MétaCan
Menu
Back to cohort
Record W4409283522 · doi:10.1136/bmjebm-2024-113066

Novel AI applications in systematic review: GPT-4 assisted data extraction, analysis, review of bias

2025· article· en· W4409283522 on OpenAlexaff
Jin K. Kim, Michael Chua, Tian Li, Mandy Rickard, Armando J. Lorenzo

Bibliographic record

VenueBMJ evidence-based medicine · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsHospital for Sick ChildrenUniversity of Toronto
Fundersnot available
KeywordsData extractionConcordanceComparabilityComputer scienceMeta-analysisSystematic reviewStatisticsData miningArtificial intelligenceMedicineMEDLINEMathematicsInternal medicineBiology

Abstract

fetched live from OpenAlex

OBJECTIVE: To assess custom GPT-4 performance in extracting and evaluating data from medical literature to assist in the systematic review (SR) process. DESIGN: A proof-of-concept comparative study was conducted to assess the accuracy and precision of custom GPT-4 models against human-performed reviews of randomised controlled trials (RCTs). SETTING: Four custom GPT-4 models were developed, each specialising in one of the following areas: (1) extraction of study characteristics, (2) extraction of outcomes, (3) extraction of bias assessment domains and (4) evaluation of risk of bias using results from the third GPT-4 model. Model outputs were compared against data from four SRs conducted by human authors. The evaluation focused on accuracy in data extraction, precision in replicating outcomes and agreement levels in risk of bias assessments. PARTICIPANTS: Among four SRs chosen, 43 studies were retrieved for data extraction evaluation. Additionally, 17 RCTs were selected for comparison of risk of bias assessments, where both human comparator SRs and an analogous SR provided assessments for comparison. INTERVENTION: Custom GPT-4 models were deployed to extract data and evaluate risk of bias from selected studies, and their outputs were compared to those generated by human reviewers. MAIN OUTCOME MEASURES: Concordance rates between GPT-4 outputs and human-performed SRs in data extraction, effect size comparability and inter/intra-rater agreement in risk of bias assessments. RESULTS: When comparing the automatically extracted data to the first table of study characteristics from the published review, GPT-4 showed 88.6% concordance with the original review, with <5% discrepancies due to inaccuracies or omissions. It exceeded human accuracy in 2.5% of instances. Study outcomes were extracted and pooling of results showed comparable effect sizes to comparator SRs. A review of bias assessment using GPT-4 showed fair-moderate but significant intra-rater agreement (ICC=0.518, p<0.001) and inter-rater agreements between human comparator SR (weighted kappa=0.237) and the analogous SR (weighted kappa=0.296). In contrast, there was a poor agreement between the two human-performed SRs (weighted kappa=0.094). CONCLUSION: Customized GPT-4 models perform well in extracting precise data from medical literature with potential for utilization in review of bias. While the evaluated tasks are simpler than the broader range of SR methodologies, they provide an important initial assessment of GPT-4's capabilities.

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
gemmaMetaresearch
Domain: Methods · Genre: Empirical
About the Canadian research system: no · About a Canadian topic: no
Simulation or modelinglow
gptMetaresearch
Domain: Methods · Genre: Methods
About the Canadian research system: no · About a Canadian topic: no
Systematic reviewmedium
models splitAgreement 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)0.307
metaresearch head score (Gemma)0.458
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Bibliometrics, Insufficient payload (model declined to judge)
Consensus categoriesMetaresearch
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Systematic review · Consensus signal: Systematic review
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.302
Threshold uncertainty score0.999

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.3070.458
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0120.002
Bibliometrics0.0020.022
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0050.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0060.000

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 head0.842
GPT teacher head0.631
Teacher spread0.211 · 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.

Metaresearch

The models disagree on parts of this classification; every voice is preserved in the section at the end of the page.

Study designSimulation or modeling · Systematic review
DomainMethods
GenreEmpirical · Methods

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

Citations7
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueBMJ evidence-based medicineSame topicMeta-analysis and systematic reviewsCategoryMetaresearchFrench-language works237,207