Exploring Patient Perspectives, Engagement, and Output Quality in Doctor-Supervised Use of Artificial Intelligence During Informed Consent Consultation With ChatGPT and Retrieval Augmented Generation (RAG): Quantitative Exploratory Study
Integrating RAG with ChatGPT significantly improves the quality, clarity, and reliability of preoperative information, enhancing patient satisfaction and engagement beyond native ChatGPT. However, patients maintain a strong preference for physician-led informed consent, underscoring the role of AI chatbots as complementary tools rather than replacements. These findings support the cautious adoption of customized AI assistants to augment, not substitute, human interaction in surgical consent processes.
Authors
- Stefanie Donner (ORCID: https://orcid.org/0000-0001-8270-0462)
- Arne Kienzle (ORCID: https://orcid.org/0000-0002-4556-2993)
- Sascha Donner (ORCID: https://orcid.org/0000-0002-3633-7452)
- Carsten Perka (ORCID: https://orcid.org/0000-0002-0993-581X)
- Joost A. Burger (ORCID: https://orcid.org/0000-0001-9360-2884)
- Jesse David Dinneen (ORCID: https://orcid.org/0000-0001-5214-5891)
- Poroshista Knauer
Institutions
- Humboldt-Universität zu Berlin (DE)
- Charité - Universitätsmedizin Berlin (DE)
- University of Borås (SE)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-08-28
- DOI
- https://doi.org/10.2196/73717
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00