Large language models vs thrombosis experts: a comparative study on patient education and clinical decision-making in venous thromboembolism
LLMs outperform experts in venous thromboembolism-related patient education and match or exceed them in clinical decision making, providing responses indistinguishable from experts. Although major barriers need to be addressed, LLMs have strong potential to support clinical management and patient education in the field of thrombosis and hemostasis.
Authors
- Ingrid Pabinger (ORCID: https://orcid.org/0000-0002-7677-9896)
- Cihan Ay (ORCID: https://orcid.org/0000-0003-2607-9717)
- Sabine Eichinger
- Jean M. Connors (ORCID: https://orcid.org/0000-0001-6445-582X)
- Stephan Nopp (ORCID: https://orcid.org/0000-0002-4504-482X)
- Walter Ageno (ORCID: https://orcid.org/0000-0002-1922-8879)
- Nikola Vladić (ORCID: https://orcid.org/0009-0002-3806-2250)
Institutions
- Brigham and Women's Hospital (US)
- Harvard University (US)
- University of Padua (IT)
- Medical University of Vienna (AT)
Publication Details
- Journal
- Journal of Thrombosis and Haemostasis
- Published
- 2025-09-25
- DOI
- https://doi.org/10.1016/j.jtha.2025.09.004
- Citations
- 2
- Primary Topic
- Venous Thromboembolism Diagnosis and Management
- Type
- article
- Field-Weighted Citation Impact
- 3.74