MétaCan
Menu
← Back to cohort
Record W4413729242 · doi:10.1136/bmjopen-2025-100411

Disparity between statistical significance and clinical importance in published randomised controlled trials: a methodological study

2025· article· en· W4413729242 on OpenAlexaff
Tonya M. Esterhuizen, Lawrence Mbuagbaw, Nadia Rehman, Nathan Yanwou, Devron J Swaby, Esme Kittle, Lehana Thabane

Bibliographic record

VenueBMJ Open · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsHamilton Health SciencesMcMaster UniversityMcGill University Health CentreSt. Joseph’s Healthcare HamiltonMcGill UniversityImpact
FundersFogarty International Center
KeywordsMedicineSample size determinationConfidence intervalClinical trialStatistical significanceMultinomial logistic regressionLogistic regressionMeta-analysisPsychological interventionClinical significanceRandomized controlled trialInternal medicineStatistics

Abstract

fetched live from OpenAlex

OBJECTIVES: We estimated the extent of the disparity between statistical significance and clinical importance in published randomised controlled trials (RCTs), and explored factors associated with this disparity. DESIGN: A methodological study of trials published between 2018 and 2022 and indexed in PubMed was conducted. Primary reports of two-arm, phase three, superiority trials of human health interventions were included. Pharmacokinetic studies and pilot trials were excluded. The relationship between the specified delta value or minimum clinically important difference (as specified in the sample size calculation) and the effect size determined the clinical importance of the trial results. Studies where the clinical importance was at least possible, with no statistical significance, were classified as SS-CI+ disparity, and studies which were definitely not clinically important but statistically significant were classified as SS+CI- disparity. Factors associated with each type of disparity were explored at the study level using multinomial logistic regression. RESULTS: 500 trials were included. In 38.4% (n=192) of these, information was not available to classify clinical importance. Overall disparity was found in 63 of the remaining 308 studies, 20.5% (95% confidence interval (CI) 16.2% to 25.5%). SS+CI- disparity was 10.3% (15/145) (95% CI 6.1% to 16.8%) and SS-CI+ disparity was 29.5% (48/163) (95% CI 22.7% to 37.2%).Studies testing complementary or alternative medicines relative to drug trials were positively associated with SS+CI- disparity. Low journal impact factor, small sample size, unfunded or grant funding and failure to mention allocation concealment were positively associated with SS-CI+disparity. CONCLUSIONS: In up to 20% of RCTs, there may be a disparity between statistical significance and clinical importance. Clinical importance of results should be taken into account in the interpretation of trial results, and trials should adhere stringently to reporting guidelines.

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)0.707
metaresearch head score (Gemma)0.879
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (broad)
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: Methods
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.992
Threshold uncertainty score0.362

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.7070.879
Meta-epidemiology (narrow)0.0020.003
Meta-epidemiology (broad)0.0080.018
Bibliometrics0.0220.023
Science and technology studies0.0020.010
Scholarly communication0.0080.012
Open science0.0050.011
Research integrity0.0050.005
Insufficient payload (model declined to judge)0.0040.000

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 head0.933
GPT teacher head0.716
Teacher spread0.217 · 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 designObservational
DomainMethods
GenreEmpirical

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

Citations5
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueBMJ Open→Same topicMeta-analysis and systematic reviews→French-language works237,207→