切换至 "中华医学电子期刊资源库"

第五届中国出版政府奖音像电子网络出版物奖提名奖

中国科技核心期刊

中国科学引文数据库(CSCD)来源期刊

中华重症医学电子杂志 ›› 2026, Vol. 12 ›› Issue (03) : 256 -261. doi: 10.3877/cma.j.issn.2096-1537.2026.03.004

述评

围手术期肺部并发症人工智能辅助诊治的现状与前景
张金权1,2,3, 刘泽宇1,2,3, 陈志霞1, 李泉1,2,3,†()   
  1. 1 518116 深圳,国家癌症中心 国家肿瘤临床医学研究中心 中国医学科学院北京协和医学院肿瘤医院深圳医院麻醉科
    2 518100 深圳,广州中医药大学深圳临床医学院
    3 510006 广州,广州中医药大学
  • 收稿日期:2025-08-01 出版日期:2026-08-28
  • 通信作者: 李泉
  • 基金资助:
    国家自然科学基金项目(81971882); 中国医学科学院肿瘤医院深圳医院院内科研课题(E010224009); 深圳市高水平医院建设专项; 深圳市“医疗卫生三名工程”项目(SZSM202311003)

Artificial intelligence-assisted diagnosis and treatment of perioperative pulmonary complications: current status and prospects

Jinquan Zhang1,2,3, Zeyu Liu1,2,3, Zhixia Chen1, Quan Li1,2,3,†()   

  1. 1 Department of Anesthesiology, National Cancer Center, National Clinical Research Center for Cancer, Cancer Hospital & Shenzhen Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Shenzhen 518116, China
    2 Shenzhen Clinical Medical College, Guangzhou University of Chinese Medicine, Shenzhen 518100, China
    3 Guangzhou University of Chinese Medicine, Guangzhou 510006, China
  • Received:2025-08-01 Published:2026-08-28
  • Corresponding author: Quan Li
引用本文:

张金权, 刘泽宇, 陈志霞, 李泉. 围手术期肺部并发症人工智能辅助诊治的现状与前景[J/OL]. 中华重症医学电子杂志, 2026, 12(03): 256-261.

Jinquan Zhang, Zeyu Liu, Zhixia Chen, Quan Li. Artificial intelligence-assisted diagnosis and treatment of perioperative pulmonary complications: current status and prospects[J/OL]. Chinese Journal of Critical Care & Intensive Care Medicine(Electronic Edition), 2026, 12(03): 256-261.

近年来,人工智能(AI)技术已经在围手术期肺部并发症(PPCs)的诊断、治疗和预后评估方面取得了一些成果,为临床医师提供了新的思路和方法,为患者提供了更加优化、高效、安全的围手术期管理方案。例如,在急性肺损伤/急性呼吸窘迫综合征(ALI/ARDS)、呼吸机相关性肺炎(VAP)、术后呼吸衰竭(PRF)等常见严重肺部并发症中,AI技术可以利用大量的数据进行分析、挖掘、建模和优化,从而提高诊断的准确性、治疗的及时性和有效性、预后的可靠性,特别是在围手术期肺保护通气策略方面,AI技术可以实现对机械通气过程中的多种参数的动态监测和智能调节,以减少呼吸机相关性肺损伤(VALI)的发生风险,提高患者的安全性和舒适性。总体而言,AI技术在围手术期医学中具有广泛的应用和巨大的潜力,然而它仍需解决数据、算法、伦理三大瓶颈,例如数据质量和数量的不足、算法的复杂性和不透明性,以及患者隐私等伦理问题。因此,未来的研究需要加强数据标准化和共享、算法优化和验证、模型解释和评估、伦理和法律的制定和遵守等方面的工作,以促进AI技术在围手术期医学中更广泛和更深入的应用。本文围绕AI技术在常见PPCs的诊治和预后评估中的研究进展作一述评,分析AI技术在围手术期医学中的优势和不足,提出未来的研究方向和建议。

In recent years, artificial intelligence (AI) technology has achieved significant progress in the diagnosis, treatment and prognosis evaluation of perioperative pulmonary complications (PPCs), offering new insights and approaches for clinicians, and delivering more optimized, efficient and safe perioperative management plans for patients. For instance, in common severe pulmonary complications such as acute lung injury/acute respiratory distress syndrome (ALI/ARDS), ventilator-associated pneumonia (VAP), and postoperative respiratory failure (PRF), AI technology can leverage large amounts of data to perform analysis, mining, modeling and optimization, thereby enhancing the accuracy of diagnosis, the timeliness and effectiveness of treatment, and the reliability of prognosis. Particularly, in the perioperative lung protective ventilation strategy, AI technology can enable the dynamic monitoring and intelligent adjustment of various parameters in the mechanical ventilation process, reducing the risk of ventilator-associated lung injury (VALI) and improving the safety and comfort of patients. Overall, AI technology demonstrates extensive applications and immense potential in perioperative medicine, yet it must overcome three critical bottlenecks—data, algorithmic, and ethical challenges—including insufficient data quality and quantity, algorithmic complexity and opacity, along with ethical concerns such as patient privacy issues. Therefore, future research needs to strengthen the work on data standardization and sharing, algorithm optimization and validation, model interpretation and evaluation, ethics and law formulation and compliance, etc., to promote the wider and deeper application of AI technology in perioperative medicine. This article provides a review of the recent research advances in the application of AI technology for the diagnosis, treatment and prognostic assessment of common PPCs. We also analyzed the strengths and weaknesses of AI technology in perioperative medicine, and suggested future research directions and recommendations.

1
王天佑, 李单青, 崔永, 等.胸外科围手术期肺保护中国专家共识 (2019版)[J].中国胸心血管外科临床杂志, 2019, 26(9): 835-842.
2
LAS VEGAS investigators. Epidemiology, practice of ventilation and outcome for patients at increased risk of postoperative pulmonary complications: LAS VEGAS - an observational study in 29 countries[J]. Eur J Anaesthesiol, 2017, 34(8): 492-507.
3
Khan NA, Quan H, Bugar JM, et al. Association of postoperative complications with hospital costs and length of stay in a tertiary care center[J]. J Gen Intern Med, 2006, 21(2): 177-180.
4
Hashimoto DA, Witkowski E, Gao L, et al. Artificial intelligence in anesthesiology: current techniques, clinical applications, and limitations[J]. Anesthesiology, 2020, 132(2): 379-394.
5
Temsah MH, Jamal A, Alhasan K, et al. OpenAI o1-preview vs. ChatGPT in healthcare: a new frontier in medical AI reasoning[J]. Cureus, 2024, 16(10): e70640.
6
Shah NH, Entwistle D, Pfeffer MA. Creation and adoption of large language models in medicine[J]. JAMA, 2023, 330(9): 866-869.
7
Normile D. Chinese firm's large language model makes a splash[J]. Science, 2025, 387(6731): 238.
8
Habehh H, Gohel S. Machine Learning in Healthcare[J]. Curr Genomics, 2021, 22(4): 291-300.
9
Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks[J]. Nature, 2017, 542(7639): 115-118.
10
Kaouk JH, Garisto J, Eltemamy M, et al. Robot-assisted surgery for benign distal ureteral strictures: step-by-step technique using the SP® surgical system[J]. BJU Int, 2019, 123(4): 733-739.
11
Tang J, Liu R, Zhang YL, et al. Application of machine-learning models to predict Tacrolimus stable dose in renal transplant recipients[J]. Sci Rep, 2017, 7: 42192.
12
Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare[J]. Nat Biomed Eng, 2018, 2(10): 719-731.
13
Zhang A, Wu Z, Wu E, et al. Leveraging physiology and artificial intelligence to deliver advancements in health care[J]. Physiol Rev, 2023, 103(4): 2423-2450.
14
Song B, Zhou M, Zhu J. Necessity and importance of developing AI in anesthesia from the perspective of clinical safety and information security[J]. Med Sci Monit, 2023, 29: e938835.
15
Kayaalp ME, Ollivier M, Winkler PW, et al. Embrace responsible ChatGPT usage to overcome language barriers in academic writing[J]. Knee Surg Sports Traumatol Arthrosc, 2024, 32(1): 5-9.
16
Borsetto D, Sia E, Axon P, et al. Quality of information provided by artificial intelligence chatbots surrounding the management of vestibular schwannomas: a comparative analysis between ChatGPT-4 and Claude 2[J]. Otol Neurotol, 2025, 46(4): 432-436.
17
Kayaalp ME, Prill R, Sezgin EA, et al. DeepSeek versus ChatGPT: multimodal artificial intelligence revolutionizing scientific discovery. From language editing to autonomous content generation-redefining innovation in research and practice[J]. Knee Surg Sports Traumatol Arthrosc, 2025, 33(5): 1553-1556.
18
Gambus PL, Jaramillo S. Machine learning in anaesthesia: reactive, proactive… predictive![J]. Br J Anaesth, 2019, 123(4): 401-403.
19
Giri R, Firdhos SH, Vida TA. Artificial Intelligence in anesthesia: enhancing precision, safety, and global access through data-driven systems[J]. J Clin Med, 2025, 14(19): 6900.
20
钱柳, 刘进. 人工智能在麻醉学科的前景与挑战[J]. 临床麻醉学杂志, 2021, 37(6): 565-568.
21
徐瑾, 邓晓明, 晏馥霞. 机器学习算法在麻醉领域的应用[J]. 中国医学科学院学报, 2020, 42(5): 696-701.
22
高宇晨, 敖虎山. 人工智能在心血管手术围手术期应用的研究进展[J]. 心肺血管病杂志, 2022, 41(11): 1201-1204.
23
易斌, 李洪. 围手术期大数据的应用与展望[J]. 陆军军医大学学报, 2023, 45(8): 725-731.
24
Maheshwari K, Ruetzler K, Saugel B. Perioperative intelligence: applications of artificial intelligence in perioperative medicine[J]. J Clin Monit Comput, 2020, 34(4): 625-628.
25
Carr ZJ, Siller S, McDowell BJ. Perioperative pulmonary complications in the older adults: the forgotten system[J]. Clin Geriatr Med, 2025, 41(1): 1-18.
26
Li P, Gao S, Wang Y, et al. Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications[J]. Br J Anaesth, 2024, 132(6): 1315-1326.
27
Maheshwari K, Cywinski JB, Papay F, et al. Artificial intelligence for perioperative medicine: perioperative intelligence[J]. Anesth Analg, 2023, 136(4): 637-645.
28
Zhou Z, Long Y. Dynamic monitoring of serum protein in acute respiratory distress syndrome based on artificial neural network[J]. Comput Math Methods Med, 2022, 2022: 3542942.
29
Bitker L, Talmor D, Richard JC. Imaging the acute respiratory distress syndrome: past, present and future[J]. Intensive Care Med, 2022, 48(8): 995-1008.
30
Herrmann P, Busana M, Cressoni M, et al. Using artificial intelligence for automatic segmentation of CT lung images in acute respiratory distress syndrome[J]. Front Physiol, 2021, 12: 676118.
31
Mantuani D, Nagdev A, Stone M. Three-view bedside ultrasound for the differentiation of acute respiratory distress syndrome from cardiogenic pulmonary edema[J]. Am J Emerg Med, 2012, 30(7): 1324.e1-4.
32
Kimura S, Stoicea N, Rosero Britton BR, et al. Preventing ventilator-associated lung injury: a perioperative perspective[J]. Front Med (Lausanne), 2016, 3: 25.
33
Perchiazzi G, Rylander C, Pellegrini M, et al. Monitoring of total positive end-expiratory pressure during mechanical ventilation by artificial neural networks[J]. J Clin Monit Comput, 2017, 31(3): 551-559.
34
Wang Z, Zhang L, Huang T, et al. Developing an explainable machine learning model to predict the mechanical ventilation duration of patients with ARDS in intensive care units[J]. Heart Lung, 2023, 58: 74-81.
35
Nguyen B, Bernstein DB, Bates JH. Controlling mechanical ventilation in acute respiratory distress syndrome with fuzzy logic[J]. J Crit Care, 2014, 29(4): 551-556.
36
Bernstein DB, Nguyen B, Allen GB, et al. Elucidating the fuzziness in physician decision making in ARDS[J]. J Clin Monit Comput, 2013, 27(3): 357-363.
37
Attaallah AF, Vallejo MC, Elzamzamy OM, et al. Perioperative risk factors for postoperative respiratory failure[J]. J Perioper Pract, 2019, 29(3): 49-53.
38
Banner MJ, Euliano NR, Brennan V, et al. Power of breathing determined noninvasively with use of an artificial neural network in patients with respiratory failure[J]. Crit Care Med, 2006, 34(4): 1052-1059.
39
Gottschalk A, Hyzer MC, Geer RT. A comparison of human and machine-based predictions of successful weaning from mechanical ventilation[J]. Med Decis Making, 2000, 20(2): 160-169.
40
Knorr-Chung BR, McGrath SP, Blike GT. Identifying airway obstructions using photoplethysmography (PPG)[J]. J Clin Monit Comput, 2008, 22(2): 95-101.
41
Ranzani OT, Niederman MS, Torres A. Ventilator-associated pneumonia[J]. Intensive Care Med, 2022, 48(9): 1222-1226.
42
Rello J, Ollendorf DA, Oster G, et al. Epidemiology and outcomes of ventilator-associated pneumonia in a large US database[J]. Chest, 2002, 122(6): 2115-2121.
43
Liang Y, Zhu C, Tian C, et al. Early prediction of ventilator-associated pneumonia in critical care patients: a machine learning model[J]. BMC Pulm Med, 2022, 22(1): 250.
44
Giang C, Calvert J, Rahmani K, et al. Predicting ventilator-associated pneumonia with machine learning[J]. Medicine (Baltimore), 2021, 100(23): e26246.
45
Cai Y, Zhang W, Zhang R, et al. Combined use of three machine learning modeling methods to develop a ten-gene signature for the diagnosis of ventilator-associated pneumonia[J]. Med Sci Monit, 2020, 26: e919035.
46
Liao YH, Wang ZC, Zhang FG, et al. Machine learning methods applied to predict ventilator-associated pneumonia with Pseudomonas aeruginosa infection via sensor array of electronic nose in Intensive Care Unit[J]. Sensors (Basel), 2019, 19(8): 1866.
47
Shelley B, Shaw M. Machine learning and preoperative risk prediction: the machines are coming[J]. Br J Anaesth, 2024, 133(5): 925-930.
[1] 李珂, 张译尹, 杨后圃, 王殊. 乳腺癌保留乳房手术中精准定位与切缘评估技术的研究进展[J/OL]. 中华乳腺病杂志(电子版), 2026, 20(05): 272-278.
[2] 郑民华, 李树春, 马君俊. 数字人工智能在直肠癌微创外科的发展[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(06): 511-515.
[3] 晏阳, 谢天宇, 杜晓辉. 智能化在直肠癌微创外科的实践[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(06): 516-519.
[4] 方振, 商亮, 李乐平. 智能化与个体化在直肠癌微创外科的应用[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(06): 520-523.
[5] 何梓芸, 杨志, 任传富, 夏雪峰. 普外科围手术期甲状腺功能亢进诊治的临床经验:三项关键教训与“防-控-救”应对策略[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(06): 593-596.
[6] 蔡泽荣, 兰平, 吴小剑. 数字智能化在右半结肠癌微创外科的发展[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(05): 409-413.
[7] 燕速, 何坤山, 谢宏宇, 霍博文, 刘云荣, 李园园. 智能化与个体化在右半结肠癌微创外科的应用[J/OL]. 中华普外科手术学杂志(电子版), 2026, 20(05): 414-419.
[8] 朱洪浩, 邢晨, 张少玲, 江春, 范新祥, 董文, 孔坚秋. 人工智能在肾上腺肿瘤诊疗中的应用进展[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(05): 581-587.
[9] 李佳颖, 刘溪, 陈宇航, 桂程鹏, 习明, 陈炜, 罗俊航. 卷积神经网络在预测肾透明细胞癌全视野数字切片肿瘤坏死中的应用研究[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2026, 20(04): 389-398.
[10] 张燚, 寇贤帅, 饶旭, 贺斌峰. 人工智能在慢性阻塞性肺疾病诊断与管理中的应用研究进展[J/OL]. 中华肺部疾病杂志(电子版), 2026, 19(05): 882-887.
[11] 马煜博, 李起, 耿智敏. 胆道恶性肿瘤预后预测模型:现状、挑战与未来展望[J/OL]. 中华肝脏外科手术学电子杂志, 2026, 15(05): 702-710.
[12] 中国抗癌协会大肠癌专业委员会, 中国抗癌协会大肠癌专业委员会NOSES技术推广专家委员会, 海峡两岸医药卫生交流协会肿瘤学分会日间手术学组. 结直肠癌日间手术专家共识(2026版)[J/OL]. 中华结直肠疾病电子杂志, 2026, 15(05): 385-394.
[13] 赵晨野, 王嘉浩, 高媛媛, 董泽鹏, 胡世博, 牟明超, 李小鹏, 余钧辉, 孙学军, 郑见宝. NOSES与传统腹腔镜手术治疗左半结肠癌和直肠癌的围手术期及长期肿瘤学结局比较:基于倾向评分匹配研究[J/OL]. 中华结直肠疾病电子杂志, 2026, 15(05): 410-418.
[14] 林静, 侯世会, 王佳丽, 甘宏博, 封蕾, 李民, 陈客宏. 生成式人工智能支持的纠错式案例教学在肾内科实习中的应用[J/OL]. 中华肾病研究电子杂志, 2026, 15(05): 280-285.
[15] 郭桂芳, 吴海燕, 石玮, 顾国利. ERAS人文关怀理念在超高龄胃肠恶性肿瘤围手术期中的应用[J/OL]. 中华临床医师杂志(电子版), 2026, 20(06): 465-469.
阅读次数
全文


摘要


AI
小
编
AI小编
你好!我是《中华医学电子期刊资源库》AI小编,有什么可以帮您的吗?