@inproceedings{liu-etal-2026-jointcoder,
    title = "{J}oint{C}oder: Exploring Automated {ICD} Coding on Real-World {C}hinese {EHR}s with a Multi-Agent Framework",
    author = "Liu, Kangjun  and
      Li, Zhenyu  and
      Wang, Jianlei  and
      Guan, Hongjiao  and
      Lian, Ying  and
      Chen, Guoqiang  and
      Xin, Tao  and
      Lu, Wenpeng",
    editor = "Durrett, Greg  and
      Jian, Ping",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-demo.26/",
    pages = "263--274",
    ISBN = "979-8-89176-392-0",
    abstract = "Automated ICD coding is a critical task for standardizing clinical information from electronic health records (EHRs) and supporting downstream healthcare administration.However, existing automated ICD coding systems face several fundamental challenges. First, the majority of existing research focuses on English ICD tasks, with limited attention to Chinese-language clinical contexts due to the scarcity of publicly available Chinese ICD datasets. Second, most approaches primarily target disease coding, overlooking procedure coding as well as the multi-stage workflows followed in real-world clinical practice. Moreover, many recent methods rely heavily on closed-source large language models or substantial computational resources, which limits their scalability and deployability in clinical environments.To address these gaps, this paper proposes \textit{JointCoder}, which includes a real-world Chinese ICD coding dataset and a multi-agent framework that reformulates automated ICD coding as a joint disease-procedure coding task. JointCoder explicitly models real-world clinical coding workflows through stage-wise agent collaboration.All agents are instantiated using locally deployed 1.7B-parameter models, enabling scalable and privacy-preserving deployment.Extensive experiments on real-world Chinese ICD coding datasets demonstrate JointCoder{'}s superiority over state-of-the-art baselines across all evaluation metrics."
}