Patients Prefer ChatGPT to Institutional Websites for Questions on Radiation-based Imaging Exams: International Mixed-Methods Study
Abstract Background Radiology-risk communication affects multiple clinical specialties that use ionizing radiation, and many patients seek related information online. Prior expert evaluations found comparable performance between ChatGPT-generated and radiology risk answers from official institutions, but patient perspectives have not been assessed. Purpose to assess patients’ perceptions of ChatGPT versus human-generated radiology risk information. Methods and Materials From December 2024 to March 2025, patients at three hospitals in the United States, Switzerland, and Lebanon were randomly assigned to one of five common radiology risk questions. Participants, blinded to source, provided subjective ratings of both ChatGPT‑3.5 and human-generated institutional responses on 7-point Likert scales for satisfaction (primary outcome), comprehensibility, trust, and reassurance. Quantitative comparisons were performed with Inverse Normalizing Transformation, and free-text comments were analyzed using thematic coding. Results A total of 328 patients participated (34% aged 18-39 years, 33% aged 40-59 years, 31% aged 60-79 years, 3% aged ≥80 years; 188 female). ChatGPT responses were rated significantly higher than human responses for satisfaction (0.70-point advantage; p<.001), comprehensibility (0.27 points; p<.01), trust (0.65 points; p<.001), and reassurance (0.51 points; p<.001). Findings converged with qualitative written comments (r = 0.91, p<.05), in which ChatGPT attracted 2.3× more positive comments while human-generated responses received 1.7× more negative comments. Conclusions Unlike experts, patients preferred ChatGPT-generated responses to institutional materials for radiology risk questions. This divergence highlights the need for patient-centered communication and suggests that LLM-based styles, implemented with expert oversight, may improve the perceived clarity and trustworthiness of educational materials in medical specialties that use ionizing radiation.
Authors
- M. Nowak (ORCID: https://orcid.org/0000-0003-2481-2049)
- Chiara Pozzessere (ORCID: https://orcid.org/0000-0003-1379-5888)
- Florian Poncet
- Jonas Richiardi (ORCID: https://orcid.org/0000-0002-6975-5634)
- Marianna Gulizia (ORCID: https://orcid.org/0000-0001-5494-2691)
- Sofyan Jankowski (ORCID: https://orcid.org/0000-0003-0866-3290)
- Stephanie De Labouchère (ORCID: https://orcid.org/0009-0000-7992-9223)
- David Rotzinger
- Charbel Mourad
- Wendy Brito Rodriguez
- Emily Harkness
- Francesco Ria
Institutions
- Duke University (US)
- HES-SO University of Applied Sciences and Arts Western Switzerland (CH)
- Centre Hospitalier Universitaire Vaudois (CH)
- Lebanese Hospital Geitaoui-University Medical Center (LB)
- Duke Medical Center (US)
- Centre d'Imagerie BioMedicale (CH)
- University of Lausanne (CH)
Publication Details
- Journal
- Radiology Advances
- Published
- 2026-07-23
- DOI
- https://doi.org/10.1093/radadv/umag033
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00