MétaCan
Menu
Back to cohort
Record W3118650257 · doi:10.1186/s13063-020-04951-6

Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines

2021· letter· en· W3118650257 on OpenAlexaff
Hussein Ibrahim, Xiaoxuan Liu, Samantha Cruz Rivera, David Moher, An‐Wen Chan, Matthew R. Sydes, Melanie Calvert, Alastair K. Denniston

Bibliographic record

VenueTrials · 2021
Typeletter
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsWomen's College HospitalUniversity of TorontoOttawa HospitalUniversity of Ottawa
FundersMoorfields Eye Hospital NHS Foundation TrustUniversity College LondonNational Institute for Health and Care ResearchUniversity Hospitals Birmingham NHS Foundation TrustAlan Turing InstituteWellcome TrustMedical Research CouncilWellcome
KeywordsPsychological interventionMedicineConsolidated Standards of Reporting TrialsTransparency (behavior)Multidisciplinary approachClinical trialHealth careAlternative medicineMedical educationArtificial intelligenceManagement scienceComputer scienceNursingPathology

Abstract

fetched live from OpenAlex

BACKGROUND: The application of artificial intelligence (AI) in healthcare is an area of immense interest. The high profile of 'AI in health' means that there are unusually strong drivers to accelerate the introduction and implementation of innovative AI interventions, which may not be supported by the available evidence, and for which the usual systems of appraisal may not yet be sufficient. MAIN TEXT: We are beginning to see the emergence of randomised clinical trials evaluating AI interventions in real-world settings. It is imperative that these studies are conducted and reported to the highest standards to enable effective evaluation because they will potentially be a key part of the evidence that is used when deciding whether an AI intervention is sufficiently safe and effective to be approved and commissioned. Minimum reporting guidelines for clinical trial protocols and reports have been instrumental in improving the quality of clinical trials and promoting completeness and transparency of reporting for the evaluation of new health interventions. The current guidelines-SPIRIT and CONSORT-are suited to traditional health interventions but research has revealed that they do not adequately address potential sources of bias specific to AI systems. Examples of elements that require specific reporting include algorithm version and the procedure for acquiring input data. In response, the SPIRIT-AI and CONSORT-AI guidelines were developed by a multidisciplinary group of international experts using a consensus building methodological process. The extensions include a number of new items that should be reported in addition to the core items. Each item, where possible, was informed by challenges identified in existing studies of AI systems in health settings. CONCLUSION: The SPIRIT-AI and CONSORT-AI guidelines provide the first international standards for clinical trials of AI systems. The guidelines are designed to ensure complete and transparent reporting of clinical trial protocols and reports involving AI interventions and have the potential to improve the quality of these clinical trials through improvements in their design and delivery. Their use will help to efficiently identify the safest and most effective AI interventions and commission them with confidence for the benefit of patients and the public.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.548
metaresearch head score (Gemma)0.763
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Reporting · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.452
Threshold uncertainty score0.557

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.5480.763
Meta-epidemiology (narrow)0.0090.009
Meta-epidemiology (broad)0.0200.033
Bibliometrics0.0230.025
Science and technology studies0.0060.016
Scholarly communication0.0190.011
Open science0.0190.011
Research integrity0.0260.039
Insufficient payload (model declined to judge)0.0200.021

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.959
GPT teacher head0.734
Teacher spread0.225 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; the direct Gemma label and the distilled Codex classifier agree on what is shown here.

Study designNot applicable
DomainReporting
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations153
Published2021
Admission routes1
Has abstractyes

Explore more

Same venueTrialsSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207