EUVIMEDEUVIMED entdecken
Open Access

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

Takehiko Oami iD, Yohei Okada iD, Taka-Aki Nakada iD

JMIR Medical Informatics · 12.03.2025 · 13 · e64682-e64682

DOI: 10.2196/64682 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 12.03.2025. Verfasst von Takehiko Oami und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo, Chiba, 260-8677, Japan, 81 432…. Hauptthemen laut MEDLINE: Review Literature as Topic, Systematic Reviews as Topic. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 10 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Review Literature as TopicSystematic Reviews as TopicHumansAbstracting and IndexingGenerative Artificial Intelligence

Stichwörter der Autor:innen

AIGPTJapanJapaneseLLMaccuracyartificial intelligencecitation screeningcitationsclinical practice guidelinescritical careefficiencylarge language modelsreliabilityreview

Autor:innen und Institutionen

  • Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chuo, Chiba, 260-8677, Japan, 81 432262372.
  • Department of Preventive Services, Kyoto University Graduate School of Medicine, Kyoto, Japan.
  • Health Services and Systems Research, Duke-NUS Medical School, National University of Singapore, Singapore, Singapore.

ORCID-Profile: Takehiko Oami, Yohei Okada, Taka-Aki Nakada

Zitieren

APA

Oami, T., Okada, Y., & Nakada, T. A. (2025). GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews. JMIR Medical Informatics, 13, e64682-e64682. https://doi.org/10.2196/64682

Vancouver

Oami T, Okada Y, Nakada TA. GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews. JMIR Medical Informatics. 2025;13:e64682-e64682. doi:10.2196/64682

BibTeX
@article{Oami2025,
  author = {Oami, Takehiko and Okada, Yohei and Nakada, Taka-Aki},
  title = {GPT-3.5 Turbo and GPT-4 Turbo in Title and Abstract Screening for Systematic Reviews},
  journal = {JMIR Medical Informatics},
  year = {2025},
  volume = {13},
  pages = {e64682--e64682},
  doi = {10.2196/64682}
}
Kostenlos starten →