{
  "abstract": "Managing diabetic kidney disease (DKD) is inherently complex, requiring clinicians to synthesize patient history, fluctuating biomarkers, and evolving treatment guidelines. While large language models (LLMs) show promise in medical decision support, their clinical adoption is hindered by factual inaccuracies and a lack of specific reasoning required for individualized patient management. To address this, we developed a hierarchical multi-agent system that integrates a locally deployed retrieval-augmented generation (RAG) framework with a cloud-based advanced reasoning engine, grounding responses in a curated corpus of clinical guidelines. We conducted a multi-center retrospective validation using 267 patient cases. The system’s performance was evaluated against baseline models through a blinded review by twelve independent physicians across clinical dimensions including accuracy, safety, and factuality. Our evaluation reveals that the RAG-enhanced system significantly outperforms unaugmented models in providing accurate, guideline-compliant recommendations. Notably, it substantially reduced safety-critical errors, particularly in identifying medication contraindications related to renal function stages, while achieving high inter-rater reliability. This study demonstrates that anchoring LLMs with authoritative knowledge effectively mitigates hallucination risks and enhances clinical reliability. The proposed framework functions as a reliable on-demand assistant for DKD management, providing guideline-grounded decision support for primary care providers.",
  "abstract_shown": true,
  "affiliations": [
    "Department of Pathology, The First Affiliated Hospital, Fujian Medical University, Fuzhou, China",
    "Department of Pathology, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou, China",
    "Institute of Molecular Medicine, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China",
    "Department of Neurosurgery, Shanghai Tenth People’s Hospital, School of Medicine, Tongji University, Shanghai, China",
    "School of Basic Medical Sciences, Tsinghua University, Beijing, China",
    "Zhangzhou Affiliated Hospital of Fujian Medical University, Zhangzhou, China",
    "Fujian Medical University Provincial Clinical Medical College, Fuzhou, China",
    "The Second Affiliated Hospital of Fujian Medical University, Quanzhou, China",
    "Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, China",
    "Department of Endocrinology, Sanya Central Hospital, The Third People’s, Hospital of Hainan Province, Sanya, China"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 15,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Xuan Tao"
    },
    {
      "affs": [
        2
      ],
      "name": "Lan Tian"
    },
    {
      "affs": [
        3
      ],
      "name": "Chenhao Fang"
    },
    {
      "affs": [
        4
      ],
      "name": "Jin-hao Li"
    },
    {
      "affs": [
        0
      ],
      "name": "Jia-qi Lin"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Xiao-jie Liu"
    },
    {
      "affs": [
        5
      ],
      "name": "Xin-ying Song"
    },
    {
      "affs": [
        6
      ],
      "name": "Zi-hang Chen"
    },
    {
      "affs": [
        6
      ],
      "name": "Yi-nan Wu"
    },
    {
      "affs": [
        7
      ],
      "name": "Yan-hong Lin"
    },
    {
      "affs": [
        6
      ],
      "name": "Ze-yang Zhu"
    },
    {
      "affs": [
        0
      ],
      "name": "Min-xia Wang"
    },
    {
      "affs": [
        8
      ],
      "name": "Wan-xuan Chen"
    },
    {
      "affs": [
        9
      ],
      "name": "Jian-ya Xu"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Hong Chen"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bjxqwt5xnnwys.bib",
  "cited_by": 1,
  "doi": "10.1038/s41746-026-03035-0",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13748643/",
  "id": "bjxqwt5xnnwys",
  "issns": [
    "2398-6352"
  ],
  "landing_url": "https://doi.org/10.1038/s41746-026-03035-0",
  "language": "en",
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7169732532",
  "pdf_url": null,
  "pmcid": "PMC13748643",
  "pmid": "42477060",
  "published": "2026-07-20",
  "publisher": "Nature Publishing Group",
  "ris": "https://research.draconitic.com/paper/bjxqwt5xnnwys.ris",
  "sources": [
    {
      "first_seen": "2026-11-13T12:26:36Z",
      "native_id": "PMC13748643",
      "source": "pmc",
      "url": "https://doi.org/10.1038/s41746-026-03035-0"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Generating guideline-concordant and safe recommendations for diabetic kidney disease management via a hierarchical retrieval-augmented large language model",
  "title_text": "Generating guideline-concordant and safe recommendations for diabetic kidney disease management via a hierarchical retrieval-augmented large language model",
  "type": "peer-reviewed",
  "updated_at": "2026-11-14T12:21:35Z",
  "url": "https://research.draconitic.com/paper/bjxqwt5xnnwys",
  "venue": "NPJ Digital Medicine",
  "versions": []
}