指南
不错
正确性
计算机科学
基线(sea)
医学
图形
范围(计算机科学)
临床试验
人工智能
管道(软件)
健康信息学
临床决策支持系统
软件部署
排名(信息检索)
钥匙(锁)
知识翻译
梅德林
卓越
队列
肾脏疾病
可读性
概率逻辑
术语
数据挖掘
翻译研究信息学
依赖关系图
机器学习
鼻窦CT
以患者为中心的结果
数据科学
作者
M. Berkan Sesen,Joshua Au Yeung,Elham Asgari
出处
期刊:
[BMJ]
日期:2026-11-01
卷期号:2 (1): e000041-e000041
被引量:2
标识
DOI:10.1136/bmjdh-2026-000041
摘要
Objective Chronic kidney disease (CKD) is a progressive condition requiring evidence-based management, but adherence to complex guidelines remains challenging. Large Language Models (LLMs) could support clinical decision-making, yet their unreliability limits direct use. This study aimed to evaluate whether Retrieval-Augmented Generation (RAG), particularly a knowledge graph-enhanced pipeline (GraphRAG), improves guideline-based clinical decision support (CDS) in CKD management.Methods and analysis We compared three approaches: a baseline LLM (GPT-4o), a vector-indexed RAG pipeline and a GraphRAG pipeline. Each model answered nine clinically relevant questions for a synthetic cohort of 70 CKD patients. Outputs were assessed for clinical correctness, patient specificity and clarity using both clinician-led evaluations and an LLM-as-Judge framework.Results RAG achieved higher clinician-rated correctness than the baseline LLM (76.6% vs 70.8%), with GraphRAG showing a similar improvement (75.6%). GraphRAG produced the most patient-specific responses but was associated with substantially longer outputs and reduced clarity. Response length was strongly correlated with both specificity and clarity, indicating that this trade-off is largely length-driven. Agreement between clinician and LLM-based evaluation varied by task type (Cohen’s kappa 0.13–0.97), with lower agreement for open-ended tasks. All retrieval-based methods were constrained by the scope of the indexed guideline.Conclusions RAG and GraphRAG provide a scalable, auditable foundation for guideline-aligned CDS in CKD. RAG showed higher clinician-rated correctness, while GraphRAG improved patient specificity without a corresponding gain in correctness. Trade-offs between specificity and clarity were largely driven by response length. Effective deployment will require robust content management, calibrated evaluation frameworks and integration within clinical governance structures.
科研通智能强力驱动
Strongly Powered by AbleSci AI