Large Language Models Outperform Traditional Natural Language Processing Methods in Extracting Patient-Reported Outcomes in Inflammatory Bowel Disease
LLMs are accurate and generalizable methods for extracting PROs. They maintain excellent accuracy across institutions, despite heterogeneity in note templates and authors. Widespread adoption of such tools has the potential to enhance IBD research and patient care.
Authors
- Perseus V. Patel (ORCID: https://orcid.org/0000-0002-8287-3424)
- Amariel Ralbovsky
- Tina Hernandez‐Boussard (ORCID: https://orcid.org/0000-0001-6553-3455)
- Shadera Slatter
- Christopher Y. K. Williams (ORCID: https://orcid.org/0000-0001-8867-1623)
- Michael Rosen (ORCID: https://orcid.org/0000-0002-8842-6692)
- Vivek A. Rudrapatna (ORCID: https://orcid.org/0000-0003-1789-3004)
- Behzad Naderalvojoud
- Conner Davis
- Daniel Tinoco
Institutions
- Palo Alto University (US)
- University of California, San Francisco (US)
- Stanford Medicine (US)
- Stanford University (US)
Publication Details
- Journal
- Gastro Hep Advances
- Published
- 2024-10-10
- DOI
- https://doi.org/10.1016/j.gastha.2024.10.003
- Citations
- 8
- Primary Topic
- Inflammatory Bowel Disease
- Type
- article
- Field-Weighted Citation Impact
- 4.40
Funders
- Microsoft Research
- University of California, San Francisco
- U.S. National Library of Medicine
- National Center for Advancing Translational Sciences
- Clinical and Translational Science Institute, University of California, Los Angeles