Assessing the Accuracy, Readability and Understandability of Websites, ChatGPT, Copilot, and Bard Answers on the Radiation during Pregnancy
Authors: Burcu Mert, Emre Emekli
Why is this study important?
This study sheds light on how large language models like ChatGPT, Copilot, and Bard perform when answering patients' questions about radiation exposure during pregnancy. Since patients often seek health information online, it is critical to ensure that the information they find is not only accurate but also readable and understandable. The results highlight the potential of AI in health communication while emphasizing the importance of simplicity and clarity for patient education. This research serves as a guide for improving AI-generated content in sensitive medical contexts.
Read the Full Article (PDF)
Citation
Mert, B., & Emekli, E. (2025). Assessing the Accuracy, Readability and Understandability of Websites, ChatGPT, Copilot, and Bard Answers on the Radiation during Pregnancy. 25(1): 27-39 Ankara Medical Journal. doi:10.5505/amj.2025.54810
@article{mert2025radiation,
title={Assessing the Accuracy, Readability and Understandability of Websites, ChatGPT, Copilot, and Bard Answers on the Radiation during Pregnancy},
author={Mert, Burcu and Emekli, Emre},
journal={Ankara Medical Journal},
volume={25},
number={1},
pages={27--39},
year={2025},
doi={10.5505/amj.2025.54810}
}