大语言模型时代面向患者的医学知识简化：以糖尿病为例的案例研究
Medical Knowledge Simplification for Patients in the Era of LLMs: A Case Study on Diabetes
查看机构详情
- Macquarie University（麦考瑞大学）
- Beijing Normal–Hong Kong Baptist University（北京师范大学-香港浸会大学联合国际学院）
- National Tsing Hua University（国立清华大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对患者理解医学信息困难的问题，本文提出基于LLM和RAG的MediClear系统，以糖尿病为例进行案例研究，通过可读性指标和人工评估验证其能有效降低阅读难度并提升用户满意度。
中文摘要 AI 辅助
复杂的医学信息往往难以被患者理解，因此有效的医学知识简化对于提高患者的理解能力、促进知情决策和改善健康结果至关重要。近年来，大语言模型（LLM）的进展为将复杂的医学信息简化为患者友好型语言提供了一种有前景的方法；然而，其在真实世界患者教育中的有效性通过人工评估进行的研究仍不充分。为了探究其实际效果，本文通过实施和评估MediClear——一个基于LLM并结合检索增强生成（RAG）的医学知识简化系统——对糖尿病知识简化进行了案例研究。来自澳大利亚糖尿病协会、世界卫生组织（WHO）、美国糖尿病协会（ADA）、美国国立糖尿病与消化及肾脏疾病研究所（NIDDK）和澳大利亚健康与福利研究所（AIHW）的公开糖尿病相关文章被索引到RAG知识库中，以检索具有临床依据的信息，随后由LLM将其简化为易于患者理解的解释。我们使用标准可读性指标（包括Flesch-Kincaid年级水平（FKGL））评估生成的回答，并开展了一项涉及10名参与者的人工研究。结果表明，MediClear持续将生成回答的阅读水平降至推荐的患者识字范围内，同时实现了较高的用户满意度和未来使用意愿。本案例研究证明了LLM在提高患者教育中医学知识可及性方面的潜力。
英文摘要
Complex medical information is often difficult for patients to understand, making effective medical knowledge simplification essential for improving patient comprehension, informed decision-making, and health outcomes. Recent advances in large language models (LLMs) provide a promising approach for simplifying complex medical information into patient-friendly language; however, their effectiveness in real-world patient education remains insufficiently explored through human evaluation. To investigate their practical effectiveness, this paper presents a case study on diabetes knowledge simplification through the implementation and evaluation of MediClear, an LLM-based medical knowledge simplification system enhanced with Retrieval-Augmented Generation (RAG). Public diabetes-related articles from Diabetes Australia, WHO, American Diabetes Association (ADA), NIDDK, and AIHW are indexed in the RAG knowledge base to retrieve clinically grounded information, which is then simplified by the LLM into accessible patient explanations. We evaluate the generated responses using standard readability metrics, including the Flesch-Kincaid Grade Level (FKGL), and conduct a human study involving 10 participants. Results show that MediClear consistently reduces the reading level of generated responses to the recommended patient literacy range while achieving high user satisfaction and willingness for future use. This case study demonstrates the potential of LLMs to improve the accessibility of medical knowledge for patient education.
