⌘+K

Pulse Explore Clubs Researchers Journals

Home Clubs Explore

May 20, 2024Annals of Internal Medicine

Sensitivity and Specificity of Using GPT-3.5 Turbo Models for Title and Abstract Screening in Systematic Reviews and Meta-analyses

Viet-Thi Tran Gerald Gartlehner Sally Yaacoub Isabelle Boutron Lukas Schwingshackl Julia Stadelmaier Isolde Sommer Farzaneh Alebouyeh Sivem Afach Joerg J Meerpohl Philippe Ravaud

View Full Paper

Ask AI

Bookmark

Share

No abstract yet

We only have this paper's title and publication details.

Read it at the source→

Abstract

Systematic reviews are performed manually despite the exponential growth of scientific literature.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Tran et al. (2024) studied this question.

synapsesocial.com/papers/68e6936db6db64358761a3f7 https://doi.org/10.7326/m23-3389

View Full Paper

Ask AI

Bookmark

Share

Keep reading

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Human-Comparable Sensitivity of Large Language Models in Identifying Eligible Studies Through Title and Abstract Screening: 3-Layer Strategy Using GPT-3.5 and GPT-4 for Systematic Reviews2024 · 47 citations
2Evaluating the Efficacy of Large Language Models for Systematic Review and Meta-Analysis Screening2024 · 8 citations
3GPT API Models Can Function as Highly Reliable Second Screeners of Titles and Abstracts in Systematic Reviews2024 · 2 citations
4A comparative study of screening performance between abstrackr and GPT models: Systematic review and contextual analysis2025 · 6 citations
5Can large language models replace humans in systematic reviews? Evaluating <scp>GPT</scp>‐4's efficacy in screening and extracting data from peer‐reviewed and grey literature in multiple languages2024 · 256 citations