Incorporating information retrieval into AI chatbots for patient education on thyroid eye disease
Specialized medical AI models may have better clinical accuracy, while general-purpose models may outperform in patient communication and accessibility. The development of retrieval augmented generation-based approaches combining clinical precision with effective communication represents a promising direction for AI-powered patient education in TED and, potentially, other complex conditions.
Authors
- Mark Krakauer (ORCID: https://orcid.org/0000-0002-2798-7218)
- Shayan Saeed (ORCID: https://orcid.org/0000-0002-4227-8348)
- Megan R Silas (ORCID: https://orcid.org/0000-0001-6494-7728)
- Hassan A. Shah (ORCID: https://orcid.org/0000-0002-6951-8671)
- Kameel Khabaz (ORCID: https://orcid.org/0000-0002-3164-6133)
- Zaid Parekh (ORCID: https://orcid.org/0000-0002-3898-3183)
- Asim V. Farooq (ORCID: https://orcid.org/0000-0002-8199-2915)
Institutions
- University of California, Los Angeles (US)
- University of California, Irvine (US)
- Temple College (US)
- University of Chicago (US)
- Temple University, Japan (JP)
- Temple University (US)
Publication Details
- Journal
- International Journal of Medical Informatics
- Published
- 2025-11-30
- DOI
- https://doi.org/10.1016/j.ijmedinf.2025.106213
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31