MétaCan
Menu
Back to cohort
Record W4321018817 · doi:10.1212/wnl.0000000000207078

An Introduction to Individual Participant Data Meta-analysis

2023· review· en· W4321018817 on OpenAlexaff
Areti Angeliki Veroniki, Georgios Seitidis, Georgios Tsivgoulis, Aristeidis H. Katsanos, Dimitris Mavridis

Bibliographic record

VenueNeurology · 2023
Typereview
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsSt. Michael's Hospital
FundersEuropean Commission
KeywordsCovariateMeta-analysisThrombolysisConfoundingMedicineMissing dataRandomized controlled trialIntervention (counseling)Aggregate dataOutlierStroke (engine)Subgroup analysisStandardizationComputer scienceArtificial intelligenceSurgeryInternal medicineMachine learningMyocardial infarctionPsychiatryPathology

Abstract

fetched live from OpenAlex

Meta-analysis using individual participant data (IPD-MA) from randomized controlled trials (RCTs) can strengthen evidence used for decision making and is considered the "gold standard" approach. In this study, we present the importance, properties, and main approaches of conducting an IPD-MA. We exemplify the main approaches of conducting an IPD-MA and how these can be used to obtain subgroup effects through estimation of interaction terms. IPD-MA has several benefits over traditional aggregate data (AD) meta-analysis. These include standardization of definitions of outcomes and/or scales, reanalysis of eligible RCTs using the same analysis model across all studies, accounting for missing outcome data, detecting outliers, using participant-level covariates to explore intervention-by-covariate interactions, and tailoring intervention effects to participant characteristics. IPD-MA can be performed in either a 2-stage or 1-stage approach. We exemplify the presented methods using 2 illustrative examples. The first real-life example includes 6 studies assessing sonothrombolysis with or without addition of microspheres against IV thrombolysis alone (i.e., control) in acute ischemic stroke participants with large vessel occlusions. The second real-life example includes 7 studies evaluating the association between blood pressure levels after endovascular thrombectomy and functional improvement of acute ischemic stroke in patients with large vessel occlusion. IPD reviews can be associated with higher quality statistical analysis and may differ from AD reviews. Unlike individual trials that lack power and AD meta-analysis results, which suffer from confounding and aggregation bias, the use of IPD allows us to explore intervention-by-covariate interactions. However, a key limitation of conducting an IPD-MA is retrieval of IPD from original RCTs. Time and resources should be carefully planned before embarking on retrieving IPD.

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

Direct model labels (unvalidated)

Per-model category and study-design labels from the labeling rounds. They are machine output, unvalidated, and the disagreement between models ships as data. No study design here is MEDLINE-validated yet.

Model armCategoriesStudy designConfidence
gemmano category
Domain: not available · Genre: Review
About the Canadian research system: no · About a Canadian topic: no
Not applicablelow
gptno category
Domain: not available · Genre: Review
About the Canadian research system: no · About a Canadian topic: no
Not applicablelow
models agreeAgreement compares identical category sets and study designs across arms.

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)0.187
metaresearch head score (Gemma)0.042
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Meta-epidemiology (broad), Scholarly communication, Open science, Insufficient payload (model declined to judge)
Consensus categoriesMetaresearch, Meta-epidemiology (broad), Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Meta-analysis · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.336
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.1870.042
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0350.013
Bibliometrics0.0030.011
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0130.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0250.030

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 head0.974
GPT teacher head0.653
Teacher spread0.321 · 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

Labeled directly by 2 models reading the full record.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

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

Citations33
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueNeurologySame topicMeta-analysis and systematic reviewsFrench-language works237,207