Background/aims This was a cross-sectional comparative study. We evaluated the ability of three large language models (LLMs) (ChatGPT-3.5, ChatGPT-4, and Google Bard) to generate novel patient education materials (PEMs) and improve the readability of existing PEMs on paediatric cataract. Methods We compared LLMs’ responses to three prompts. Prompt A requested they write a handout on paediatric cataract that was ‘easily understandable by an average American.’ Prompt B modified prompt A and requested the handout be written at a ‘sixth-grade reading level, using the Simple Measure of Gobbledygook (SMOG) readability formula.’ Prompt C rewrote existing PEMs on paediatric cataract ‘to a sixth-grade reading level using the SMOG readability formula’. Responses were compared on their quality (DISCERN; 1 (low quality) to 5 (high quality)), understandability and actionability (Patient Education Materials Assessment Tool (≥70%: understandable, ≥70%: actionable)), accuracy (Likert misinformation; 1 (no misinformation) to 5 (high misinformation) and readability (SMOG, Flesch-Kincaid Grade Level (FKGL); grade level <7: highly readable). Results All LLM-generated responses were of high-quality (median DISCERN ≥4), understandability (≥70%), and accuracy (Likert=1). All LLM-generated responses were not actionable (<70%). ChatGPT-3.5 and ChatGPT-4 prompt B responses were more readable than prompt A responses (p<0.001). ChatGPT-4 generated more readable responses (lower SMOG and FKGL scores; 5.59±0.5 and 4.31±0.7, respectively) than the other two LLMs (p<0.001) and consistently rewrote them to or below the specified sixth-grade reading level (SMOG: 5.14±0.3). Conclusion LLMs, particularly ChatGPT-4, proved valuable in generating high-quality, readable, accurate PEMs and in improving the readability of existing materials on paediatric cataract. Data are available on reasonable request. Data to be made are available on reasonable request.

中文翻译：

---

大语言模型：小儿白内障患者教育的新领域


背景/目标 这是一项横断面比较研究。我们评估了三种大型语言模型 ( LLMs )（ChatGPT-3.5、ChatGPT-4 和 Google Bard）生成新型患者教育材料 (PEM) 并提高现有 PEM 关于儿童白内障的可读性的能力。方法 我们比较了LLMs对三个提示的反应。提示 A 要求他们写一份关于儿童白内障的讲义，“普通美国人很容易理解”。提示 B 修改了提示 A，并要求以“六年级阅读水平，使用简单测量官方语言 (SMOG) 可读性公式”编写讲义。 Prompt C 将现有的儿童白内障 PEM 重写为“使用 SMOG 可读性公式达到六年级阅读水平”。比较答复的质量（DISCERN；1（低质量）至 5（高质量））、可理解性和可操作性（患者教育材料评估工具（≥70%：可理解，≥70%：可操作））、准确性（李克特错误信息） ；1（无错误信息）至 5（高度错误信息）和可读性（SMOG、Flesch-Kincaid 等级水平 (FKGL)；等级水平 <7：高度可读） 结果 所有LLM生成的回复都是高质量的（中值 DISCERN ≥）。 4)、可理解性 (≥70%) 和准确性 (Likert=1)。所有LLM生成的响应均不可操作 (<70%)，ChatGPT-3.5 和 ChatGPT-4 提示 B 响应比提示 A 响应更具可读性（ ChatGPT-4 生成的响应比其他两个LLMs (p<0.001) 更具可读性（较低的 SMOG 和 FKGL 分数；分别为 5.59±0.5 和 4.31±0.7），并且始终将其重写为或更低。指定的六年级阅读水平（烟雾：5.14±0.3）。 结论LLMs ，特别是 ChatGPT-4，在生成高质量、可读、准确的 PEM 和提高现有儿童白内障材料的可读性方面具有重要价值。可根据合理要求提供数据。待制作的数据可根据合理要求提供。