Human versus artificial intelligence: evaluating ChatGPT’s performance in conducting published systematic reviews with meta-analysis in chronic pain research
ChatGPT demonstrates modest to moderate accuracy in screening and study selection tasks, but performs well in data pooling and meta-analytic calculations. These findings underscore the potential of AI to augment systematic review methodologies, while also emphasizing the need for human oversight to ensure accuracy and integrity in research workflows.
Authors
- Ryan S. D’Souza (ORCID: https://orcid.org/0000-0002-4601-9837)
- Johana Klasová (ORCID: https://orcid.org/0000-0002-0303-528X)
- Anam Purewal (ORCID: https://orcid.org/0000-0002-3674-9019)
- Nasir Hussain (ORCID: https://orcid.org/0000-0003-0353-1002)
- Kalli Fautsch
Institutions
- Mayo Clinic (US)
- SUNY Downstate Health Sciences University (US)
- The Ohio State University (US)
Publication Details
- Journal
- Regional Anesthesia & Pain Medicine
- Published
- 2025-02-16
- DOI
- https://doi.org/10.1136/rapm-2024-106358
- Citations
- 14
- Primary Topic
- Musculoskeletal pain and rehabilitation
- Type
- article
- Field-Weighted Citation Impact
- 19.52