Evaluating the performance of a custom GPT in full text screening of a systematic review
<b>The assistant cGPT outperformed the autonomous cGPT. An assistant cGPT could speed up systematic reviewing in a sufficiently reliable manner, however, further research is needed to establish standardized thresholds for practical use. Improved speed of systematic reviewing has implications for directing timely public health policy decisions.</b>
Authors
- Sigrun Henjum (ORCID: https://orcid.org/0000-0002-0671-2688)
- Espen Heen (ORCID: https://orcid.org/0000-0001-7606-4834)
- S. List
- Rachel E. Davis (ORCID: https://orcid.org/0000-0002-9669-9623)
- Kendal G. Chappell
- Ahmed Madar
Institutions
- OsloMet – Oslo Metropolitan University (NO)
- University of Oslo (NO)
- Østfold University of Applied Sciences (NO)
Publication Details
- Journal
- Scandinavian Journal of Public Health
- Published
- 2026-03-13
- DOI
- https://doi.org/10.1177/14034948261423410
- Primary Topic
- Meta-analysis and systematic reviews
- Type
- article
- Field-Weighted Citation Impact
- 0.00