{
  "abstract": "Inpatient pathways require complex clinical decision-making based on comprehensive patient information, yet research on medical LLMs is limited in this area due to the lack of large-scale datasets. Existing medical benchmarks primarily focused on question-answering and examinations, overlooking the multifaceted nature of inpatient decision-making. To address this gap, we developed the IPDS benchmark, comprising 51,274 cases across 9 triage departments, 17 major disease categories, and 16 treatment options. We further proposed the Multi-Agent Inpatient Pathways (MAP) framework, containing three specialized clinical agents: a triage agent for patient admission, a diagnosis agent for diagnostic decision-making, and a treatment agent for care planning. A chief agent guides and promotes these agents to ensure coordination. Experiments demonstrated that MAP achieved superior alignment with operational protocols compared to state-of-the-art LLMs. The MAP sets a foundation for advancing inpatient support systems, offering significant potential for enhancing operational efficiency and resource planning in healthcare facilities.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Kowloon, Hong Kong SAR",
    "Department of Electronic Engineering, The Chinese University of Hong Kong, New Territories, Hong Kong SAR",
    "Guangzhou Hospital of Integrated Traditional Chinese and Western Medicine, Guangzhou, China",
    "Shenzhen Traditional Chinese Medicine Hospital, Shenzhen, China",
    "Department of Critical Care Medicine, Zhongshan Hospital Fudan University, Shanghai, China",
    "Department of Electronic Engineering, The Chinese University of Hong Kong, New Territories, Hong Kong SAR. yxyuan@ee.cuhk.edu.hk"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Zhen Chen",
      "orcid": "0000-0003-0255-6435"
    },
    {
      "affs": [
        1
      ],
      "name": "Zhihao Peng",
      "orcid": "0000-0001-8273-9527"
    },
    {
      "affs": [
        1
      ],
      "name": "Xusheng Liang"
    },
    {
      "affs": [
        1
      ],
      "name": "Cheng Wang",
      "orcid": "0000-0002-4752-0316"
    },
    {
      "affs": [
        2
      ],
      "name": "Peigan Liang"
    },
    {
      "affs": [
        3
      ],
      "name": "Linsheng Zeng",
      "orcid": "0000-0001-5089-6421"
    },
    {
      "affs": [
        4
      ],
      "name": "Minjie Ju"
    },
    {
      "affs": [
        5
      ],
      "name": "Yixuan Yuan",
      "orcid": "0000-0002-0853-6948"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/27vbayfh1tpgg.bib",
  "cited_by": 17,
  "doi": "10.1038/s44401-026-00085-0",
  "fulltext_url": null,
  "id": "27vbayfh1tpgg",
  "issns": [
    "3005-1959"
  ],
  "landing_url": "https://doi.org/10.1038/s44401-026-00085-0",
  "language": "en",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7163040852",
  "pdf_url": "https://www.nature.com/articles/s44401-026-00085-0.pdf",
  "pmcid": "PMC13336800",
  "pmid": "42527484",
  "published": "2026-06-01",
  "publisher": "Springer Science+Business Media",
  "ris": "https://research.draconitic.com/paper/27vbayfh1tpgg.ris",
  "sources": [
    {
      "first_seen": "2026-11-07T13:20:59Z",
      "native_id": "W7163040852",
      "source": "openalex",
      "url": "https://doi.org/10.1038/s44401-026-00085-0"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "MAP: evaluation and multi-agent enhancement of large language models for inpatient pathways",
  "title_text": "MAP: evaluation and multi-agent enhancement of large language models for inpatient pathways",
  "type": "peer-reviewed",
  "updated_at": "2026-11-08T13:20:51Z",
  "url": "https://research.draconitic.com/paper/27vbayfh1tpgg",
  "venue": "npj Health Systems",
  "versions": []
}