MétaCan
Menu
Back to cohort
Record W4407873728 · doi:10.7326/annals-24-02189

Development of Prompt Templates for Large Language Model–Driven Screening in Systematic Reviews

2025· article· en· W4407873728 on OpenAlexaff
Christian Cao, Jason C. Sang, Rohit Arora, David Chen, Robert Kloosterman, Milena Cecere, Jaswanth Gorla, Richard Saleh, Ian R. Drennan, Bijan Teja, Michael G. Fehlings, Paul E. Ronksley, Alexander A. C. Leung, Dany E. Weisz, Mairead Whelan, D. B. Emerson, Rahul K. Arora, Niklas Bobrovitz

Bibliographic record

VenueAnnals of Internal Medicine · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsSouth Health CampusVector InstituteHealth Sciences CentreSunnybrook Health Science CentreUniversity of TorontoSt. Michael's HospitalUniversity of Calgary
Fundersnot available
KeywordsMedicineSystematic reviewTemplateIntensive care medicineMEDLINEMedical physicsProgramming languageComputer science

Abstract

fetched live from OpenAlex

BACKGROUND: Systematic reviews (SRs) are hindered by the initial rigorous article screen, which delays access to reliable information synthesis. OBJECTIVE: To develop generic prompt templates for large language model (LLM)-driven abstract and full-text screening that can be adapted to different reviews. DESIGN: Diagnostic test accuracy. SETTING: 48 425 citations were tested for abstract screening across 10 SRs. Full-text screening evaluated all 12 690 freely available articles from the original search. Prompt development used the GPT4-0125-preview model (OpenAI). PARTICIPANTS: None. MEASUREMENTS: Large language models were prompted to include or exclude articles based on SR eligibility criteria. Model outputs were compared with original SR author decisions after full-text screening to evaluate performance (accuracy, sensitivity, and specificity). RESULTS: Optimized prompts using GPT4-0125-preview achieved a weighted sensitivity of 97.7% (range, 86.7% to 100%) and specificity of 85.2% (range, 68.3% to 95.9%) in abstract screening and weighted sensitivity of 96.5% (range, 89.7% to 100.0%) and specificity of 91.2% (range, 80.7% to 100%) in full-text screening across 10 SRs. In contrast, zero-shot prompts had poor sensitivity (49.0% abstract, 49.1% full-text). Across LLMs, Claude-3.5 (Anthropic) and GPT4 variants had similar performance, whereas Gemini Pro (Google) and GPT3.5 (OpenAI) models underperformed. Direct screening costs for 10 000 citations differed substantially: Where single human abstract screening was estimated to require more than 83 hours and $1666.67 USD, our LLM-based approach completed screening in under 1 day for $157.02 USD. LIMITATIONS: Further prompt optimizations may exist. Retrospective study. Convenience sample of SRs. Full-text screening evaluations were limited to free PubMed Central full-text articles. CONCLUSION: A generic prompt for abstract and full-text screening achieving high sensitivity and specificity that can be adapted to other SRs and LLMs was developed. Our prompting innovations may have value to SR investigators and researchers conducting similar criteria-based tasks across the medical sciences. PRIMARY FUNDING SOURCE: 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)0.251
metaresearch head score (Gemma)0.587
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: Methods · Consensus signal: Methods
Teacher disagreement score0.749
Threshold uncertainty score0.924

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.2510.587
Meta-epidemiology (narrow)0.0040.004
Meta-epidemiology (broad)0.0040.009
Bibliometrics0.0130.009
Science and technology studies0.0010.001
Scholarly communication0.0060.007
Open science0.0040.008
Research integrity0.0030.003
Insufficient payload (model declined to judge)0.0210.007

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 head0.374
GPT teacher head0.529
Teacher spread0.155 · 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
GenreMethods

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

Citations36
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueAnnals of Internal MedicineSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207