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 OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.125
metaresearch head score (Gemma)0.726
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesMetaresearch
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: Not applicable
GenreCandidate signal: Commentary · Consensus signal: Commentary
Teacher disagreement score0.600
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.1250.726
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0050.003
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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