Go to ACL ARR 2026 January homepageClinDoc Copilot: Enhancing Efficiency and Normalization in Chinese Outpatient Settings
Keywords: Copilot, medical LLM, clinical documentation
Abstract: Clinical documentation in Chinese outpatient settings is a legally regulated and time-intensive task, requiring physicians to produce records that are both efficient and auditable. Existing medical large language models demonstrate strong performance on medical benchmarks. However, their generated content cannot be directly adopted in clinical documentation due to legal risk, as responsibility for medical records cannot be delegated to or assumed by autonomous models. We present ClinDoc Copilot, a physician-centered assistant designed to support outpatient documentation. We evaluate ClinDoc Copilot in realistic simulated outpatient scenarios with licensed physicians and clinical trainees. Results show that the system improves documentation efficiency, terminology standardization, and evidence-grounded traceability. Our work highlights the value of interactive, physician-led AI assistance for clinical documentation in regulated healthcare settings. All code is available at an anonymous repository: https://anonymous.4open.science/r/ClinDoc-Copilot/README.md.
Paper Type: Long
Research Area: Clinical and Biomedical Applications
Research Area Keywords: clinical decision support, clinical and biomedical text summarisation, regulatory and ethical considerations
Contribution Types: Publicly available software and/or pre-trained models
Languages Studied: Chinese, English
Submission Number: 4715
Loading