ISSN 2097-6046（网络）
ISSN 2096-7446（印刷）
CN 10-1655/R
主管：中国科学技术协会
主办：中华护理学会
中华急危重症护理杂志

中华急危重症护理杂志 >

2026 , Vol. 7 >Issue 9: 1082 - 1088

DOI: https://doi.org/10.3761/j.issn.2096-7446.2026.09.008

急危重症智慧护理专题

人工智能在重症护理领域中应用的范围综述

  • 余严超 ,
  • 高欣 ,
  • 翁峰霞 ,
  • 卫建华 ,
  • 桑明 ,
  • 朱永康 ,
  • 陈小艳
展开
  • 1 浙江大学医学院附属第一医院外科监护室 杭州市 310003
    2 英国爱丁堡大学社会科学健康学院 爱丁堡市 EH8 9RQ
余严超：男，本科，护师，E-mail：yyc1092527822@qq.com
作者贡献声明

余严超、高欣：选题设计、文献检索、整理与分析、论文撰写及修改；翁峰霞、卫建华、陈小艳：研究指导、论文修改；桑明、朱永康：论文审阅修改

*翁峰霞，E-mail：wengfengxia@zju.edu.cn

收稿日期: 2025-09-20

  网络出版日期: 2026-08-31

基金资助

浙大一院护理学科建设项目(2022ZYHL033)

收起

Application of artificial intelligence in critical care：a scoping review

  • YU Yanchao ,
  • GAO Xin ,
  • WENG Fengxia ,
  • WEI Jianhua ,
  • SANG Ming ,
  • ZHU Yongkang ,
  • CHEN Xiaoyan
Expand
  • 1 Surgical Intensive Care Unit， the First Affiliated Hospital，Zhejiang University School of Medicine， Hangzhou 310003， China
    2 School of Health in Social Science， University of Edinburgh， Edinburgh EH8 9RQ， UK

Received date: 2025-09-20

  Online published: 2026-08-31

Supported by

Zhejiang University First Hospital Nursing Discipline Development Project(2022ZYHL033)

Fold

摘要

目的 系统梳理人工智能在重症护理领域的研究现状、应用场景、技术挑战及未来发展方向，为人工智能与重症护理的深度融合提供研究方向和理论依据，推动患者预后改善和医疗质量提升。方法 采用Arksey等提出的范围综述框架，检索PubMed、Web of Science、中国知网、万方数据库等数据库中的相关文献，检索时限为建库至2025年4月30日，最终纳入17篇文献。结果 人工智能在重症护理中的应用主要集中在监测预警系统、临床决策支持系统、文档记录自动化、资源分配优化及预测分析模型五大领域。主要挑战包括人工智能模型数据碎片化、泛化能力不足、医护人员对人工智能工具的接受度与使用能力有待提升和伦理隐私等问题。结论 人工智能应用于重症护理领域可显著改善工作流程、提高工作效率，未来研究应着重于多中心数据共享平台的构建、跨学科协作机制的完善，以及以患者为中心的人工智能系统设计，以充分发挥其在提升重症护理质量和效率方面的价值。

关键词： 人工智能; 重症护理; 机器学习; 临床决策支持; 范围综述

本文引用格式

余严超 , 高欣 , 翁峰霞 , 卫建华 , 桑明 , 朱永康 , 陈小艳 . 人工智能在重症护理领域中应用的范围综述[J]. 中华急危重症护理杂志, 2026 , 7(9) : 1082 -1088 . DOI: 10.3761/j.issn.2096-7446.2026.09.008

Abstract

Objective To systematically synthesize the current research status，application scenarios，technical challenges，and future development directions of artificial intelligence（AI） in the field of critical care. This review aims to provide novel research perspectives and theoretical foundations for the in-depth integration of AI and critical care，thereby promoting improvements in patient prognosis and healthcare quality. Methods Using the scoping review framework proposed by Arksey et al.，relevant literature was searched in databases such as PubMed，Web of Science，CNKI，and Wanfang Database，with the search period up to April 30，2025，and a total of 17 articles were ultimately included. Results The applications of AI in critical care primarily focus on five core domains，including monitoring and early warning systems，clinical decision support systems，documentation automation，resource allocation optimization，and predictive analysis models. The primary challenges include data fragmentation in AI models，limited generalization capability，the need to improve medical staff’s acceptance and practical skills with AI tools，as well as ethical and privacy concerns. Conclusion The integration of AI into critical care can significantly optimize workflow efficiency and enhance work performance. Future research should prioritize the establishment of multi-center data sharing platforms，the refinement of interdisciplinary collaboration mechanisms，and the design of patient-centered AI systems，to fully unleash the value of AI in improving the quality and efficiency of critical care services.

Key words： Artificial Intelligence; Critical Care; Machine Learning; Clinical Decision Support; Scoping Review

参考文献

[1] Martinez-Ortigosa A, Martinez-Granados A, Gil-Hernández E, et al. Applications of artificial intelligence in nursing care:a systematic review[J]. J Nurs Manag, 2023, 2023:3219127.
[2] 夏浩然, 陈小艳, 赵慧明, 等. 搭载ChatGPT的人工机械瓣膜置换术后患者自我监测随访大数据平台的建设与实践[J]. 中国实用护理杂志, 2023, 39(29):2276-2284.
  Xia HR, Chen XY, Zhao HM, et al. Construction and practice of a big data platform for self-monitoring follow-up of patients after mechanical valve replacement using ChatGPT[J]. Chin J Pract Nurs, 2023, 39(29):2276-2284.
[3] 徐春健, 蔡婷婷, 谢逸菲, 等. 机器学习模型在安宁疗护中应用的范围综述[J]. 中华护理杂志, 2025, 60(12):1524-1531.
  Xu CJ, Cai TT, Xie YF, et al. Machine learning models in hospice care:a scope review[J]. Chin J Nurs, 2025, 60(12):1524-1531.
[4] Park Y, Chang SJ, Kim E. Artificial intelligence in critical care nursing:a scoping review[J]. Aust Crit Care, 2025, 38(4):101225.
[5] Arksey H, O’Malley L. Scoping studies:towards a methodological framework[J]. Int J Soc Res Methodol, 2005, 8(1):19-32.
[6] Wang SR, Liu XY, Yuan SH, et al. Artificial intelligence based multispecialty mortality prediction models for septic shock in a multicenter retrospective study[J]. NPJ Digit Med, 2025, 8(1):228.
[7] 李梦珂, 孙焱, 刘鸿齐, 等. 基于机器学习算法的非计划重返ICU风险预测模型研究[J]. 护理研究, 2024, 38(22):3976-3982.
  Li MK, Sun Y, Liu HQ, et al. Research on risk prediction model for unplanned return to ICU based on machine learning algorithm[J]. Chin Nurs Res, 2024, 38(22):3976-3982.
[8] Zhang S, Cui W, Ding S, et al. A cluster-randomized controlled trial of a nurse-led artificial intelligence assisted prevention and management for delirium(AI-AntiDelirium) on delirium in intensive care unit:study protocol[J]. PLoS One, 2024, 19(2):e0298793.
[9] Milliren CE, Ozonoff A, Fournier KA, et al. Enhancing pressure injury surveillance using natural language processing[J]. J Patient Saf, 2024, 20(2):119-124.
[10] Gu SY, Lee EW, Zhang WH, et al. Evaluating natural language processing packages for predicting hospital-acquired pressure injuries from clinical notes[J]. Comput Inform Nurs, 2024, 42(3):184-192.
[11] 李世玫, 余爱华, 王苗苗, 等. 基于人工智能压力性损伤图片分析系统的精细干预在神经内科重症患者中的应用[J]. 河北医药, 2024, 46(20):3194-3196,3200.
  Li SM, Yu AH, Wang MM, et al. Application of fine intervention based on artificial intelligence stress injury imaging analysis system to critically ill patients in the neurology department[J]. Hebei Med J, 2024, 46(20):3194-3196,3200.
[12] Tran A, Topp R, Tarshizi E, et al. Predicting the onset of sepsis using vital signs data:a machine learning approach[J]. Clin Nurs Res, 2023, 32(7):1000-1009.
[13] Sotoodeh M, Zhang WH, Simpson RL, et al. A comprehensive and improved definition for hospital-acquired pressure injury classification based on electronic health records:comparative study[J]. JMIR Med Inform, 2023, 11:e40672.
[14] Lei L, Zhang S, Yang L, et al. Machine learning-based prediction of delirium 24 h after pediatric intensive care unit admission in critically ill children:a prospective cohort study[J]. Int J Nurs Stud, 2023, 146:104565.
[15] Im S, Lee SM. Development of mortality prediction model using electronic health record(EHR) data and machine learning algorithm in intensive care unit(ICU)[J]. Korean Data Anal Soc, 2023, 25(5):1977-1992.
[16] Mulkey M, Albanese T, Kim S, et al. Delirium detection using GAMMA wave and machine learning:a pilot study[J]. Res Nurs Health, 2022, 45(6):652-663.
[17] Xu J, Chen DX, Deng XF, et al. Development and validation of a machine learning algorithm-based risk prediction model of pressure injury in the intensive care unit[J]. Int Wound J, 2022, 19(7):1637-1649.
[18] Huang KX, Gray TF, Romero-Brufau S, et al. Using nursing notes to improve clinical outcome prediction in intensive care patients:a retrospective cohort study[J]. J Am Med Inform Assoc, 2021, 28(8):1660-1666.
[19] Ladios-Martin M, Fernández-de-Maya J, Ballesta-López FJ, et al. Predictive modeling of pressure injury risk in patients admitted to an intensive care unit[J]. Am J Crit Care, 2020, 29(4):e70-e80.
[20] Korach ZT, Yang J, Rossetti SC, et al. Mining clinical phrases from nursing notes to discover risk factors of patient deterioration[J]. Int J Med Inform, 2020, 135:104053.
[21] Tawfik DS, Profit J, Lake ET, et al. Development and use of an adjusted nurse staffing metric in the neonatal intensive care unit[J]. Health Serv Res, 2020, 55(2):190-200.
[22] 任国奇. 深度逆强化学习在脓毒症中的应用[D]. 大连: 大连理工大学, 2020.
  Ren GQ. Application of deep inverse reinforcement learning in sepsis[D]. Dalian: Dalian University of Technology, 2020.
[23] 穆兰, 徐文博, 王学通. 类ChatGPT大语言模型在护理教育中应用的实证探讨与前景展望[J]. 卫生职业教育, 2024, 42(20):4-7.
  Mu L, Xu WB, Wang XT. Empirical exploration and prospect on the application of ChatGPT-like large language model in nursing education[J]. Health Vocat Educ, 2024, 42(20):4-7.
[24] 马应卓, 王俊, 刘彤, 等. 大语言模型在护理学领域应用的范围综述[J]. 护理学杂志, 2024, 39(19):124-129.
  Ma YZ, Wang J, Liu T, et al. A scoping review of the applications of large language models in nursing science[J]. J Nurs Sci, 2024, 39(19):124-129.
[25] Bomrah S, Uddin M, Upadhyay U, et al. A scoping review of machine learning for sepsis prediction-feature engineering strategies and model performance:a step towards explainability[J]. Crit Care, 2024, 28(1):180.
[26] 袁力蓉, 谭文君, 朱皓阳, 等. 智能吸痰机器人安全性和有效性的实验研究[J]. 临床医学研究与实践, 2020, 5(17):5-8.
  Yuan LR, Tan WJ, Zhu HY, et al. Experimental study on safety and effectiveness of intelligent sputum-sucking robot[J]. Clin Res Pract, 2020, 5(17):5-8.
[27] Woodnutt S, Allen C, Snowden J, et al. Could artificial intelli-gence write mental health nursing care plans[J]. J Psychiatr Ment Health Nurs, 2024, 31(1):79-86.
[28] 李丹彤, 梁会营, 刘广建. 临床科研数据库建设中的数据标准化问题探讨[J]. 中国数字医学, 2021, 16(1):29-34.
  Li DT, Liang HY, Liu GJ. Discussion on data standardization in the construction of clinical research database[J]. China Digit Med, 2021, 16(1):29-34.
[29] 赵永信, 顾莺, 张晓波, 等. 基于临床护理分类系统的患儿体温过高护理程序知识库的构建[J]. 中华护理杂志, 2020, 55(12):1808-1812.
  Zhao YX, Gu Y, Zhang XB, et al. Construction of nursing procedures knowledge base for pediatric hyperthermia based on clinical care classification[J]. Chin J Nurs, 2020, 55(12):1808-1812.
Options
文章导航

/

〈 〉