Evaluating Artificial Intelligence-Generated Responses to Patient Questions Regarding Orthobiologic Injections
In this study, ChatGPT, Gemini, and Grok provided generally accurate information on orthobiologics but failed to produce responses at a patient-appropriate readability level. Gemini outperformed ChatGPT in accuracy, although all 3 models demonstrated significant limitations in clarity. Until these issues are resolved, AI-generated responses should serve only as supplemental resources, with final patient education directed by physicians.
Authors
- Jesse Seilern und Aspang (ORCID: https://orcid.org/0000-0002-4479-3132)
- Destin Hill
- Richard M. Danilkowicz (ORCID: https://orcid.org/0000-0003-3183-5310)
- Kyle E. Hammond (ORCID: https://orcid.org/0000-0002-3481-4921)
- Jasmine Patel (ORCID: https://orcid.org/0009-0009-3712-7519)
- Prathap Jayaram (ORCID: https://orcid.org/0000-0003-0849-5573)
- Benjamin W. King
Institutions
- Emory University (US)
Publication Details
- Journal
- Orthopaedic Journal of Sports Medicine
- Published
- 2026-02-01
- DOI
- https://doi.org/10.1177/23259671251414852
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00