MétaCan
Menu
Back to cohort

Enhancing search strategies for systematic reviews on drug Harms: An evaluation of the utility of ChatGPT in error detection and keyword generation

2025· article· en· W4410800786 on OpenAlexaff
Victor Gitman, Colleen J. Maxwell, John‐Michael Gamble

Bibliographic record

VenueComputers in Biology and Medicine · 2025
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsComputer scienceDrugInformation retrievalData miningMachine learningRisk analysis (engineering)MedicinePharmacology

Abstract

fetched live from OpenAlex

Developing search strategies for synthesizing evidence on drug harms requires specialized expertise and knowledge. The aim of this study was to evaluate ChatGPT's ability to enhance search strategies for systematic reviews of drug harms by identifying missing and generating omitted keywords. A literature search in PubMed identified systematic reviews of drug harms from 10 high-impact journals between 1-Nov-2013 to 27-Nov-2023. Sixteen search strategies used in these reviews were selected each with a single error of omission introduced. ChatGPT's (GPT-4) performance was evaluated based on error detection, similarity between the extracted and generated search strategies via strict and semantic keyword matching, and proportion of omitted keywords generated. ChatGPT identified the introduced errors in all search strategies. Under strict matching, the mean Jaccard's similarity measure was 0.17 (range: 0.00–0.52) and with semantic matching this increased to 0.23 (range: 0.00–0.53). Similarly, the mean proportion of keywords recreated by ChatGPT was 49 % using strict matching increasing to 71 % with semantic matching. ChatGPT effectively detected errors and generated relevant keywords, showing potential as a tool for evidence retrieval on drug harms. • ChatGPT was tested on its ability to enhance search strategies for systematic reviews of drug harms. • ChatGPT was able to identify intentional errors introduced into search strategies with high sensitivity. • ChatGPT generated relevant keywords, showing potential to enhance the efficiency and quality of systematic reviews on drug harms.

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)0.230
metaresearch head score (Gemma)0.588
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.770
Threshold uncertainty score0.949

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.2300.588
Meta-epidemiology (narrow)0.0040.002
Meta-epidemiology (broad)0.0060.007
Bibliometrics0.0230.016
Science and technology studies0.0010.001
Scholarly communication0.0040.008
Open science0.0030.010
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0050.001

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 head0.677
GPT teacher head0.577
Teacher spread0.100 · 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 designBench or experimental
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

Citations3
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueComputers in Biology and MedicineSame topicMeta-analysis and systematic reviewsFrench-language works237,207