呼吸机警报管理知识图谱和智能问答系统的构建及可用性评价

doi:10.3761/j.issn.2096-7446.2024.06.003

摘要/Abstract

摘要：

目的构建基于知识图谱的ICU呼吸机警报管理智能问答系统，提高医护人员对呼吸机警报的识别和处理能力，确保患者安全和治疗效果。方法整合学术论文、指南、标准、临床实践案例、设备用户手册等多种来源知识，通过专家访谈和专家会议制订知识框架。采用自动化和人工审核相结合的方式进行实体构建、知识抽取、融合，以“实体-关系-实体”三元组数据输入Neo4j图数据库进行存储。并针对自然语言问题进行语义理解和解析，创建知识图谱Cypher查询语句，使知识图谱具有智能问答功能。采用系统可用性量表进行问答系统可用性测试。结果构建的知识图谱涵盖通气模式、参数设置、警报类型、警报原因、处理措施、设备维护6个领域，包含206个知识实体、15种实体间关系及256条知识点的联接，并基于知识图谱开发了Web端智能问答系统。系统可用性量表得分为（76.44±13.17）分。结论该研究应用知识图谱构建的呼吸机警报管理智能问答系统具有较好的科学性和可用性。通过知识体系可视化、智能问答、个性化推荐等功能，为医护人员提供了有效识别、精准解除警报的辅助决策支持工具，有利于提高临床警报安全。

关键词: 重症监护病房, 通气机, 机械, 警报管理, 知识图谱, 智能问答系统

Abstract:

Objective To construct a knowledge graph based intelligent Q&A system for ventilator alarm management in intensive care units，to improve healthcare professionals’ ability to recognize and handle ventilator alarms，and to enhance patient safety and treatment outcomes. Methods We integrated knowledge from various sources such as thesis，guidelines，standards，clinical practice cases，device user manuals，etc.，and developed the knowledge framework through expert interviews and expert meetings. We used a combination of automation and manual review to construct entities，extract and integrate knowledge，and input data into the Neo4j graph database as “entity-relationship-entity” ternary data for storage. And for the semantic understanding and parsing of natural language questions，the knowledge graph Cypher query statement was created，so that the knowledge graph has intelligent question and answer functions. The system usability scale was used to test the usability of the Q&A system. Results The constructed knowledge graph covered six fields，including ventilation mode，parameter settings，alarm types，alarm causes，treatment measures，and equipment maintenance，and contains 206 knowledge entities，15 kinds of inter-entity relationships，and 256 linkages of knowledge points，and a web-side intelligent Q&A system has been developed based on the knowledge graph. The mean score of the System Usability Scale was （76.44 ± 13.17）. Conclusion The knowledge graph based intelligent Q&A system for ventilator alarm management constructed in this study has certain scientific validity and usability. Through the visualization of knowledge system functions，intelligent question and answer，and personalized recommendation，it provides an auxiliary decision support tool for healthcare professionals to effectively identify and accurately deactivate the alarms，and improves the safety of clinical alarms.

Key words: Intensive Care Units, Ventilators, Mechanical, Alarm Management, Knowledge Graph, Intelligent Question Answering System

王瀚敏, 张玉美, 王巧红, 王建, 余璐江, 李莉. 呼吸机警报管理知识图谱和智能问答系统的构建及可用性评价[J]. 中华急危重症护理杂志, 2025, 6(6): 659-664.

WANG Hanmin, ZHANG Yumei, WANG Qiaohong, WANG Jian, YU Lujiang, LI Li. Construction and usability evaluation of knowledge graph and intelligent Q&A system for ventilator alarm management[J]. Chinese Journal of Emergency and Critical Care Nursing, 2025, 6(6): 659-664.

图/表 3

参考文献 23

[1]	尹曾珍, 岳丽青, 李珍,等. 重症监护室呼吸机警报管理研究进展[J]. 中国护理管理, 2020, 20(2):241-245.
	Yin ZZ, Yue LQ, Li Z,et al. Research progress on ventilator alarm management in Intensive Care Unit[J]. Chin Nurs Manag, 2020, 20(2):241-245.
[2]	ECRI Institute. 2019 top 10 health technology hazards executive brief:a report from health devices[C]. Plymouth Meeting. PA: ECRI Institute, 2018.
[3]	中国医院协会. 中国医院协会患者安全目标(2019版)[J]. 中国卫生, 2019(12):57-58.
	Chinese Hospital Association. Patient safety goals of the Chinese Hospital Association(2019 edition)[J]. China Health, 2019(12):57-58.
[4]	The Joint Commission. National patient safety goals effective January 2023 for the critical access hospital program[EB/OL]. (2022-10-27)[2024-12-20]. https://www.jointcommission.org/-/media/tjc/documents/standards/national-patient-safety-goals/2023/npsg_chapter_cah_jan2023.pdf.
[5]	梁国鹏, 杨福, 康焰,等. 中国呼吸治疗的现状与发展[J]. 中国呼吸与危重监护杂志, 2020, 19(6):533-535.
	Liang GP, Yang F, Kang Y,et al. Current situation and development of respiratory therapy in China[J]. Chin J Respir Crit Care Med, 2020, 19(6):533-535.
[6]	Walsh BK, Waugh JB. Alarm strategies and surveillance for mechanical ventilation[J]. Respir Care, 2020, 65(6):820-831. doi: 10.4187/respcare.07546 pmid: 32457173
[7]	仇露露, 张洪涛, 万薇薇,等. ICU患者呼吸机警报管理的最佳证据总结[J]. 中华护理杂志, 2023, 58(23):2864-2872. doi: 10.3761/j.issn.0254-1769.2023.23.007
	Qiu LL, Zhang HT, Wan WW,et al. Summary of best evidence for ventilator alarm management for ICU patients[J]. Chin J Nurs, 2023, 58(23):2864-2872. doi: 10.3761/j.issn.0254-1769.2023.23.007
[8]	Li Q, Li JX, Wu J,et al. Triplet-aware graph neural networks for factorized multi-modal knowledge graph entity alignment[J]. Neural Netw, 2024, 179:106479.
[9]	付子轩, 周鹏, 任海燕,等. 基于知识图谱的中西医结合急腹症诊疗推理分析[J]. 中国实验方剂学杂志, 2023, 29(11):190-199.
	Fu ZX, Zhou P, Ren HY,et al. Diagnosis and treatment reasoning of integrated traditional Chinese and western medicine against acute abdomen based on knowledge graph[J]. Chin J Exp Tradit Med Formulae, 2023, 29(11):190-199.
[10]	王子豪. 基于知识图谱和因果推理的医疗诊断模型[D]. 长春: 吉林大学, 2023.
	Wang ZH. Medical diagnosis model based on knowledge graph andcausal reasoning[D]. Changchun: Jilin University, 2023.
[11]	陈兰珍, 郑泾飞, 王华珍,等. 基于护理知识图谱的智能问答系统研究[J]. 医学信息, 2024, 37(11):58-62,68.
	Chen LZ, Zheng JF, Wang HZ,et al. Research on intelligent question answering system based on nursing knowledge graph[J]. J Med Inf, 2024, 37(11):58-62,68.
[12]	张山, 高丽, 王艳玲,等. 基于知识图谱的 “四维”《内科护理学》智慧服务体系的构建[J]. 护士进修杂志, 2024, 39(15):1644-1649.
	Zhang S, Gao L, Wang YL,et al. Construction of the intelligent service system of “four-dimensional” Internal Medicine Nursing based on the knowledge graph[J]. J Nurses Train, 2024, 39(15):1644-1649.
[13]	颜钰, 龚姝, 段棣飞,等. 知识图谱在慢性病患者饮食管理中的应用进展[J]. 中华护理杂志, 2024, 59(6):753-757. doi: 10.3761/j.issn.0254-1769.2024.06.016
	Yan Y, Gong S, Duan DF,et al. Application and progress of knowledge graphs in dietary management of patients with chronic diseases[J]. Chin J Nurs, 2024, 59(6):753-757. doi: 10.3761/j.issn.0254-1769.2024.06.016
[14]	Borsci S, Federici S, Lauriola M. On the dimensionality of the System Usability Scale:a test of alternative measurement models[J]. Cogn process, 2009, 10(3):193-197.
[15]	Wang YH, Lei T, Liu XX. Chinese system usability scale:translation,revision,psychological measurement[J]. Int J Hum, 2020, 36(10):953-963.
[16]	宋海贝, 温川飙, 程小恩. 基于AI的中医舌象面象辅助诊疗系统构建[J]. 时珍国医国药, 2020, 31(2):502-505.
	Song HB, Wen CB, Cheng XE. Construction of AI-based tongue and facial imageassisted diagnosis and treatment system of Traditional Chinese Medicine[J]. Lishizhen Med Mater Med Res, 2020, 31(2):502-505.
[17]	林怡, 王斌, 许家佗,等. 基于面部图像特征融合的中医望诊面色分类研究[J]. 实用临床医药杂志, 2020, 24(14):1-5.
	Lin Y, Wang B, Xu JT,et al. Facial color classification of traditional Chinese medicine inspection based on fusion of facial image features[J]. J Clin Med Pract, 2020, 24(14):1-5.
[18]	魏珂, 司春婴, 王贺,等. 人工智能在心血管疾病诊断及风险预测中的研究进展[J]. 世界科学技术-中医药现代化, 2020, 22(10):3576-3582.
	Wei K, Si CY, Wang H,et al. Research progress of artificial intelligence for cardiovascular disease diagnosis and risk prediction[J]. World Sci Tech-Modern TCM, 2020, 22(10):3576-3582.
[19]	杨罗宽, 龚敏, 刘麒麟. 基于Wi-Fi的医疗设备物联网采集装置设计[J]. 中国医学装备, 2024, 21(7):182-184.
	Yang LK, Gong M, Liu QL. Design of Wi-Fi-based IoT acquisition device for medical equipment[J]. China Med Equip, 2024, 21(7):182-184.
[20]	嵇泽胜, 刘重斌, 王瑞,等. ICU医疗设备报警疲劳的研究进展[J]. 护士进修杂志, 2020, 35(11):985-987.
	Ji ZS, Liu CB, Wang R,et al. Research progress of alarm fatigue in ICU medical equipment[J]. J Nurses Train, 2020, 35(11):985-987.
[21]	王明达, 吴志生, 朱光辉,等. 燃气轮机故障知识图谱构建方法与应用研究[J]. 中国安全生产科学技术, 2023, 19(11):121-128.
	Wang MD, Wu ZS, Zhu GH,et al. Research on construction method and application of knowledge graph for gas turbine fault[J]. J Saf Sci Technol, 2023, 19(11):121-128.
[22]	王巧红, 杨辉, 程慧,等. 新型冠状病毒肺炎疫情下对护理教育的思考[J]. 中华护理杂志, 2020, 55(S1):719-720.
	Wang QH, Yang H, Cheng H,et al. Reflections on nursing education under thesituation of coronav irus disease 2019 epidemic[J]. Chin J Nurs, 2020, 55(S1):719-720.
[23]	Li BY, Yue LQ, Nie HY,et al. The effect of intelligent management interventions in intensive care units to reduce false alarms:an integrative review[J]. Int J Nurs Sci, 2023, 11(1):133-142.