MétaCan
Menu
Back to cohort
Record W4399280155 · doi:10.1101/2024.06.01.24308323

Prompting is all you need: LLMs for systematic review screening

2024· preprint· en· W4399280155 on OpenAlexaff
Christian Cao, Jason C. Sang, Rohit Arora, Robbie Kloosterman, Matt Cecere, Jaswanth Gorla, Richard Saleh, David Chen, 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

VenuemedRxiv · 2024
Typepreprint
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsHealth Sciences CentreUniversity of CalgarySunnybrook Health Science CentreVector InstituteSouth Health CampusUniversity of Toronto
Fundersnot available
KeywordsMedicine

Abstract

fetched live from OpenAlex

Abstract Systematic reviews (SRs) are the highest standard of evidence, shaping clinical practice guidelines, policy decisions, and research priorities. However, their labor-intensive nature, including an initial rigorous article screen by at least two investigators, delays access to reliable information synthesis. Here, we demonstrate that large language models (LLMs) with intentional prompting can match human screening performance. We introduce Framework Chain-of-Thought, a novel prompting approach that directs LLMs to systematically reason against predefined frameworks. We evaluated our prompts across ten SRs covering four common types of SR questions (i.e., prevalence, intervention benefits, diagnostic test accuracy, prognosis), achieving a mean accuracy of 93.6% (range: 83.3-99.6%) and sensitivity of 97.5% (89.7-100%) in full-text screening. Compared to experienced reviewers (mean accuracy 92.4% [76.8-97.8%], mean sensitivity 75.1% [44.1-100%]), our full-text prompt demonstrated significantly higher sensitivity in four reviews (p<0.05), significantly higher accuracy in one review (p<0.05), and comparable accuracy in two of five reviews (p>0.05). While traditional human screening for an SR of 7000 articles required 530 hours and $10,000 USD, our approach completed screening in one day for $430 USD. Our results establish that LLMs can perform SR screening with performance matching human experts, setting the foundation for end-to-end automated SRs.

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 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)0.254
metaresearch head score (Gemma)0.094
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow), Scholarly communication, Insufficient payload (model declined to judge)
Consensus categoriesMetaresearch, Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Systematic review · Consensus signal: Systematic review
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.734
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.2540.094
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0140.008
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0030.000
Open science0.0050.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0040.008

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 head0.742
GPT teacher head0.543
Teacher spread0.199 · 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; both teacher heads agree on what is shown here.

Study designSystematic review
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

Citations16
Published2024
Admission routes1
Has abstractyes

Explore more

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