High-performance automated abstract screening with large language model ensembles
LLMs may reduce the human labor cost of systematic review with maintained or improved accuracy, thereby increasing the efficiency and quality of evidence synthesis.
Authors
- Archie Watt (ORCID: https://orcid.org/0000-0002-7572-4586)
- Haider Butt (ORCID: https://orcid.org/0000-0003-2434-9525)
- Mustafa F. Mahmood (ORCID: https://orcid.org/0000-0003-1394-285X)
- Arun James Thirunavukarasu (ORCID: https://orcid.org/0000-0001-8968-4768)
- Andrew A. S. Soltan (ORCID: https://orcid.org/0000-0003-2391-5361)
- Jessica O’Logbon (ORCID: https://orcid.org/0000-0003-1216-9703)
- Rohan Sanghera (ORCID: https://orcid.org/0000-0001-6370-8426)
- Genrokuro NISHIMURA
- Yuqing Chen (ORCID: https://orcid.org/0000-0002-4052-2191)
- Marc Khoury
Institutions
- MedStar Washington Hospital Center (US)
- King's College London (GB)
- Georgetown University (US)
- University of Cambridge (GB)
- University of Oxford (GB)
- Cambridge School (PT)
- Oxford University Hospitals NHS Trust (GB)
- University College London (GB)
Publication Details
- Journal
- Journal of the American Medical Informatics Association
- Published
- 2025-03-22
- DOI
- https://doi.org/10.1093/jamia/ocaf050
- Citations
- 26
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 17.01