Application of large language and artificial intelligence modeling in the prediction of peer-review outcomes
This proof-of-concept study demonstrates that fine-tuned AI models, particularly GPT-3, can predict manuscript acceptance with reasonable accuracy using only textual reviewer comments. Emerging themes that lend weight to article outcome include article clarity, utility, suitability, cohort size, and diligence in addressing reviewer queries. These findings suggest that, when fine-tuned, AI modeling holds significant potential in assisting and facilitating the peer-review process.
Authors
- Austin J. Borja (ORCID: https://orcid.org/0000-0002-8604-7816)
- David J. Coté (ORCID: https://orcid.org/0000-0001-5419-1517)
- Lawrance K. Chung (ORCID: https://orcid.org/0009-0008-6410-9490)
- Ishan Shah (ORCID: https://orcid.org/0000-0003-2249-1827)
- Robert G. Briggs (ORCID: https://orcid.org/0000-0001-9329-4471)
- Gillian Shasby (ORCID: https://orcid.org/0000-0003-2023-3357)
- Jonathan Sisti (ORCID: https://orcid.org/0000-0001-9011-1668)
- J. T. Rutka
- Jonathan Dallas
- Gabriel Zada
- David Gomez
- Benjamin S. Hopkins
Institutions
- University of Southern California (US)
- University of Toronto (CA)
- American Association of Neurological Surgeons (US)
Publication Details
- Journal
- Journal of neurosurgery
- Published
- 2026-01-22
- DOI
- https://doi.org/10.3171/2025.8.jns242667
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00