Cited by 66Artificial Intelligence in Healthcare and EducationMeta-analysis and systematic reviewsAcademic Writing and Publishing

AI Reporting Guidelines: How to Select the Best One for Your Research

Open access
Klontzas, Michail E., Gatti, Anthony A., Tejani, Ali S., Kahn, Charles E.·2023·Radiology: Artificial Intelligence

Abstract

T he rapid increase in publications related to artificial intelligence (AI) in medical imaging has pinpointed the need for transparent and organized research reporting.Publications on AI research should provide the necessary information to ensure adherence to high scientific standards while allowing the independent reproduction of the research.Reproducibility is necessary to enable clinical translation and adoption of AI algorithms that may otherwise remain on paper.For this purpose, a series of tools have been developed to guide the comprehensive reporting of AI research to promote research reproducibility, adherence to ethical standards, comprehensibility of research manuscripts, and publication of scientifically valid results.The use of such guidelines has been encouraged or mandated by scientific journals to allow appropriate evaluation of research output during the review process.The majority of existing guidelines and checklists allow authors to confirm the inclusion of specific information in each manuscript section: Title, Abstract, Introduction, Methods, Results, and Discussion.The content of these checklists highlights the minimum information a journal requires for the publication of an AI study, providing researchers with guidelines to conduct their research while also easing and standardizing the review process.Existing guidelines or guidelines under development specific to AI include CLAIM (Checklist for Artificial Intelligence in Medical Imaging), STARD-AI (Standards for Reporting of Diagnostic Accuracy Study-AI), CONSORT-AI (Consolidated Standards of Reporting Trials-AI), SPIRIT-AI (Standard Protocol Items: Recommendations for Interventional Trials-AI), FUTURE-AI (Fairness Universality Traceability Usability Robustness Explainability-AI), MI-CLAIM (Minimum Information about Clinical Artificial Intelligence Modeling), MINIMAR (Minimum Information for Medical AI Reporting), and RQS (Radiomics Quality Score).In this editorial, we compare these guidelines and their content to help readers find the best guideline for their research.Table 1 provides a high-level overview including a summary of guidelines' availability, purpose, and format and brief information about which manuscript sections they address.Table 2 details specific content for each manuscript section and indicates which checklists include this information.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1148/ryai.230055

Cites

3 of 3 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

Self-check

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

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Klontzas, M. E., Gatti, A. A., Tejani, A. S., & Kahn, C. E.
Affiliations
University of Crete (GR)
Venue
Radiology: Artificial Intelligence
Published
2023-05-01
Volume
5
Issue
3
Pages
e230055-e230055
ISSN
2638-6100 (ISSN-L)
OpenAlex
W4362606820
Cited by
66
References
3
Citations by year
2026: 11 · 2025: 23 · 2024: 21 · 2023: 11
Type
journal article
Language
en
Open access
Locations
  • Radiology Artificial Intelligence (publishedVersion)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Social Sciences › Arts and Humanities › History and Philosophy of Science › Academic Writing and Publishing
Keywords
artificial intelligence in medical imaging, reporting guidelines, reproducibility, CONSORT-AI, radiomics quality score

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.

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