用知识图谱增强大模型，自动理解儿科牙科病历并安全推荐抗生素。
Knowledge-Guided Large Language Model for Automatic Pediatric Dental Record Understanding and Safe Antibiotic Recommendation
- 融合知识图谱与检索增强生成，从病历中提取结构化信息。
- 在3.2万份病历上测试，抗生素推荐准确率提升6.6%，不安全建议减少50%。
- 适合临床决策支持系统开发者和儿科医疗AI研究者使用。
准确理解儿科牙科临床记录并安全开具抗生素仍是牙科信息学中的长期挑战。传统基于规则的临床决策支持系统难以应对非结构化牙科描述、影像报告不全及复杂的用药安全约束。为此，本研究提出一种知识引导的大语言模型（KG-LLM），整合儿科牙科知识图谱、检索增强生成（RAG）及多阶段安全验证流程，实现基于证据的抗生素推荐。该框架首先通过临床命名实体识别与关系抽取模块，从牙科笔记和放射报告中提取结构化实体与关系；随后从知识图谱中检索相关指南、药物安全规则及历史相似病例，输入LLM进行诊断摘要与剂量-药物-时长预测；安全保障通过双层机制实现：结合确定性规则检查与学习型分类器，检测过敏、禁忌症和用药错误。在32,000份去标识化儿科牙科就诊记录上的实验表明，相较于领域适配的Llama-2基线模型，KG-LLM在病历理解性能（F1: 0.914 vs. 0.867）、药物剂量时长预测准确率（Top-1: 0.782 vs. 0.716）方面均有提升，并使不安全抗生素建议减少50%。总结质量、推荐准确率与全局安全评分的综合评估进一步验证了系统的鲁棒性。消融分析显示，知识图谱、RAG与安全模块均对临床可靠性与可解释性有显著贡献。
原文摘要 · Abstract (English)
Accurate interpretation of pediatric dental clinical records and safe antibiotic prescribing remain persistent challenges in dental informatics. Traditional rule-based clinical decision support systems struggle with unstructured dental narratives, incomplete radiographic descriptions, and complex safety constraints. To address these limitations, this study proposes a Knowledge-Guided Large Language Model (KG-LLM) that integrates a pediatric dental knowledge graph, retrieval-augmented generation (RAG), and a multi-stage safety validation pipeline for evidence-grounded antibiotic recommendation. The framework first employs a clinical NER/RE module to extract structured entities and relations from dental notes and radiology reports. Relevant guidelines, drug-safety rules, and analogous historical cases are subsequently retrieved from the knowledge graph and supplied to the LLM for diagnostic summarization and dose-drug-duration prediction. Safety assurance is achieved through a dual-layer validation mechanism combining deterministic rule checking with a learned classifier for detecting allergies, contraindications, and dosing errors. Experiments on 32,000 de-identified pediatric dental visit records demonstrate the effectiveness of the proposed approach. Compared with a domain-adapted Llama-2 clinical baseline, KG-LLM improves record-understanding performance (F1: 0.914 vs. 0.867), drug-dose-duration accuracy (Top-1: 0.782 vs. 0.716), and reduces unsafe antibiotic suggestions by 50%. Additional evaluation across summary quality, recommendation accuracy, and global safety scores further confirms the robustness of the system. Ablation analyses indicate that the knowledge graph, RAG, and safety modules each contribute substantially to clinical reliability and interpretability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。