Key result
ChatGPT improves readability but misses 6th-grade targets, while Bard reaches them but omits ~83% of content.
Why the study?
Patient information materials often tend to be written at a reading level that is too advanced for patients.
Do ChatGPT and Google Bard improve the readability of written patient information?
Do ChatGPT and Google Bard improve the readability of written patient information?
Large language models like ChatGPT can improve the readability of patient information materials, though achieving specific grade levels without content loss remains challenging.
Answers are grounded in this paper and cite their sources.
LLM use for patient materials warrants content verification before clinical deployment; leaves open whether refined models can balance readability and completeness.
Patient information materials often tend to be written at a reading level that is too advanced for patients. In this proof-of-concept study, we used ChatGPT and Google Bard to reduce the reading level of three selected patient information sections from scientific journals. ChatGPT successfully improved readability. However, it could not achieve the recommended 6th-grade reading level. Bard reached the reading level of 6th graders but oversimplified the texts by omitting up to 83% of the content. Despite the present limitations, developers of patient information are encouraged to employ large language models, preferably ChatGPT, to optimize their materials.
No takes yet. Share an insight, caveat, or question.
Moons et al. (2023) studied this question. ChatGPT and Google Bard was evaluated on Reading level. ChatGPT improved readability of patient information texts without reaching a 6th-grade level, whereas Google Bard achieved the 6th-grade level but omitted up to 83% of the content.
Synapse has enriched 10 related papers. Consider them for comparative context: