MétaCan
Menu
Back to cohort
Record W4416713244 · doi:10.1016/j.jposna.2025.100294

Not Ready for Prime Time: Limitations of a Retrieval-Augmented Generation Large Language Model in Assessing Risk of Bias in Observational Studies

2025· article· en· W4416713244 on OpenAlexaboutno aff
Samuel A. Beber, Katherine D. Groff, Tyler R. Mange, Joshua T. Bram, Peter D. Fabricant

Bibliographic record

VenueJournal of the Pediatric Orthopaedic Society of North America · 2025
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsnot available
Fundersnot available
KeywordsObservational studyPrime (order theory)Identification (biology)Component (thermodynamics)Risk assessment

Abstract

fetched live from OpenAlex

Background: Current research has focused on the use of large language models (LLMs) to augment systematic reviews. LLMs are limited by their vulnerability to "hallucinations"; retrieval-augmented generation (RAG) reduces these by limiting the model's source knowledge to user-provided material. The purpose of this study was to evaluate the accuracy and reliability of a RAG-LLM in quality assessment of observational studies in pediatric orthopaedic literature as compared to manual review. Methods: Previously published systematic reviews of observational studies in pediatric orthopaedics containing reported Newcastle-Ottawa Scale (NOS) scores from our group were included. After uploading observational study source files, NotebookLM (Google, Mountain View, CA) evaluated each of the included studies using the NOS scoring sheet. Agreement among scores across all NotebookLM trials was determined using a two-way random, average measures, absolute agreement intraclass correlation coefficient [ICC(2,k)]. Agreement among individual scores generated by each NotebookLM instance (LM1, LM2, LM3, and LM4) and ground truth (published manual review score) was calculated using a two-way random, single measures, absolute agreement intraclass correlation coefficient [ICC(2,1)]. Results: Two systematic reviews comprising a total of 27 observational studies were included. ICC across all measurements (ICC(2,k)-Reviewer-LM1,2,3,4) was 0.69 (95% CI: 0.46-0.84), indicating moderate agreement. ICC comparing individual NotebookLM scores to ground truth demonstrated poor agreement [ICC(2,1) LM1-Reviewer = 0.27 (95% CI: -0.064 to 0.57), LM2-Reviewer = 0.18 (95% CI: -0.12 to 0.48), LM3-Reviewer = 0.081 (95% CI: -0.24 to 0.41), and LM4-Reviewer = 0.23 (95% CI: -0.14 to 0.55)]. Percent agreement ranged from 14.8% to 29.6%. Single measures ICCs comparing individual NotebookLM scores across multiple trials demonstrated moderate-to-poor agreement. Conclusions: NotebookLM demonstrated low reliability and accuracy in performing quality assessment of observational studies. Caution should be taken when implementing LLMs to augment research efforts in pediatric orthopaedics. Key Concepts: (1)NotebookLM (Google, Mountain View, CA) demonstrated low reliability and accuracy in performing quality assessment of observational studies.(2)Caution should be taken when implementing artificial intelligence tools such as large language models (LLMs) to augment research efforts, even retrieval-augmented generation (RAG)-LLM models that reduce hallucinations.(3)Until emerging artificial intelligence technologies are further validated it remains essential that researchers and clinicians continue to critically appraise new studies independently. Level of Evidence: IV.

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)0.792
metaresearch head score (Gemma)0.919
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (broad)
Consensus categoriesMetaresearch
DomainCandidate signal: Evaluation · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.990
Threshold uncertainty score0.257

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.7920.919
Meta-epidemiology (narrow)0.0050.004
Meta-epidemiology (broad)0.0100.021
Bibliometrics0.0160.017
Science and technology studies0.0030.009
Scholarly communication0.0130.013
Open science0.0080.012
Research integrity0.0040.005
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 head0.346
GPT teacher head0.449
Teacher spread0.104 · 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
DomainEvaluation
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

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJournal of the Pediatric Orthopaedic Society of North AmericaSame topicArtificial Intelligence in Healthcare and EducationFrench-language works237,207