Extracting TNFi switching reasons and trajectories from real-world data using large language models
Both GPT-4 and locally deployable LLMs effectively extracted complex treatment trajectories and rationale from clinical notes, supporting their broader utility in scalable EHR review and real-world evidence generation.
Authors
- Marie Binvignat (ORCID: https://orcid.org/0000-0001-7473-7636)
- Jinoos Yazdany (ORCID: https://orcid.org/0000-0002-3508-4094)
- Brenda Y. Miao (ORCID: https://orcid.org/0000-0002-3393-9837)
- Atul J. Butte (ORCID: https://orcid.org/0000-0002-7433-2740)
- Gabriela Schmajuk (ORCID: https://orcid.org/0000-0003-2687-5043)
- Chiyuan Miao (ORCID: https://orcid.org/0000-0001-6413-7020)
- Christopher Y. K. Williams (ORCID: https://orcid.org/0000-0001-8867-1623)
- Augusto García-Agúndez (ORCID: https://orcid.org/0000-0002-5440-1032)
- Vivek A. Rudrapatna (ORCID: https://orcid.org/0000-0003-1789-3004)
- Ahmed Alaa
- Maxim Bravo
Institutions
- Executive Office of the President (US)
- Inserm (FR)
- University of California, San Francisco (US)
- Sorbonne Université (FR)
- Centre d'Immunologie et des Maladies Infectieuses (FR)
- Centre de Recherche Saint-Antoine (FR)
- Immunologie - Immunopathologie - Immunothérapie (FR)
- University of San Francisco (US)
- University of California, Berkeley (US)
Publication Details
- Journal
- JAMIA Open
- Published
- 2025-11-03
- DOI
- https://doi.org/10.1093/jamiaopen/ooaf132
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00