发表机构
Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出DAU循环，利用LLM自动化临床文档中的提供者查询，通过构建退化基准和分析真实对话，发现有用问题预测器具有任务特异性，且约9%的查询轮次有害，强调学习“何时不问”的重要性。
AI 中文摘要
提供者查询是临床文档专家发送给医生的澄清请求，用于弥合临床记录中的缺口并确保准确计费。先前的工作在假设完整转录本的前提下，自动化了笔记起草、ICD-10编码和医嘱提取，但这些缺口仍未得到解决。我们研究大型语言模型（LLM）是否能在上述三项任务中自动化查询循环，称为DAU（起草、询问、更新）。对3,000次真实就诊的审计识别了缺失文档的来源，并据此在公共数据上构建了五个转录本退化基准。通过分析真实对话中的21,000个澄清轮次，我们发现有用问题预测器具有任务特异性：预言机置信度占主导地位，但笔记完整性仅需简单的回忆性问题，而ICD-10编码则需要更难的、多选项的问题。约9%的轮次会损害性能，这主要由冗余问题和仍触发重写的非答案驱动。部署取决于学习“何时不问”与“问什么”同等重要。
英文摘要
Provider queries are clarifying requests sent by clinical documentation specialists to physicians to close gaps in the clinical note and ensure accurate billing. Prior work automates note drafting, ICD-10 coding, and order extraction assuming a complete transcript, leaving these gaps unaddressed. We study whether an LLM can automate the query loop, termed DAU (Draft, Ask, Update), across those three tasks. An audit of 3,000 real visits identifies the sources of missing documentation, from which we build five transcript-degradation benchmarks on public data. Analyzing 21k clarification turns on real conversations, we find useful-question predictors are task-specific: oracle confidence dominates, but note completeness needs only simple recall questions while ICD-10 coding needs harder, multi-option ones. About 9% of turns hurt performance, driven by redundant questions and non-answers that still trigger a rewrite. Deployment depends on learning "when not" as much as "what to" ask.
