Using large language models to generate child-friendly education materials on myopia
DIGITAL HEALTH · 2025-05 · 11
DOI: 10.1177/20552076251362338 ↗Kurz gefasst
Fachartikel in der Zeitschrift DIGITAL HEALTH, online erschienen am 30.07.2025. Verfasst von Xuewei Li und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Ophthalmology, Peking University People's Hospital, Eye Diseases and Optometry Institute, Beijing, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Capital's Funds for Health Improvement and Research, National Natural Science Foundation of China.
Abstract (Originalsprache)
Aim
To evaluate the ability of large language models (LLMs) to produce patient education materials for myopic children and their parents.
Methods
Thirty-five common myopia-related questions were used with two distinct prompts to produce responses aimed at adults (Prompt A) and children (Prompt B). Five ophthalmologists evaluated the responses using a 5-point Likert scale for correctness, completeness, conciseness, and potential harm. Readability was assessed via Flesch–Kincaid scores. The Kruskal-Wallis and Mann-Whitney U tests were used to identify significant differences in LLM performance.
Results
ChatGPT 4o achieved the most positive ratings (“good” and above) in correctness (Prompt A: 91%; Prompt B: 83%) and conciseness (Prompt A: 79%; Prompt B: 63%), as well as the lowest negative ratings in potential harm ratings (“not at all” and “slightly,” Prompt A: 99%; Prompt B: 97%) in the generation of educational materials for both adults and children (all p < 0.001). In terms of completeness, the results varied between the two prompts. Specifically, in Prompt A, ChatGPT 4.0 demonstrated the highest level of completeness (ChatGPT 4o: 69%, ChatGPT 4.0: 74%, ChatGPT 3.5: 51%, Gemini: 73%, p < 0.001), whereas in Prompt B, ChatGPT 4o achieved the highest score (ChatGPT 4o: 71%, ChatGPT 4.0: 65%, ChatGPT 3.5: 38%, Gemini: 46%, p < 0.001). The responses generated with Prompt B were significantly more readable than those generated with Prompt A across all LLMs ( p ≤ 0.001).
Conclusion
Large language models, particularly ChatGPT 4o, hold potential for delivering effective patient education materials on myopia for both adult and pediatric populations. While generally effective, LLMs have limitations for complex medical queries, necessitating continued refinement for reliable clinical use.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Ophthalmology, Peking University People's Hospital, Eye Diseases and Optometry Institute, Beijing, China.
- Institute of Medical Technology, Peking University Health Science Center, Beijing, China.
- Department of Ophthalmology, Beijing Key Laboratory of the Diagnosis and Therapy of Retinal and Choroid Diseases, Beijing, China.
- College of Optometry, Peking University Health Science Center, Beijing, China.
ORCID-Profile: Kai Wang
Förderung
- Capital's Funds for Health Improvement and Research
- National Natural Science Foundation of China
Zitieren
APA
Li, X., Zhang, Y., Zheng, T., Deng, Y., Lu, Y., Hu, J., Chen, S., Li, Y., & Wang, K. (2025). Using large language models to generate child-friendly education materials on myopia. DIGITAL HEALTH, 11. https://doi.org/10.1177/20552076251362338
Vancouver
Li X, Zhang Y, Zheng T, Deng Y, Lu Y, Hu J, et al. Using large language models to generate child-friendly education materials on myopia. DIGITAL HEALTH. 2025;11. doi:10.1177/20552076251362338
BibTeX
@article{Li2025,
author = {Li, Xuewei and Zhang, Yixuan and Zheng, Tonglei and Deng, Yuanqi and Lu, Yuchang and Hu, Jie and Chen, Sitong and Li, Yan and Wang, Kai},
title = {Using large language models to generate child-friendly education materials on myopia},
journal = {DIGITAL HEALTH},
year = {2025},
volume = {11},
doi = {10.1177/20552076251362338}
}
EUVIMED