医学知识并非万能：当医学问答变为情境化患者辅助
Medical Knowledge Is Not All You Need: When Medical Q&A Becomes Situated Patient Assistance
浏览论文内容
中文总结 AI 辅助
本研究通过皮肤癌患者术后护理实验，揭示医学问答可靠性需依赖情境信息，提出情境化医疗辅助设计空间以连接系统与患者能力。
中文摘要 AI 辅助
在医学问答中，可靠性通常通过将回答基于权威医学信息来实现。我们表明，当问答嵌入到持续护理中时，可靠性不仅取决于系统在医学上知道什么。在一项涉及73名皮肤癌患者进行术后伤口护理的研究中，41.9%的需要回答的问题依赖于手术之外的信息，包括视觉或身体状态、环境背景或先前行为。这些需求在不同患者间有所差异，这与患者将辅助系统招募到不同信息角色的现象一致。随后，我们将这些问题重放给七个大型语言模型，同时添加手术和术后指导。错误仍然显著，包括在明确防护措施下也将未知状态视为已知；在完整手术背景下，七个模型中有六个更倾向于过早引入后续步骤。基于这些发现，我们提出了一个情境化医疗辅助的设计空间，将辅助系统和患者各自能可靠确定的内容与所提供的辅助形式联系起来。
英文摘要
Reliability in medical Q&A is often pursued by grounding responses in authoritative medical information. We show that when Q&A is embedded within ongoing care, reliability depends on more than what the system knows medically. In a study with 73 skin cancer patients practicing postoperative wound care, 41.9% of response-requiring questions depended on information beyond the procedure, including visual or physical state, environmental context, or prior actions. These demands varied across patients, consistent with patients recruiting the assistant into different informational roles. We then replayed the questions to seven LLMs while adding procedural and postoperative guidance. Errors remained substantial, including treating unknown states as known, even under explicit guardrails; with full procedural context, six of seven models more often introduced later steps prematurely. Based on these findings, we propose a design space for situated medical assistance that connects what the assistant and patient can each reliably establish to the form of assistance provided.
发表机构
- University Hospitals of Cleveland（克利夫兰大学医院）
- Case Western Reserve University School of Medicine（凯斯西储大学医学院）
- Case Western Reserve University（凯斯西储大学）
- University Hospitals Cleveland Medical Center（克利夫兰大学医疗中心）
机构由 AI 辅助整理，请以论文原文为准。
