ChatGPT in urogynecology: Comparing large language model responses to human experts
In this exploratory study, women rated ChatGPT's responses as clearer and more reassuring than consultant answers. These findings reflect patient perceptions in a limited setting and should be interpreted with caution. While LLMs may have a supportive role in patient education, their use must remain secondary to expert clinical care and subject to careful oversight.
Authors
- Misgav Rottenstreich (ORCID: https://orcid.org/0000-0003-4875-1455)
- Reut Rotem (ORCID: https://orcid.org/0000-0002-4063-5911)
- Barry O’Reilly (ORCID: https://orcid.org/0000-0003-4031-9414)
- Orfhlaith E. O’Sullivan (ORCID: https://orcid.org/0000-0003-0553-1874)
- Cristiane Paulin Simon (ORCID: https://orcid.org/0000-0001-7318-8305)
- Adi Y. Weintraub (ORCID: https://orcid.org/0000-0002-4239-8665)
Institutions
- Ben-Gurion University of the Negev (IL)
- Shaare Zedek Medical Center (IL)
- Cork University Hospital (IE)
- National Maternity Hospital (IE)
Publication Details
- Journal
- Acta Obstetricia Et Gynecologica Scandinavica
- Published
- 2025-10-23
- DOI
- https://doi.org/10.1111/aogs.70085
- Citations
- 3
- Primary Topic
- Patient-Provider Communication in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 8.45