提升人工智能生成的脆性骨折医学信息的可读性:提示词表述对ChatGPT回答的作用
本研究通过Google Trends识别与「脆性骨折」和「骨质疏松性骨折」相关的32个高频搜索关键词,从中选取24个依次输入ChatGPT,比较「嵌入关键词的通俗语言提示」与「仅关键词提示」两种方式生成回答的可读性。结果显示,通俗语言提示的Flesch-Kincaid阅读易度评分中位数34.35,高于仅关键词提示的23.60;Flesch-Kincaid年级水平评分中位数12.05,低于仅关键词提示的14.50,差异均具统计学显著性。
要点
- 使用通俗语言提示时,ChatGPT回答的阅读易度评分中位数34.35,高于仅关键词提示的23.60。
- 使用通俗语言提示时,年级水平评分中位数12.05,低于仅关键词提示的14.50。
- 作者认为,临床医生和内容创作者在使用人工智能进行患者教育时可考虑此方法以优化理解。
核心结论
- 研究提示,使用对话式提示可提升人工智能生成的脆性骨折医学信息的可读性。
- 作者认为,临床医生和内容创作者在使用人工智能进行患者教育时可考虑此方法以优化理解。
研究设计与样本
- 通过Google Trends识别与「脆性骨折」和「骨质疏松性骨折」相关的32个最常搜索关键词。
- 从该组关键词中基于相关性选取24个关键词,依次输入ChatGPT。
- 每个关键词测试两种提示类型:嵌入关键词的通俗语言提示和仅关键词提示。
- 使用Flesch-Kincaid阅读易度(FKRE)和Flesch-Kincaid年级水平(FKGL)分别评估人工智能生成回答的可读性和可理解性。
- 采用Mann-Whitney U检验比较回答的评分。
主要发现
- FKRE评分显示,通俗语言提示的中位数34.35,仅关键词提示的中位数23.60,通俗语言提示的可读性显著更高。
- FKGL显示,通俗语言提示的中位数12.05,仅关键词提示的中位数14.50,通俗语言提示的年级水平更低,差异具统计学显著性。
关键数值与推荐
- FKRE评分:通俗语言提示中位数34.35 vs 仅关键词提示中位数23.60,差异具统计学显著性。
- FKGL评分:通俗语言提示中位数12.05 vs 仅关键词提示中位数14.50,差异具统计学显著性。
临床怎么用
- 作者认为,临床医生和内容创作者在使用人工智能进行患者教育时可考虑此方法以优化理解。
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
UNLABELLED: Understanding how the questions used when interacting with chatbots impact the readability of the generated text is essential for effective health communication. Using descriptive queries instead of just keywords during interaction with ChatGPT results in more readable and understandable answers about fragility fractures. PURPOSE: Large language models like ChatGPT can enhance patients' understanding of medical information, making health decisions more accessible. Complex terms, such as "fragility fracture," can confuse patients, so presenting its medical content in plain language is crucial. This study explored whether conversational prompts improve readability and understanding compared to keyword-based prompts when generating patient-centered health information on fragility fractures. METHODS: The 32 most frequently searched keywords related to "fragility fracture" and "osteoporotic fracture" were identified using Google Trends. From this set, 24 keywords were selected based on relevance and entered sequentially into ChatGPT. Each keyword was tested with two prompt types: (1) plain language with keywords embedded and (2) keywords alone. The readability and comprehensibility of the AI-generated responses were assessed using the Flesch-Kincaid reading ease (FKRE) and Flesch-Kincaid grade level (FKGL), respectively. The scores of the responses were compared using the Mann-Whitney U test. RESULTS: The FKRE scores indicated significantly higher readability with plain language prompts (median 34.35) compared to keyword-only prompts (median 23.60). Similarly, the FKGL indicated a lower grade level for plain language prompts (median 12.05) versus keyword-only (median 14.50), with both differences achieving statistical significance. CONCLUSION: Our findings suggest that using conversational prompts can enhance the readability of AI-generated medical information on fragility fractures. Clinicians and content creators should consider this approach when using AI for patient education to optimize comprehension.
引用
- Akkan H, Seyyar GK. Improving readability in AI-generated medical information on fragility fractures: the role of prompt wording on ChatGPT's responses. Osteoporos Int. 2025. PMID: 39777491. doi:10.1007/s00198-024-07358-0
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。