Automating pharmacovigilance evidence generation: using large language models to produce context-aware structured query language
This study presents a novel approach to employing LLMs for safety data retrieval and analysis, demonstrating significant advancements in query generation accuracy. The methodology offers a framework applicable to various data-intensive domains, enhancing the accessibility of information retrieval for non-technical users.
Authors
- Andrew Bate (ORCID: https://orcid.org/0000-0003-3151-3653)
- Jeffery L. Painter (ORCID: https://orcid.org/0000-0001-9651-9904)
- Raymond Kassekert
- Venkateswara Rao Chalamalasetti
Institutions
- University of London (GB)
- GlaxoSmithKline (United Kingdom) (GB)
- London School of Hygiene & Tropical Medicine (GB)
- GlaxoSmithKline (United States) (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2024-12-26
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf003
- Citations
- 8
- Primary Topic
- Software Engineering Research
- Type
- article
- Field-Weighted Citation Impact
- 6.23
Funders
- GlaxoSmithKline