arXiv：cs.CL· Joseph Paul Cohen, Raj Shah, Han-Chin Shing, Fang Wang, Susan Nguyen, Chaitanya Shivade, Jack Moriarty·· 6 小时前AI 评分38
用自动化医生问询弥补门诊临床文档缺口：LLM 的 DAU 查询循环研究
Closing Ambient Clinical Documentation Gaps with Automated Provider Queries
AI 导读
研究提出用 LLM 自动化临床文档的查询循环 DAU（Draft、Ask、Update），覆盖病历起草、ICD-10 编码与医嘱提取三项任务。对 3,000 次真实就诊的审计定位了文档缺失来源，并据此在公开数据上构建五个转录退化基准。
正文
Abstract: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.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07502 [cs.CL] |
| (or arXiv:2610.07502v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07502 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Joseph Paul Cohen [view email]
[v1]
Mon, 5 Oct 2026 23:07:16 UTC (192 KB)
来源：arXiv：cs.CL · arxiv.org