Development and evaluation of Retrieval-Augmented Generation (RAG) and GraphRAG for guideline-based clinical decision support in chronic kidney disease

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]
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
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
111发布了新的文献求助10
刚刚
搜集达人的应助被琳琳林采纳,获得10
刚刚
诚心花生发布了新的文献求助10
刚刚
无所谓菩萨会保佑我完成签到,获得积分10
刚刚
刚刚
1秒前
LL完成签到,获得积分10
1秒前
研友_VZG7GZ的应助被panda采纳,获得10
2秒前
2秒前
3秒前
杨yi完成签到,获得积分10
3秒前
哒哒哒哒哒完成签到,获得积分10
3秒前
3秒前
今后的应助被Lu采纳,获得10
4秒前
4秒前
KevinL完成签到,获得积分20
5秒前
嘻嘻哈哈的应助被馨馨采纳,获得10
5秒前
5秒前
5秒前
Bi完成签到,获得积分10
6秒前
搜集达人的应助被zhang0403采纳,获得10
6秒前
科研通AI6.4的应助被诚心花生采纳,获得10
6秒前
7秒前
7秒前
7秒前
打打的应助被Lily采纳,获得10
7秒前
漾漾完成签到,获得积分10
7秒前
852的应助被jiaweizhao采纳,获得10
7秒前
7秒前
晴空完成签到,获得积分10
8秒前
8秒前
zhikaiyici发布了新的文献求助30
8秒前
水鸟发布了新的文献求助10
8秒前
钟梓袄发布了新的文献求助10
9秒前
9秒前
9秒前
Miro发布了新的文献求助10
9秒前
9秒前
wwwwwl发布了新的文献求助10
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
八旗制度の研究 600
Improving the wear resistance of vehicle gear oil by oil soluble LaF3 nanoparticles and typical additives of gear oil 500
Boundaries and Bodhisattvas 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8183204
求助须知:如何正确求助?哪些是违规求助? 9572434
关于积分的说明 21825655
捐赠科研通 7779988
什么是DOI,文献DOI怎么找? 3433852
关于科研通互助平台的介绍 2558060
邀请新用户注册赠送积分活动 2480148