Novel AI applications in systematic review: GPT-4 assisted data extraction, analysis, review of bias
Customized GPT-4 models perform well in extracting precise data from medical literature with potential for utilization in review of bias. While the evaluated tasks are simpler than the broader range of SR methodologies, they provide an important initial assessment of GPT-4's capabilities.
Authors
- Armando José Lorenzo (ORCID: https://orcid.org/0000-0001-6735-9462)
- Michael Chua (ORCID: https://orcid.org/0000-0002-4388-4067)
- Mandy Rickard (ORCID: https://orcid.org/0000-0003-0598-1824)
- Tian Li (ORCID: https://orcid.org/0000-0001-6181-5156)
- Jin K. Kim (ORCID: https://orcid.org/0000-0003-0964-9503)
Institutions
- University of Toronto (CA)
- Hospital for Sick Children (CA)
- Riley Hospital for Children (US)
Publication Details
- Journal
- BMJ evidence-based medicine
- Published
- 2025-04-08
- DOI
- https://doi.org/10.1136/bmjebm-2024-113066
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62