Data Extractions Using a Large Language Model (Elicit) and Human Reviewers in Randomized Controlled Trials: A Systematic Comparison
Systematic reviews are labor-intensive. Data extraction process may be facilitated by artificial intelligence tools. Use of Elicit may require a human reviewer to double-check the extracted data.
Authors
- Julian Hirt (ORCID: https://orcid.org/0000-0001-6589-3936)
- J Bianchi
- Magdalena Vogt (ORCID: https://orcid.org/0009-0002-1281-8304)
- Janine Vetsch (ORCID: https://orcid.org/0000-0002-5564-7093)
Institutions
- University of Basel (CH)
- University Hospital of Basel (CH)
- OST - Ostschweizer Fachhochschule (CH)
- University of Applied Sciences St. Gallen (CH)
- Ostschweizer Kinderspital (CH)
- Martin Luther University Halle-Wittenberg (DE)
Publication Details
- Journal
- Cochrane Evidence Synthesis and Methods
- Published
- 2025-06-08
- DOI
- https://doi.org/10.1002/cesm.70033
- Citations
- 8
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 5.23