Augmenting large language models with clinical knowledge graph for personalized perioperative fluid therapy question answering

作者：Jie Song, Jinhua Feng, Yuxin Zhang, Cheng Bi, Xin Zheng, Zhichuan Xu, J Du, Mengqiao He, Meng Xiao, Xiaoran Li, Qiongfang Cao, Chi Zhang, Hao Yang (328526), Rongrong Wu, Bairong Shen · 发表于：PLOS Digital Health · 年份：2026 · DOI：10.1371/journal.pdig.0001474 · 被引用次数：1 · 研究领域：Topic Modeling、Artificial Intelligence in Healthcare and Education、Machine Learning in Healthcare

Personalized perioperative fluid therapy is important for reducing postoperative complications and adverse outcomes. Although large language models (LLMs) show promise in healthcare, their application in fluid therapy remains challenged by hallucinations, limited domain-specific knowledge, and insufficient personalization. To address these limitations, Retrieval-Augmented Generation (RAG) is an effective method, while Knowledge Graphs (KGs) provide more accurate and reliable information. In this paper, we constructed a Personalized Fluid Therapy Knowledge Graph (PFTKG) comprising 6,490 entities and 15,687 relationships, and adapted GraphRAG, a graph-based RAG strategy that employs community detection and recursive summarization to support finding-level retrieval of clinically relevant information. We compared GraphRAG with document-based retrieval-augmented generation (DocRAG) and mainstream prompting strategies, including Vanilla, Chain-of-Thought (CoT), and Reflection-of-Thoughts (RoT), across three LLMs: GPT-4o, Claude Opus 4, and Gemini 2.5 Pro. Performance was evaluated using a 300-question knowledge-based question set and a 262-question retrospective case-based question set derived from 206 abdominal surgery patients. Evaluation included accuracy, honesty, error composition, response length, and response time. On the knowledge-based question set, GraphRAG achieved the highest average accuracy: 96.89% for multiple-choice questions and 66.44% for open-ended questions. On ...