ChatGPT用于改善多个整形外科领域的术后指导
本研究获取乳房、颅颌面、手部和美容四个整形外科亚专科的术后指导,用ChatGPT将其改写为六年级和四年级阅读水平,并评估可读性、可理解性、可操作性和安全性。结果显示ChatGPT可将术后指导调整至更具可读性的六年级水平且不损害安全性,但四年级改写版的可操作性下降。
要点
- ChatGPT可将术后指导改写至六年级阅读水平且不损害安全性。
- 作者建议提示ChatGPT写出比目标阅读水平低一到两个年级的文本。
- 六年级仍是术后指导的最佳阅读水平,四年级改写版可操作性下降。
核心结论
- ChatGPT可将术后指导调整至更具可读性的六年级水平且不损害安全性。
- 作者建议提示ChatGPT写出比目标阅读水平低一到两个年级的文本。
- 尽管所有ChatGPT改写版的可理解性均提高,但四年级水平指导的可操作性下降;六年级仍是术后指导的最佳阅读水平。
研究设计与样本
- 研究获取整形外科四个索引手术的术后指导,使用ChatGPT改写至六年级和四年级阅读水平。
- 通过七种可读性指数评估可读性,使用印刷材料患者教育评估工具问卷评估可理解性和可操作性,由主刀外科医生评估安全性。
主要发现
- 原始术后指导的平均可读性介于七年级至八年级水平。
- 六年级ChatGPT改写版中仅有一份降至六年级水平;四年级ChatGPT改写版均降至六年级或以下,但无一达到四年级水平。
- 可理解性评分随阅读水平降低而升高,而四年级改写版的可操作性评分下降。
- 所有改写版的安全性均未受损害。
临床怎么用
- 作者认为ChatGPT可通过改善术后指导的可读性来帮助提升患者照护。
- 作者建议提示ChatGPT写出比目标阅读水平低一到两个年级的文本。
- 作者指出六年级仍是术后指导的最佳阅读水平。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Clear discharge instructions are vital for patients and caregivers to manage postoperative care at home. However, they often exceed the sixth-grade reading level recommended by national associations. It was hypothesized that ChatGPT could help rewrite instructions to this level for increased accessibility and comprehension. This study aimed to assess the readability, understandability, actionability, and safety of ChatGPT rewritten postoperative instructions in four plastic surgery subspecialties: breast, craniofacial, hand, and aesthetic surgery. METHODS: Postoperative instructions from four index procedures in plastic surgery were obtained. ChatGPT was used to rewrite at the sixth- and fourth-grade reading levels. Readability was determined by seven readability indexes, understandability and actionability by the Patient Education Materials Assessment Tool for printable materials questionnaire, and safety by the primary surgeons. RESULTS: Overall, the average readability of the original postoperative instructions ranged between the seventh and eighth grade levels. Only one of the sixth-grade ChatGPT instructions was lowered to the sixth-grade level. Of the fourth-grade ChatGPT instructions, all were reduced to the sixth-grade-level or below, but none achieved the fourth-grade level. Understandability scores increased as reading levels decreased, whereas actionability scores decreased for fourth-grade rewrites. Safety was not compromised in all rewrites. CONCLUSIONS: ChatGPT can adapt postoperative instructions to a more readable sixth-grade level without compromising safety. This study suggests prompting ChatGPT to write one to two grade levels lower than the desired reading level. While understandability increased for all ChatGPT rewrites, actionability decreased for fourth-grade-level instructions. Sixth-grade remains the optimal reading level for postoperative instructions. This study demonstrates that ChatGPT can help improve patient care by improving the readability of postoperative instructions.
引用
- Zhang A, Li CXR, Piper M, et al. ChatGPT for improving postoperative instructions in multiple fields of plastic surgery. J Plast Reconstr Aesthet Surg. 2024. PMID: 39383672. doi:10.1016/j.bjps.2024.08.065
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。