go-v.orgdoi

GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews

Takehiko Oami, Yohei Okada, Taka‐aki Nakada · JMIR Medical Informatics · 2025

  • DOI 10.2196/64682
  • Publisher JMIR Publications
  • Type review
  • Issued 2025

Not cached yet. This record was fetched live for this request and is stored after the lookup. Reopening the page should serve the cached copy.

JMIR Medical Informatics · JMIR Publications · review · 2025

Abstract

Unlabelled: This study demonstrated that while GPT-4 Turbo had superior specificity when compared to GPT-3.5 Turbo (0.98 vs 0.51), as well as comparable sensitivity (0.85 vs 0.83), GPT-3.5 Turbo processed 100 studies faster (0.9 min vs 1.6 min) in citation screening for systematic reviews, suggesting that GPT-4 Turbo may be more suitable due to its higher specificity and highlighting the potential of large language models in optimizing literature selection.

Open the resolved locator · 10.2196/64682

Metadata licence: OpenAlex metadata (CC0)

Registry
OpenAlex DOI index + API
Fetched
2026-11-20 04:32 UTC
Cache state
not cached yet (bulk-index+openalex)
Locator
https://medinform.jmir.org/2025/1/e64682
Metadata licence
OpenAlex metadata (CC0)
Scope
Metadata as returned by the resolver; abstracts are never generated here.