Validation of automated paper screening for esophagectomy systematic review using large language models
This study demonstrates promising use of LLMs to streamline the workflow of systematic reviews. The integration of LLMs in systematic reviews could lead to significant time and cost savings, however caution must be taken for reviews involving stringent a narrower and exclusion criterion. Future research is needed and should explore integrating LLMs in other steps of the systematic review, such as full text screening or data extraction, and compare different LLMs for their effectiveness in various types of systematic reviews.
Authors
- Jamie Strain (ORCID: https://orcid.org/0000-0002-4023-5715)
- Rashi Ramchandani (ORCID: https://orcid.org/0000-0002-6144-6423)
- Daniel M. Jones
- William Klement (ORCID: https://orcid.org/0000-0002-9616-8662)
- Risa Shorr (ORCID: https://orcid.org/0000-0003-0388-5812)
- Eddie Guo (ORCID: https://orcid.org/0000-0002-7223-0505)
- Erin Williams (ORCID: https://orcid.org/0000-0001-5418-814X)
- Sébastien Gilbert (ORCID: https://orcid.org/0000-0003-4357-9553)
- J. Bhupender Singh Rathod
- Esra Rakab
Institutions
- Dalhousie University (CA)
- University of Ottawa (CA)
- University of Calgary (CA)
- University of Toronto (CA)
- Ottawa Hospital (CA)
- Ottawa Hospital Research Institute (CA)
Publication Details
- Journal
- PeerJ Computer Science
- Published
- 2025-04-30
- DOI
- https://doi.org/10.7717/peerj-cs.2822
- Citations
- 1
- Primary Topic
- Esophageal Cancer Research and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.01