Practical Aspects of Using Large Language Models to Screen Abstracts for Cardiovascular Drug Development: Cross-Sectional Study
Cardiovascular drug development requires synthesizing relevant literature about indications, mechanisms, biomarkers, and outcomes. This short study investigates the performance, cost, and prompt engineering trade-offs of 3 large language models accelerating the literature screening process for cardiovascular drug development applications.
Authors
- Jay G. Ronquillo (ORCID: https://orcid.org/0000-0002-0438-7172)
- Jamie Ye (ORCID: https://orcid.org/0000-0003-3024-4711)
- Donal Gorman (ORCID: https://orcid.org/0000-0003-4853-9817)
- Adina R. Lemeshow (ORCID: https://orcid.org/0000-0003-2994-1341)
- Stephen Watt (ORCID: https://orcid.org/0000-0003-1403-5493)
Institutions
- Pfizer (United States) (US)
- Pfizer (United Kingdom) (GB)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2024-09-30
- DOI
- https://doi.org/10.2196/64143
- Citations
- 6
- Primary Topic
- Health Systems, Economic Evaluations, Quality of Life
- Type
- article
- Field-Weighted Citation Impact
- 6.78