人工智能在气道管理方面的研究进展

doi:10.11958/20251687

天津医药 ›› 2025, Vol. 53 ›› Issue (10): 1098-1104.doi: 10.11958/20251687

人工智能在气道管理方面的研究进展

李佳蓉¹(), 朱晓敏¹, 赵晓赟²^,^△()

¹ 天津大学医学院（邮编 300072）
² 天津大学胸科医院呼吸与危重症医学科

收稿日期:2025-04-22 修回日期:2025-07-10 出版日期:2025-10-15 发布日期:2025-10-12
通讯作者: ^△E-mail：zxydoctor@163.com
作者简介:李佳蓉（1998），女，硕士在读，主要从事气道管理、人工智能方面研究。E-mail：doctorl98@163.com
基金资助:
国家临床重点专科建设项目;天津市医学重点学科（专科）项目(TJYXZDXK-049A);天津市卫生健康科技临床重点专项(TJWJ2024ZK003)

Advances in artificial intelligence for airway management of intubated patients

LI Jiarong¹(), ZHU Xiaomin¹, ZHAO Xiaoyun²^,^△()

¹ Medical School of Tianjin University, Tianjin 300072, China
² Department of Respiratory and Critical Care Medicine, Tianjin University Chest Hospital

Received:2025-04-22 Revised:2025-07-10 Published:2025-10-15 Online:2025-10-12
Contact: ^△E-mail：zxydoctor@163.com

李佳蓉, 朱晓敏, 赵晓赟. 人工智能在气道管理方面的研究进展[J]. 天津医药, 2025, 53(10): 1098-1104.

LI Jiarong, ZHU Xiaomin, ZHAO Xiaoyun. Advances in artificial intelligence for airway management of intubated patients[J]. Tianjin Medical Journal, 2025, 53(10): 1098-1104.

摘要/Abstract

摘要：

气道管理是危重患者救治的关键环节，尽管传统的气道管理方法在一定程度上有效，但仍面临诸多挑战，如困难气道、气管插管延迟、气管导管移位、难以预测的气道并发症以及机械通气撤机失败等。人工智能（AI）不但可用于患者生命体征的实时监测、呼吸机参数的动态调整、气道并发症的监测与评估以及辅助机器人插管等领域，还能够基于大数据建立预测模型，帮助降低机械通气患者的损伤风险，并辅助临床医生及时作出决策。该文综述了AI在气道管理中的研究进展，探讨了AI使用过程中可能面临的问题，并对AI在未来气道管理中发挥的作用进行了展望。

关键词: 人工智能, 气道管理, 插管法, 气管内, 呼吸, 人工, 困难气道, 机器人气管插管

Abstract:

Airway management is a critical component of critical patient care. Although traditional methods of airway management are effective to some extent, they still face many challenges, such as difficult airways, delayed endotracheal intubation, endotracheal tube migration, unpredictable airway complications and failure to mechanical ventilation weaning. Artificial intelligence (AI), a technological tool with advanced algorithms, offers important innovations to improve the safety and efficiency of airway management with its multimodal data integration and real-time decision support capabilities. For example, AI can be used in areas such as real-time monitoring of patients' vital signs, dynamic adjustment of ventilator parameters, monitoring and assessment of airway complications, and assisted robotic tracheal intubation. In addition, AI is able to build predictive models based on big data to help reduce the risk of injury in mechanically ventilated patients and assist clinicians in making timely decisions. This paper reviews the research progress of AI in airway management and discusses issues of privacy and security, ethics, model performance and interpretability that may be faced during the use of AI, and looks forward to a more active role for AI in airway management in future.

Key words: artificial intelligence, airway management, intubation, intratracheal, respiration, artificial, difficult airway, robotic endotracheal intubation

中图分类号:

R563，TP18

图/表 1

参考文献 48

[1]	赵美玉, 王明亚, 韩永正, 等. 基于人工智能的气道管理优化策略与实践分析[J]. 重庆医科大学学报, 2025, 50(1):1-5.
	ZHAO M Y, WANG M Y, HAN Y Z, et al. Optimization strategy and practice analysis of airway management based on artificial intelligence[J]. Journal of Chongqing Medical University, 2025, 50(1):1-5. doi:10.13406/j.cnki.cyxb.003693.
[2]	ELLIS H L, TEO J T. The influence of AI in medicine[J]. Medicine, 2024, 52(12):811-815. doi:10.1016/j.mpmed.2024.09.006.
[3]	RANA V, MEHROTRA S, ASTHANA V, et al. Radiological versus traditional parameters for airway assessment:a comparison[J]. Anesth Essays Res, 2022, 16(1):109-114. doi:10.4103/aer.aer_28_22.
[4]	WANG Z, JIN Y, ZHENG Y, et al. Evaluation of preoperative difficult airway prediction methods for adult patients without obvious airway abnormalities:a systematic review and meta-analysis[J]. BMC Anesthesiol, 2024, 24(1):242. doi:10.1186/s12871-024-02627-1.
[5]	WU J, YAO Y, ZHANG G, et al. Difficult airway assessment based on multi-view metric learning[J]. Bioengineering(Basel), 2024, 11(7):703. doi:10.3390/bioengineering11070703.
[6]	CHO H Y, LEE K, KONG H J, et al. Deep-learning model associating lateral cervical radiographic features with Cormack-Lehane grade 3 or 4 glottic view[J]. Anaesthesia, 2023, 78(1):64-72. doi:10.1111/anae.15874.
[7]	MADRID-VÁZQUEZ L, CASANS-FRANCÉS R, GÓMEZ-RÍOS M A, et al. Machine learning models based on ultrasound and physical examination for airway assessment[J]. Rev Esp Anestesiol Reanim(Engl Ed), 2024, 71(8):563-569. doi:10.1016/j.redare.2024.05.006.
[8]	YARNELL C J, PARANTHAMAN A, REARDON P, et al. An international factorial vignette-based survey of intubation decisions in acute hypoxemic respiratory failure[J]. Crit Care Med, 2025, 53(1):e117-e131. doi:10.1097/CCM.0000000000006494.
[9]	RIERA J, BARBETA E, TORMOS A, et al. Effects of intubation timing in patients with COVID-19 throughout the four waves of the pandemic: a matched analysis[J]. Eur Respir J, 2023, 61(3):2201426. doi:10.1183/13993003.01426-2022.
[10]	VENTURINI M, VAN KEILEGOM I, DE CORTE W, et al. Predicting time-to-intubation after critical care admission using machine learning and cured fraction information[J]. Artif Intell Med, 2024, 150:102817. doi:10.1016/j.artmed.2024.102817.
[11]	MOULAEI K, AFRASH M R, PARVIN M, et al. Explainable artificial intelligence (XAI) for predicting the need for intubation in methanol-poisoned patients:a study comparing deep and machine learning models[J]. Sci Rep, 2024, 14(1):15751. doi:10.1038/s41598-024-66481-4.
[12]	NGUYEN M, AMANIAN A, WEI M, et al. Predicting tracheostomy need on admission to the intensive care unit-a multicenter machine learning analysis[J]. Otolaryngol Head Neck Surg, 2024, 171(6):1736-1750. doi:10.1002/ohn.919.
[13]	TIGHE P J, BADIYAN S J, LURIA I, et al. Robot-assisted airway support:a simulated case[J]. Anesth Analg, 2010, 111(4):929-931. doi:10.1213/ANE.0b013e3181ef73ec.
[14]	HEMMERLING T M, TADDEI R, WEHBE M, et al. First robotic tracheal intubations in humans using the Kepler intubation system[J]. Br J Anaesth, 2012, 108(6):1011-1016. doi:10.1093/bja/aes034.
[15]	WANG X, TAO Y, TAO X, et al. An original design of remote robot-assisted intubation system[J]. Sci Rep, 2018, 8(1):13403. doi:10.1038/s41598-018-31607-y.
[16]	BIRO P, HOFMANN P, GAGE D, et al. Automated tracheal intubation in an airway manikin using a robotic endoscope: a proof of concept study[J]. Anaesthesia, 2020, 75(7):881-886. doi:10.1111/anae.14945.
[17]	王荣峰, 张倩雲, 丁泓帆, 等. 基于磁导航技术的气管插管装置设计及可行性研究[J]. 中国医疗器械杂志, 2021, 45(1):22-25.
	WANG R F, ZHANG Q Y, DING H F, et al. Design and feasibility study of tracheal intubation device based on magnetic navigation technology[J]. Chinese Journal of Medical lnstrumentation, 2021, 45(1):22-25. doi:10.3969/j.issn.1671-7104.2021.01.005.
[18]	DENG Z, ZHANG S, GUO Y, et al. Assisted teleoperation control of robotic endoscope with visual feedback for nasotracheal intubation[J]. Robotics and Autonomous Systems, 2024, 172:104586. doi:10.1016/j.robot.2023.104586.
[19]	NOVAK R. Spiro robotics:the future of difficult intubation management[EB/OL]. (2024-10-17)[2025-04-19]. https://theanesthesiaconsultant.com/2024/10/17/spiro-robotics-the-future-of-difficult-intubation-management/.
[20]	FRITSCH S J, CECCONI M. Setting the ventilator with AI support:challenges and perspectives[J]. Intensive Care Med, 2025, 51(3):593-595. doi:10.1007/s00134-024-07778-w.
[21]	BARAHONA J, SAHLI COSTABAL F, HURTADO D E. Machine learning modeling of lung mechanics:Assessing the variability and propagation of uncertainty in respiratory-system compliance and airway resistance[J]. Comput Methods Programs Biomed, 2024, 243:107888. doi:10.1016/j.cmpb.2023.107888.
[22]	HÄNDEL C, FRERICHS I, WEILER N, et al. Prediction and simulation of PEEP setting effects with machine learning models[J]. Med Intensiva (Engl Ed), 2024, 48(4):191-199. doi:10.1016/j.medine.2023.09.005.
[23]	郭祖源. 光学相干断层扫描气道形态图像自动识别系统建立及其在慢性阻塞性肺疾病患者随访的应用[D]. 广州: 广州医科大学, 2022.
	GUO Z Y. Establishment of automatic identification system for airway morphological images of optical coherence tomography and its application in the follow-up of patients with chronic obstructive pulmonary disease[D]. Guangzhou: Guangzhou Medical University, 2022.
[24]	DE HARO C, SANTOS-PULPÓN V, TELÍAS I, et al. Flow starvation during square-flow assisted ventilation detected by supervised deep learning techniques[J]. Crit Care, 2024, 28(1):75. doi:10.1186/s13054-024-04845-y.
[25]	AN J Y, HWANG E J, NAM G, et al. Artificial intelligence for assessment of endotracheal tube position on chest radiographs: validation in patients from two institutions[J]. AJR Am J Roentgenol, 2024, 222(1):e2329769. doi:10.2214/AJR.23.29769.
[26]	WANG C H, HWANG T, HUANG Y S, et al. Deep learning-based localization and detection of malpositioned endotracheal tube on portable supine chest radiographs in intensive and emergency medicine: a multicenter retrospective study[J]. Crit Care Med, 2024, 52(2):237-247. doi:10.1097/CCM.0000000000006046.
[27]	KIM H, YOON H K, LEE H, et al. Predicting optimal endotracheal tube size and depth in pediatric patients using demographic data and machine learning techniques[J]. Korean J Anesthesiol, 2023, 76(6):540-549. doi:10.4097/kja.23501.
[28]	LIN Z C, KOO M, CHANG W J, et al. Comparing artificial intelligence-based versus conventional endotracheal tube monitoring systems in clinical practice[J]. Stud Health Technol Inform, 2024, 315:589-591. doi:10.3233/SHTI240230.
[29]	ROSENTHAL V D, MEMISH Z A, BEARMAN G. Preventing ventilator-associated pneumonia:A position paper of the international society for infectious diseases,2024 update[J]. Int J Infect Dis, 2025, 151:107305. doi:10.1016/j.ijid.2024.107305.
[30]	FRONDELIUS T, ATKOVA I, MIETTUNEN J, et al. Early prediction of ventilator-associated pneumonia with machine learning models:A systematic review and meta-analysis of prediction model performance[J]. Eur J Intern Med, 2024, 121:76-87. doi:10.1016/j.ejim.2023.11.009.
[31]	ZHANG G, LUO L, ZHANG L, et al. Research progress of respiratory disease and idiopathic pulmonary fibrosis based on artificial intelligence[J]. Diagnostics(Basel), 2023, 13(3):357. doi:10.3390/diagnostics13030357.
[32]	MOHAMMED A, VAN WYK F, CHINTHALA L K, et al. Temporal differential expression of physiomarkers predicts sepsis in critically ill adults[J]. Shock, 2021, 56(1):58-64. doi:10.1097/SHK.0000000000001670.
[33]	TE R, ZHU B, MA H, et al. Machine learning approach for predicting post-intubation hemodynamic instability (PIHI) index values: towards enhanced perioperative anesthesia quality and safety[J]. BMC Anesthesiol, 2024, 24(1):136. doi:10.1186/s12871-024-02523-8.
[34]	HUANG S, TENG Y, DU J, et al. Internal and external validation of machine learning-assisted prediction models for mechanical ventilation-associated severe acute kidney injury[J]. Aust Crit Care, 2023, 36(4):604-612. doi:10.1016/j.aucc.2022.06.001.
[35]	潘金玉, 舒欣, 孙溦. 气管切开昏迷患者沉默性误吸风险评估指标Delphi法构建与临床实证研究[J]. 陆军军医大学学报, 2023, 45(20):2113-2119.
	PAN J Y, SHU X, SUN W. Risk assessment items for silent aspiration in coma patients with tracheotomy based on Delphi method and a clinical empirical study[J]. Journal of Army Medical University, 2023, 45(20):2113-2119. doi:10.16016/j.2097-0927.202307067.
[36]	PINTO J, GONZÁLEZ H, ARIZMENDI C, et al. Analysis of the cardiorespiratory pattern of patients undergoing weaning using artificial intelligence[J]. Int J Environ Res Public Health, 2023, 20(5):4430. doi:10.3390/ijerph20054430.
[37]	RUBULOTTA F, BLANCH TORRA L, NAIDOO K D, et al. Mechanical ventilation,past,present,and future[J]. Anesth Analg, 2024, 138(2):308-325. doi:10.1213/ANE.0000000000006701.
[38]	LIU C F, HUNG C M, KO S C, et al. An artificial intelligence system to predict the optimal timing for mechanical ventilation weaning for intensive care unit patients: A two-stage prediction approach[J]. Front Med(Lausanne), 2022, 9:935366. doi:10.3389/fmed.2022.935366.
[39]	WU J, LIU Z, SHEN D, et al. Prevention of unplanned endotracheal extubation in intensive care unit:An overview of systematic reviews[J]. Nurs Open, 2023, 10(2):392-403. doi:10.1002/nop2.1317.
[40]	HUR S, MIN J Y, YOO J, et al. Development and validation of unplanned extubation prediction models using intensive care unit data: retrospective, comparative, machine learning study[J]. J Med Internet Res, 2021, 23(8):e23508. doi:10.2196/23508.
[41]	XIA M, JIN C, CAO S, et al. Development and validation of a machine-learning model for prediction of hypoxemia after extubation in intensive care units[J]. Ann Transl Med, 2022, 10(10):577. doi:10.21037/atm-22-2118.
[42]	VARÓN-VEGA F, TUTA-QUINTERO E, MALDONADO-FRANCO A, et al. Machine learning to predict extubation success using the spontaneous breathing trial, objective cough measurement, and diaphragmatic contraction velocity:Secondary analysis of the COBRE-US trial[J]. J Crit Care Med (Targu Mures), 2025, 11(1):70-77. doi:10.2478/jccm-2025-0009.
[43]	CHO T, KANNAN T, PATEL K, et al. Role of heart rate variability in predicting tracheal extubation failure: a systematic review and meta-analysis[J]. Br J Anaesth, 2025, 134(4):1225-1229. doi:10.1016/j.bja.2024.12.030.
[44]	PAN Q, ZHANG H, JIANG M, et al. Comprehensive breathing variability indices enhance the prediction of extubation failure in patients on mechanical ventilation[J]. Comput Biol Med, 2023, 153:106459. doi:10.1016/j.compbiomed.2022.106459.
[45]	WANG H, ZHAO Q Y, LUO J C, et al. Early prediction of noninvasive ventilation failure after extubation: development and validation of a machine-learning model[J]. BMC Pulm Med, 2022, 22(1):304. doi:10.1186/s12890-022-02096-7.
[46]	FROICU E M, CREANGĂ-MURARIU I, AFRĂSÂNIE V A, et al. Artificial intelligence and decision-making in oncology:a review of ethical,legal,and informed consent challenges[J]. Curr Oncol Rep, 2025 doi:10.1007/s11912-025-01698-8.
[47]	RODRÍGUEZ VILLAMIZAR P, THILLE A W, MÁRQUEZ DOBLAS M, et al. Best clinical model predicting extubation failure:a diagnostic accuracy post hoc analysis[J]. Intensive Care Med, 2025, 51(1):106-114. doi:10.1007/s00134-024-07758-0.
[48]	STERR F, REINTKE M, BAUERNFEIND L, et al. Predictors of weaning failure in ventilated intensive care patients: a systematic evidence map[J]. Crit Care, 2024, 28(1):366. doi:10.1186/s13054-024-05135-3.

人工智能在气道管理方面的研究进展

Advances in artificial intelligence for airway management of intubated patients

引用本文

RichHTML

PDF (PC)

可视化

摘要/Abstract

使用本文

图/表 1

参考文献 48

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈苗苗, 张亚征, 赵芳, 杨立恒, 焦丽娜, 赵晓赟. 阻塞性睡眠呼吸暂停和心房颤动因果关系的多组学孟德尔随机化分析[J]. 天津医药, 2025, 53(9): 946-951.
[2]	蒋文静, 郭敬肖, 耿爱桥. 血清Cc16、CD62E表达水平与新生儿呼吸窘迫综合征严重程度和肺部超声评分的关系[J]. 天津医药, 2025, 53(8): 836-839.
[3]	杜昕桃, 索莹, 赵晓赟. 睡眠呼吸障碍与肺动脉高压双向关系的研究进展[J]. 天津医药, 2025, 53(8): 889-896.
[4]	金亮, 金爱, 王苓, 齐霄茹, 代琰, 苏海涛. 表面肌电生物反馈联合呼吸训练治疗脑卒中后吞咽障碍的疗效观察[J]. 天津医药, 2025, 53(7): 688-693.
[5]	吴小霞, 郭建新, 瞿梦婷, 娜迪热·海如拉, 扎依旦·艾力, 程永凤. 不同潮气量通气对重症肺炎患儿呼吸力学和血流动力学的影响[J]. 天津医药, 2025, 53(7): 747-750.
[6]	余辉, 刘浩, 蔡凤丽, 赵婧, 白相森, 田国梁, 张含悦, 张丽媛. 基于声学信息检测阻塞性睡眠呼吸暂停的研究进展[J]. 天津医药, 2025, 53(7): 776-784.
[7]	贾建波, 孙根, 顾媛媛. 持续气道正压通气对合并阻塞性睡眠呼吸暂停综合征的脑梗死患者平均气道压及神经功能的影响[J]. 天津医药, 2025, 53(6): 639-643.
[8]	胡卓, 谢松波, 游诗伟. 序贯器官衰竭评分联合Clara细胞蛋白和血管生成素-2对脓毒症所致ARDS的预测价值[J]. 天津医药, 2025, 53(5): 519-522.
[9]	杨丽亚, 郑丽, 李利红, 李亚永, 马将. 多巴丝肼联合呼吸训练在卒中后吞咽困难中的效果评价[J]. 天津医药, 2025, 53(3): 257-261.
[10]	钱洪春, 张萍淑, 元小冬, 袁建新, 曹凌云, 段丽琴. 卒中伴阻塞性睡眠呼吸暂停患者认知功能损害与睡眠参数的关系[J]. 天津医药, 2024, 52(6): 619-624.
[11]	刘丹, 万南生, 王杰, 句仁华, 谢巍, 田羽, 冯靖. 多导睡眠图辅助药物诱导睡眠内镜正压呼吸机压力滴定的操作要点[J]. 天津医药, 2024, 52(3): 324-326.
[12]	钟晓倩, 孙高悦, 张倩倩, 李云. 驱动压导向的个体化呼气末正压通气对行腹腔镜胃癌根治术老年患者的肺保护作用[J]. 天津医药, 2024, 52(2): 188-192.
[13]	屠昌明, 田园, 汪鹏程, 任鹏, 赵寅生. SII、RAR与AECOPD患者病情严重程度及并发呼吸衰竭的关系[J]. 天津医药, 2024, 52(12): 1317-1321.
[14]	梁耀冰, 符振华, 赵梓粤, 罗剑明, 程冬瑀, 姜海行, 覃山羽. 高甘油三酯血症性急性胰腺炎并发急性呼吸衰竭危险因素及预测模型的建立[J]. 天津医药, 2024, 52(11): 1183-1187.
[15]	孟克青, 张武林, 董玮, 许衍辉, 李楠. 超声乳化白内障吸出联合CTR植入对高度近视白内障术后囊袋稳定性的影响[J]. 天津医药, 2024, 52(10): 1056-1060.