MétaCan
Menu
Back to cohort
Record W3043263805 · doi:10.1002/jrsm.1432

Performance of model‐based network meta‐analysis (MBNMA) of time‐course relationships: A simulation study

2020· article· en· W3043263805 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.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueResearch Synthesis Methods · 2020
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsnot available
FundersMedical Research CouncilPfizer UKMedical Research Council CanadaDepartment of Health and Social CareUniversity of BristolNational Institute for Health and Care ResearchUniversity Hospitals Bristol NHS Foundation TrustPfizer
KeywordsPoolingTime pointRobustness (evolution)Computer scienceEconometricsStatisticsCorrelationCovarianceRandom effects modelMeta-analysisMathematicsArtificial intelligence

Abstract

fetched live from OpenAlex

Time-course model-based network meta-analysis (MBNMA) has been proposed as a framework to combine treatment comparisons from a network of randomized controlled trials reporting outcomes at multiple time-points. This can explain heterogeneity/inconsistency that arises by pooling studies with different follow-up times and allow inclusion of studies from earlier in drug development. The aim of this study is to explore using simulation: (a) how MBNMA model parameters are affected by the quantity/location of observed time-points across studies/comparisons, (b) how reliably an appropriate MBNMA model can be identified, (c) the robustness of model estimates and predictions under different dataset characteristics. Our results indicate that model parameters for a given treatment comparison are estimated with low mean bias even when no direct evidence was available, provided there was sufficient indirect evidence to estimate the time-course. A staged model selection strategy that selects time-course function, then heterogeneity, then covariance structure, identified the true model most reliably and efficiently. Predictions and parameter estimates from selected models had low mean bias even in the presence of high heterogeneity/correlation between time-points. However, failure to properly account for heterogeneity/correlation could lead to high error in precision of the estimates. Time-course MBNMA provides a statistically robust framework for synthesizing direct and indirect evidence to estimate relative effects and predicted mean responses whilst accounting for time-course and incorporating correlation and heterogeneity. This supports the use of MBNMA in evidence synthesis, particularly when additional studies are available with follow-up times that would otherwise prohibit their inclusion by conventional meta-analysis.

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)0.491
metaresearch head score (Gemma)0.189
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Insufficient payload (model declined to judge)
Consensus categoriesMetaresearch
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.631
Threshold uncertainty score0.992

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.4910.189
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0070.004
Bibliometrics0.0010.013
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0020.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0090.000

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 head0.963
GPT teacher head0.695
Teacher spread0.267 · 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