MétaCan
Menu
Back to cohort
Record W4387144848 · doi:10.2196/48996

Automated Paper Screening for Clinical Reviews Using Large Language Models: Data Analysis Study

2023· article· en· W4387144848 on OpenAlex
Eddie Guo, Mehul Gupta, Jiawen Deng, Ye‐Jean Park, Mike Paget, Christopher Naugler

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueJournal of Medical Internet Research · 2023
Typearticle
Languageen
FieldDecision Sciences
TopicMeta-analysis and systematic reviews
Canadian institutionsUniversity of TorontoUniversity of Calgary
Fundersnot available
KeywordsComputer scienceWorkflowMachine learningPython (programming language)Artificial intelligenceNatural language processingInformation retrievalData scienceData miningDatabaseProgramming language

Abstract

fetched live from OpenAlex

BACKGROUND: The systematic review of clinical research papers is a labor-intensive and time-consuming process that often involves the screening of thousands of titles and abstracts. The accuracy and efficiency of this process are critical for the quality of the review and subsequent health care decisions. Traditional methods rely heavily on human reviewers, often requiring a significant investment of time and resources. OBJECTIVE: This study aims to assess the performance of the OpenAI generative pretrained transformer (GPT) and GPT-4 application programming interfaces (APIs) in accurately and efficiently identifying relevant titles and abstracts from real-world clinical review data sets and comparing their performance against ground truth labeling by 2 independent human reviewers. METHODS: We introduce a novel workflow using the Chat GPT and GPT-4 APIs for screening titles and abstracts in clinical reviews. A Python script was created to make calls to the API with the screening criteria in natural language and a corpus of title and abstract data sets filtered by a minimum of 2 human reviewers. We compared the performance of our model against human-reviewed papers across 6 review papers, screening over 24,000 titles and abstracts. RESULTS: -score of 0.60, a sensitivity of excluded papers of 0.91, and a sensitivity of included papers of 0.76. The interrater variability between 2 independent human screeners was κ=0.46, and the prevalence and bias-adjusted κ between our proposed methods and the consensus-based human decisions was κ=0.96. On a randomly selected subset of papers, the GPT models demonstrated the ability to provide reasoning for their decisions and corrected their initial decisions upon being asked to explain their reasoning for incorrect classifications. CONCLUSIONS: Large language models have the potential to streamline the clinical review process, save valuable time and effort for researchers, and contribute to the overall quality of clinical reviews. By prioritizing the workflow and acting as an aid rather than a replacement for researchers and reviewers, models such as GPT-4 can enhance efficiency and lead to more accurate and reliable conclusions in medical research.

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.

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)0.778
metaresearch head score (Gemma)0.333
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Scholarly communication, Open science, Insufficient payload (model declined to judge)
Consensus categoriesMetaresearch, Insufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.885
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.7780.333
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0050.003
Bibliometrics0.0020.007
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0100.002
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0150.001

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 head0.965
GPT teacher head0.755
Teacher spread0.210 · 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