Skip to main content
. 2023 Oct 5;34(5):2817–2825. doi: 10.1007/s00330-023-10213-1

Fig. 1.

Fig. 1

Prompting ChatGPT to simplify a radiology report of an oncological CT results in different responses each time. Even when responses sound plausible, the content does not need to be true. The response on the top correctly simplifies the term “thyroid struma,” while the response on the bottom fails to give a correct simplification