Using large language models to directly screen electronic databases as an alternative to traditional search strategies such as the Cochrane highly sensitive search for filtering randomized controlled trials in systematic reviews
Research Synthesis Methods · 2025-11 · 16 (6) · 1035-1041
DOI: 10.1017/rsm.2025.10034 ↗Kurz gefasst
Fachartikel in der Zeitschrift Research Synthesis Methods, online erschienen am 10.10.2025. Verfasst von Viet-Thi Tran und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Research in Epidemiology and Statistics (CRESS), https://ror.org/05f82e368Université Paris Cité and Université Sorbonne Paris Nord, INSERM…. Hauptthemen laut MEDLINE: Databases, Bibliographic, Large Language Models, Randomized Controlled Trials as Topic, Systematic Reviews as Topic. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 10 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A critical step in systematic reviews involves the definition of a search strategy, with keywords and Boolean logic, to filter electronic databases. We hypothesize that it is possible to screen articles in electronic databases using large language models (LLMs) as an alternative to search equations. To investigate this matter, we compared two methods to identify randomized controlled trials (RCTs) in electronic databases: filtering databases using the Cochrane highly sensitive search and an assessment by an LLM. We retrieved studies indexed in PubMed with a publication date between September 1 and September 30, 2024 using the sole keyword “diabetes.” We compared the performance of the Cochrane highly sensitive search and the assessment of all titles and abstracts extracted directly from the database by GPT-4o-mini to identify RCTs. Reference standard was the manual screening of retrieved articles by two independent reviewers. The search retrieved 6377 records, of which 210 (3.5%) were primary reports of RCTs. The Cochrane highly sensitive search filtered 2197 records and missed one RCT (sensitivity 99.5%, 95% CI 97.4% to100%; specificity 67.8%, 95% CI 66.6% to 68.9%). Assessment of all titles and abstracts from the electronic database by GPT filtered 1080 records and included all 210 primary reports of RCTs (sensitivity 100%, 95% CI 98.3% to100%; specificity 85.9%, 95% CI 85.0% to 86.8%). LLMs can screen all articles in electronic databases to identify RCTs as an alternative to the Cochrane highly sensitive search. This calls for the evaluation of LLMs as an alternative to rigid search strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Center for Research in Epidemiology and Statistics (CRESS), https://ror.org/05f82e368Université Paris Cité and Université Sorbonne Paris Nord, INSERM, INRAE, Paris, France.
- Centre d'Epidemiologie Clinique, AP-HP, Hôpital Hôtel Dieu, Paris, France.
- Centre Cochrane France, Paris, France.
- Department of Epidemiology, Mailman School of Public Health, Columbia University, New York, NY, USA.
Zitieren
APA
Tran, V. T., Grana Possamai, C., Boutron, I., & Ravaud, P. (2025). Using large language models to directly screen electronic databases as an alternative to traditional search strategies such as the Cochrane highly sensitive search for filtering randomized controlled trials in systematic reviews. Research Synthesis Methods, 16(6), 1035-1041. https://doi.org/10.1017/rsm.2025.10034
Vancouver
Tran VT, Grana Possamai C, Boutron I, Ravaud P. Using large language models to directly screen electronic databases as an alternative to traditional search strategies such as the Cochrane highly sensitive search for filtering randomized controlled trials in systematic reviews. Research Synthesis Methods. 2025;16(6):1035-1041. doi:10.1017/rsm.2025.10034
BibTeX
@article{Tran2025,
author = {Tran, Viet-Thi and Grana Possamai, Carolina and Boutron, Isabelle and Ravaud, Philippe},
title = {Using large language models to directly screen electronic databases as an alternative to traditional search strategies such as the Cochrane highly sensitive search for filtering randomized controlled trials in systematic reviews},
journal = {Research Synthesis Methods},
year = {2025},
volume = {16},
number = {6},
pages = {1035--1041},
doi = {10.1017/rsm.2025.10034}
}
EUVIMED