are noted below.
1. Collins, G.S., Moons, K.G.M., Dhiman, P. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024). doi:10.1136/bmj-2023-078378. Published under CC BY 4.0 — reproduction permitted with attribution. Checklist item wording is reproduced unaltered; explanatory summaries were written for this tool.
2. Moons, K.G.M., Altman, D.G., Reitsma, J.B. et al. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): explanation and elaboration. Ann Intern Med 162, W1–W73 (2015). doi:10.7326/M14-0698. Superseded by TRIPOD+AI. Used here as background for the rewritten explanatory summaries. Items that TRIPOD+AI carried over from TRIPOD 2015 are reproduced from the TRIPOD+AI statement, not from this document, and so share its wording in places.
This checklist is not endorsed by the original authors.
