MétaCan
Menu
← Back to cohort
Record W4391873644 · doi:10.1093/jcag/gwad061.105

A105 PILOT STUDY ON THE ACCURACY OF CHATGPT IN ARTICLE SCREENING FOR SYSTEMATIC REVIEWS IN GASTROENTEROLOGY

2024· article· en· W4391873644 on OpenAlexaff
C. Na, G Sinanian, Nikko Gimpaya, A Mokhtar, Deepak Chopra, Michael A. Scaffidi, E. Yeung, Samir C. Grover

Bibliographic record

VenueJournal of the Canadian Association of Gastroenterology · 2024
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsThe Scarborough HospitalQueen's UniversitySt. Michael's Hospital
Fundersnot available
KeywordsSystematic reviewMedicineMedical physicsInternal medicineGastroenterologyMEDLINEChemistryBiochemistry

Abstract

fetched live from OpenAlex

Abstract Background Systematic reviews synthesize extant research to answer a research question in a way that minimizes bias. After articles for potential inclusion are identified by sensitive searches, screening requires human expert review, which may be time-consuming and subjective. Large language models such as ChatGPT may have potential for this application. Aims This pilot study aims to assess the accuracy of ChatGPT 3.5 in screening of articles for systematic reviews in gastroenterology by (1) identifying if articles were correctly included and (2) excluding articles reported by authors as difficult to assess. Methods We searched the Cochrane Library for gastroenterology systematic reviews (January 1, 2022 to May 31, 2023) and selected the 10 most cited studies. The test set used to determine the accuracy of Open AI’s ChatGPT 3.5 model for included studies was the final list of included studies for each Cochrane review. The test set used for studies challenging to assess was the “excluded studies” list as defined in the Cochrane Handbook. Figure 1 shows the prompt used for the screening query. Articles were omitted if they did not have digital sources, abstracts or methods. Each article was screened 10 times to account for variability within ChatGPT’s outputs. Articles with ≥5 inclusion results were counted as an included study. Results ChatGPT correctly identified included studies at rates ranging from 60% to 100%. ChatGPT correctly identified exlcuded studies at rates ranging from 0% to 50% (Table 1). A total of 265 articles were screened. Conclusions In this pilot study, we demonstrated that ChatGPT is accurate in identifying articles screened for inclusion in Cochrane reviews; however, it is inaccurate in excluding articles described by the authors as being difficult to assess. We hypothesize that the GPT 3.5 model can read for keywords and broad interventions but is unable to reason cognitively, as an expert would, as to why a study may be excluded. We aim to review reasons for exclusion in future work. Table 1. Screening Results of ChatGPT Figure 1. ChatGPT Screening Prompt Funding Agencies None

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)0.569
metaresearch head score (Gemma)0.879
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesMetaresearch
DomainCandidate signal: Methods · Consensus signal: Methods
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.431
Threshold uncertainty score0.532

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.5690.879
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0030.009
Bibliometrics0.0070.010
Science and technology studies0.0020.003
Scholarly communication0.0060.011
Open science0.0030.007
Research integrity0.0040.003
Insufficient payload (model declined to judge)0.0060.001

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 head0.417
GPT teacher head0.446
Teacher spread0.029 · 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 designSimulation or modeling
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

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueJournal of the Canadian Association of Gastroenterology→Same topicMeta-analysis and systematic reviews→French-language works237,207→