Scholarlink

<p>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.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generating guideline-concordant and safe recommendations for diabetic kidney disease management via a hierarchical retrieval-augmented large language model

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月20日

查看全文
  • Xuan Tao,
  • Lan Tian,
  • Chenhao Fang,
  • Jin-hao Li,
  • Jia-qi Lin,
  • Xiao-jie Liu,
  • Xin-ying Song,
  • Zi-hang Chen,
  • Yi-nan Wu,
  • Yan-hong Lin,
  • Ze-yang Zhu,
  • Min-xia Wang,
  • Wan-xuan Chen,
  • Jian-ya Xu,
  • Hong Chen

摘要

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.