ICU警报管理数字化与智能化的研究进展

doi:10.3761/j.issn.2096-7446.2025.03.022

摘要/Abstract

摘要：

ICU警报管理是患者ICU住院期间重要的安全保障。受益于人工智能、机器学习、5G等技术的发展与应用，近年来，ICU警报已不局限于传统监护警报功能。该文对ICU警报技术发展历史、ICU常见警报系统与局限性、数字化管理下的数据自动记录与安全存储、数据集成与分析助力智慧警报、数据驱动下从指标警报到风险预警、智能穿戴助力警报万物互联、智能学习与运算减少错误警报、基于医患个体化需求的智能警报管理、现存问题与未来挑战进行综述，以期增加智能警报在治疗和预防中的交互，使患者得到最佳监护。

关键词: 警报管理, 重症监护室, 警报疲劳, 综述文献（主题）

Abstract:

ICU alarm management is an important safety guarantee for patients during ICU stay. Benefiting from the development and application of artificial intelligence，machine learning，5G and other technologies in recent years，ICU alerts are no longer limited to the traditional guardianship alert function. This paper reviewed the history of ICU alarm technology，common alarm systems and limitations in ICU，automatic data recording and safe storage under digital management，data integration and analysis for smart alarms，data-driven indicator alarms to risk warnings，smart wearable devices for alarms in the Internet of Things，smart learning and algorithms to reduce false alarms，smart alarm management based on individualized needs of patients and doctors，existing problems and future challenges. The aim is to increase the interaction of smart alerts in treatment and prevention for optimal patient monitoring.

Key words: Alarm Management, Intensive Care Unit, Alarm Fatigue, Review Literature as Topic

翁成杰, 潘向滢, 王金宁, 金佳家, 赵雪红. ICU警报管理数字化与智能化的研究进展[J]. 中华急危重症护理杂志, 2025, 6(3): 380-384.

WENG Chengjie, PAN Xiangying, WANG Jinning, JIN Jiajia, ZHAO Xuehong. Research progress on digitization and intelligence of ICU alarm management[J]. Chinese Journal of Emergency and Critical Care Nursing, 2025, 6(3): 380-384.

参考文献 35

[1]	Bosma S, Christopher R. Implementing a unit-based alarm management bundle for critical care nurses[J]. Crit Care Nurse, 2023, 43(2):36-45. doi: 10.4037/ccn2023418 pmid: 37001877
[2]	Ferrara P, Carelli L, Ruta F, et al. Alarm fatigue in nursing students undertaking clinical training in intensive care units:a multicenter study[J]. Med Lav, 2023, 114(2):e2023015.
[3]	Gündoğan G, Erdağı Oral S. The effects of alarm fatigue on the tendency to make medical errors in nurses working in intensive care units[J]. Nurs Crit Care, 2023, 28(6):996-1003. doi: 10.1111/nicc.12969 pmid: 37632222
[4]	张茂. 未来智慧ICU的建设[J]. 中华医学信息导报, 2022, 37(6):16.
	Zhang M. Construction of future smart ICU[J]. China Med Issues, 2022, 37(6):16.
[5]	潘盼, 程海博, 解立新. 智慧化ICU病房建设:未来是否可及[J]. 中华结核和呼吸杂志, 2023, 46(9):851-853.
	Pan P, Cheng HB, Xie LX. Intelligent intensive care unit design:will it be accessible in the future[J]. Chin J Tuberc Respir Dis, 2023, 46(9):851-853.
[6]	潘盼, 解立新. 智慧重症监护病房助力重症医疗可及性[J]. 中华医学杂志, 2023, 103(26):1966-1969.
	Pan P, Xie LX. Intelligent intensive care unit makes medicine more accessible[J]. Natl Med J China, 2023, 103(26):1966-1969.
[7]	Reisner-Sénélar L. The birth of intensive care medicine:Björn Ibsen’s records[J]. Intensive Care Med, 2011, 37(7):1084-1086. doi: 10.1007/s00134-011-2235-z pmid: 21611906
[8]	Clemmer TP. Computers in the ICU:where we started and where we are now[J]. J Crit Care, 2004, 19(4):201-207. pmid: 15648035
[9]	Hyland SL, Faltys M, Hüser M, et al. Early prediction of circulatory failure in the intensive care unit using machine learning[J]. Nat Med, 2020, 26(3):364-373. doi: 10.1038/s41591-020-0789-4 pmid: 32152583
[10]	阮萍, 周虹, 来岚, 等. 基于多感知混合现实技术的智能化急诊科危急值辅助决策系统的构建及应用[J]. 中华危重症医学杂志(电子版), 2022, 15(4):318-320.
	Ruan P, Zhou H, Lai L, et al. Construction and application of intelligent emergency department critical value assistant decision system based on multi-perception mixed reality technology[J]. Chin J Crit Care Med(Electron Ed), 2022, 15(4):318-320.
[11]	Wong A, Young AT, Liang AS, et al. Development and validation of an electronic health record-based machine learning model to estimate delirium risk in newly hospitalized patients without known cognitive impairment[J]. JAMA Netw Open, 2018, 1(4):e181018.
[12]	Dung-Hung C, Tian C, Jiang ZY, et al. External validation of a machine learning model to predict hemodynamic instability in intensive care unit[J]. Crit Care, 2022, 26(1):215.
[13]	Alistair Johnson. MIMIC-IV[EB/OL]. (2024-07-23)[2024-08-30]. https://physionet.org/content/mimiciv/3.0/.
[14]	Poncette AS, Mosch L, Spies C, et al. Improvements in patient monitoring in the intensive care unit:survey study[J]. J Med Internet Res, 2020, 22(6):e19091.
[15]	申秋, 张云, 吴兆华. 基于云技术的重症监护室监护设备报警系统构建及其在患者管理中的效能分析[J]. 中国医学装备, 2023, 20(11):177-180.
	Shen Q, Zhang Y, Wu ZH. Construction of ICU monitoring equipment alarm system based on cloud technology and analysis of its application in ICU patient management[J]. China Med Equip, 2023, 20(11):177-180.
[16]	王陆, 袁睿, 杨萌萌, 等. 大数据背景下关于重症医学研究生培养的思考[J]. 中国继续医学教育, 2019, 11(7):43-45.
	Wang L, Yuan R, Yang MM, et al. Thoughts on the cultivation of critical medicine graduate students under the background of big data[J]. China Continuing Med Educ, 2019, 11(7):43-45.
[17]	朱功绪, 李云妹, 陈晓辉, 等. 基于大数据的急诊临床科研一体化平台建设[J]. 中华危重病急救医学, 2023, 35(11):1218-1222.
	Zhu GX, Li YM, Chen XH, et al. Construction of integrated platform for emergency clinical scientific research based on big data[J]. Chin Crit Care Med, 2023, 35(11):1218-1222.
[18]	Bawua LK, Miaskowski C, Suba S, et al. Thoracic impedance pneumography-derived respiratory alarms and associated patient characteristics[J]. Am J Crit Care, 2022, 31(5):355-365. doi: 10.4037/ajcc2022295 pmid: 36045046
[19]	Cho KJ, Kim JS, Lee DH, et al. Prospective,multicenter validation of the deep learning-based cardiac arrest risk management system for predicting in-hospital cardiac arrest or unplanned intensive care unit transfer in patients admitted to general wards[J]. Crit Care, 2023, 27(1):346.
[20]	Rusin CG, Acosta SI, Vu EL, et al. Automated prediction of cardiorespiratory deterioration in patients with single ventricle[J]. J Am Coll Cardiol, 2021, 77(25):3184-3192. doi: 10.1016/j.jacc.2021.04.072 pmid: 34167643
[21]	Shashikumar SP, Josef CS, Sharma A, et al. DeepAISE-An interpretable and recurrent neural survival model for early prediction of sepsis[J]. Artif Intell Med, 2021, 113:102036.
[22]	Liu ZY, Khojandi A, Mohammed A, et al. HeMA:a hierarchically enriched machine learning approach for managing false alarms in real time:a sepsis prediction case study[J]. Comput Biol Med, 2021, 131:104255.
[23]	Sangari A, Bingham MA, Cummins M, et al. A spatiotemporal and multisensory approach to designing wearable clinical ICU alarms[J]. J Med Syst, 2023, 47(1):105. doi: 10.1007/s10916-023-01997-2 pmid: 37847469
[24]	Zasuwa GA, Yee J, Passalacqua KD, et al. Remote monitoring of sustained low-efficiency dialysis(SLED) machines in intensive care unit[J]. Kidney Med, 2022, 4(5):100452.
[25]	Chromik J, Klopfenstein SAI, Pfitzner B, et al. Computational approaches to alleviate alarm fatigue in intensive care medicine:a systematic literature review[J]. Front Digit Health, 2022, 4:843747.
[26]	Fernandes C, Miles S, Lucena CJP. Detecting false alarms by analyzing alarm-context information:algorithm development and validation[J]. JMIR Med Inform, 2020, 8(5):e15407.
[27]	Broer SDL, Cramer SJE, Tan RNGB, et al. Minimising alarm pressure on a single room NICU through automated withdrawal of resolved alarms[J]. Acta Paediatr, 2024, 113(2):206-211.
[28]	Rozenes S, Fux A, Kagan I, et al. Alert-grouping:smart personalization of monitoring system thresholds to help healthcare teams struggle with alarm fatigue in intensive care[J]. J Med Syst, 2023, 47(1):113. doi: 10.1007/s10916-023-02010-6 pmid: 37934335
[29]	Zhou YR, Zhao GS, Li J, et al. A contrastive learning approach forICU false arrhythmiaalarm reduction[J]. Sci Rep, 2022, 12(1):4689.
[30]	Bollepalli SC, Sevakula RK, Au-Yeung WM, et al. Real-time arrhythmia detection using hybrid convolutional neural networks[J]. J Am Heart Assoc, 2021, 10(23):e023222.
[31]	Hever G, Cohen L, O’Connor MF, et al. Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU[J]. J Clin Monit Comput, 2020, 34(2):339-352. doi: 10.1007/s10877-019-00307-x pmid: 30955160
[32]	Manna T, Swetapadma A, Abdar M. Decision tree predictive learner-based approach for false alarm detection in ICU[J]. J Med Syst, 2019, 43(7):191. doi: 10.1007/s10916-019-1337-y pmid: 31115734
[33]	Pelter MM, Carey MG, Al-Zaiti S, et al. An annotated ventricular tachycardia(VT) alarm database:toward a uniform standard for optimizing automated VT identification in hospitalized patients[J]. Ann Noninvasive Electrocardiol, 2023, 28(4):e13054.
[34]	陈妞, 陈莹, 郭瑾, 等. 人工智能在危重症护理中的应用现状及挑战[J]. 中华急危重症护理杂志, 2022, 3(3):276-279.
	Chen N, Chen Y, Guo J, et al. The application and challenge of artificial intelligence in critical care[J]. Chin J Emerg Crit Care Nurs, 2022, 3(3):276-279.
[35]	李冬凉, 赖昱臣, 张薇薇, 等. 我国转化医学国家重大科技基础设施建设初探[J]. 上海交通大学学报(医学版), 2020, 40(6):701-706.
	Li DL, Lai YC, Zhang WW, et al. Preliminary study on the construction of national major science and technology infrastructure for translational medicine in China[J]. J Shanghai Jiaotong Univ Med Sci, 2020, 40(6):701-706.