Enhancing Evidence Synthesis Efficiency: Leveraging Large Language Models and Agentic Workflows for Optimized Literature Screening
The GREP-Agent shows promise in improving the efficiency and effectiveness of evidence synthesis in dynamic public health contexts. Further development and refinement of adaptable human-in-the-loop AI systems for screening literature are essential to support future public health response activities, while maintaining a human-centric approach.
Authors
- Stéphanie Brazeau
- Tricia Corrin (ORCID: https://orcid.org/0000-0001-5514-1589)
- Bing Hu (ORCID: https://orcid.org/0009-0006-2913-6659)
- Andre Henriques (ORCID: https://orcid.org/0000-0003-1521-3423)
- Lisa Waddell (ORCID: https://orcid.org/0000-0003-4887-5124)
- Alice Simniceanu (ORCID: https://orcid.org/0000-0003-4068-6177)
- Kusala Pussegoda (ORCID: https://orcid.org/0009-0007-8383-827X)
- Elias Sandner
- Andreas Wagner (ORCID: https://orcid.org/0000-0001-9589-2635)
- Luca Fontana (ORCID: https://orcid.org/0000-0002-8614-4114)
- Emmalie Tomini
Institutions
- Health Canada (CA)
- University of Waterloo (CA)
- Public Health Agency of Canada (CA)
- Graz University of Technology (AT)
- World Health Organization (CH)
- European Organization for Nuclear Research (CH)
Publication Details
- Journal
- Cochrane Evidence Synthesis and Methods
- Published
- 2025-10-21
- DOI
- https://doi.org/10.1002/cesm.70042
- Primary Topic
- COVID-19 epidemiological studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Public Health Agency