Impact of GPT-4–Generated Discharge Letters on Patients’ Medical Comprehension: Prospective Crossover Study
In this explanatory study, GPT-4-generated patient letters improved comprehension of safety-relevant discharge information among standardized patients, particularly regarding medication and organizational aspects. However, they were less effective in supporting higher-order understanding, such as risk prevention or lifestyle management. These hypothesis-driven findings can be interpreted within a CLT framework and may motivate prospective evaluation of multimodal, iterative supports.
Authors
- Martin Holderried (ORCID: https://orcid.org/0000-0002-1337-0516)
- Friederike Holderried (ORCID: https://orcid.org/0000-0003-1828-0920)
- Nils Heyne (ORCID: https://orcid.org/0000-0001-9982-5093)
- Konstantin Sering (ORCID: https://orcid.org/0000-0002-1178-7932)
- Felix Eisinger (ORCID: https://orcid.org/0009-0009-8902-532X)
- Alessandra Sonanini (ORCID: https://orcid.org/0009-0009-4893-3989)
- Philipp Spitzer
- Martina Guthoff
- Christian Stegemann–Philipps
- Anne Herrmann–Werner
Institutions
- Friedrich-Alexander-Universität Erlangen-Nürnberg (DE)
- Städtisches Klinikum Karlsruhe (DE)
- Nephrologisches Zentrum Villingen-Schwenningen (DE)
- University of Tübingen (DE)
Publication Details
- Journal
- Journal of Medical Internet Research
- Published
- 2025-12-24
- DOI
- https://doi.org/10.2196/81243
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00