中山大学附属第一医院麻醉科,广东 广州 510080
杨力铭,第一作者,研究方向:人工智能在围术期管理与临床麻醉中的应用,E-mail:yanglm29@mail2.sysu.edu.cn
收稿:2025-07-18,
修回:2025-12-16,
录用:2025-12-22,
纸质出版:2026-01-20
移动端阅览
杨力铭,温仕宏.人工智能在临床麻醉中的应用进展[J].中山大学学报(医学科学版),2026,47(01):77-83.
YANG Liming,WEN Shihong.Advances in the Application of Artificial Intelligence in Clinical Anesthesia[J].Journal of Sun Yat-sen University(Medical Sciences),2026,47(01):77-83.
杨力铭,温仕宏.人工智能在临床麻醉中的应用进展[J].中山大学学报(医学科学版),2026,47(01):77-83. DOI: 10.11714/jsysu.med.YX20250087.
YANG Liming,WEN Shihong.Advances in the Application of Artificial Intelligence in Clinical Anesthesia[J].Journal of Sun Yat-sen University(Medical Sciences),2026,47(01):77-83. DOI: 10.11714/jsysu.med.YX20250087.
近年来,随着ChatGPT、DeepSeek等大语言模型走进大众视野,人工智能(AI)正成为21世纪发展最迅速的领域之一。随着AI的不断发展,各类新模型层出不穷,特别是通过整合多模态数据实现了更全面的信息捕捉与分析,展现出对AI赋能的临床麻醉诊治决策的显著价值。术前,AI可辅助评估患者整体健康状况,帮助选择合适的麻醉方式,并预测困难气道等潜在风险。术中,AI能协同麻醉医生监测生理指标,从低血压预测和药物自动输注控制系统等方面优化麻醉管理策略。术后,AI可通过预测肺部并发症、术后谵妄及主要不良心血管事件等并发症,加速患者康复并提高长期生存率。本文分析了近年来国内外AI技术在医学领域中的赋能,系统梳理AI在临床麻醉中的应用场景,详细介绍了其在术前患者风险评估,制订个性化麻醉计划,术中麻醉监测、决策支持,术后患者恢复和远期随访等方面的最新进展。同时提出未来研究应加强多模态数据库建设、提升模型泛化能力、开发可解释框架并完善伦理治理,为麻醉医生和相关研究者提供了参考,凸显AI在推动麻醉学科智能化转型中的作用,并为后续研究提供指导意义。
In recent years, with the emergence of large language models like ChatGPT and DeepSeek into the public domain, artificial intelligence (AI) has become one of the most rapidly developing fields of the 21st century. As AI continues to evolve, new models are constantly emerging, particularly through the integration of multimodal data that enables more comprehensive information capture and analysis, demonstrating significant value in supporting clinical anesthesia decision-making. Preoperatively, AI can assist in evaluating patients’ overall health status, aid in selecting appropriate anesthesia methods, and predict potential risks such as difficult airways. Intraoperatively, AI can collaborate with anesthesiologists to monitor physiological parameters and optimize anesthesia management strategies, especially in predicting hypotension and improving automated drug infusion control systems. Postoperatively, AI can predict pulmonary complications, postoperative delirium, and major adverse cardiovascular events, thereby accelerating recovery and improving long-term survival.This article analyzes recent advances in AI technology in medicine worldwide, systematically reviews its application scenarios in clinical anesthesia, and provides detailed accounts of progress in preoperative risk assessment, formulation of personalized anesthesia plans, intraoperative monitoring and decision support, postoperative recovery, and long-term follow-up. It further highlights the need for future research to strengthen multimodal database construction, enhance model generalizability, develop explainable frameworks, and improve ethical governance. By summarizing current achievements and challenges, this review offers valuable reference for anesthesiologists and researchers, underscores the role of AI in driving the intelligent transformation of anesthesiology, and provides guidance for subsequent research directions.
Russell SJ , Norvig P . Artificial intelligence: a modern approach [M]. 2003 .
Tung A , Dutton RP . Anesthesia quality improvement: current state and future opportunities [J]. Anesthesiology , 2025 , 142 ( 1 ): 12 .
《中华麻醉学杂志》编委会“十大科学问题”编著组 . 麻醉与围术期医学亟待解决的十大科学问题(2025版) [J]. 中华麻醉学杂志 , 2025 , 45 ( 1 ): 5 - 13 .
Editorial Board of Chinese Journal of Anesthesiology . Ten scientific questions to be solved in anesthesiology and perioperative medicine (2025 Edition) [J]. Chin J Anesthesiol , 2025 , 45 ( 1 ): 5 - 13 .
熊利泽 . 2025:争做有“人工智能”素养的麻醉人 [J]. 中华麻醉学杂志 , 2025 , 45 ( 1 ): 1 - 2 .
Xiong LZ . 2025: striving to be anesthesiologists with “AI literacy” [J]. Chin J Anesthesiol , 2025 , 45 ( 1 ): 1 - 2 .
刘蓬然 , 霍彤彤 , 陆林 , 等 . 人工智能在医学中的应用现状与展望 [J]. 中华医学杂志 , 2021 , 101 ( 44 ): 7 - 13 .
Liu PR , Huo TT , Lu L , et al . Current status and future prospects of AI in medicine [J]. Chin Med J , 2021 , 101 ( 44 ): 7 - 13 .
胡高凯 , 牛亚楠 , 龚玉康 , 等 . 深度学习在腰椎疾病诊断、手术规划及术后预测中的应用研究进展 [J]. 实用医学杂志 , 2025 , 41 ( 6 ): 921 - 928 .
Hu GK , Niu YN , Gong YK , et al . Research progress on the application of deep learning in lumbar spine disease [J]. J Pract Med , 2025 , 41 ( 6 ): 921 - 928 .
Acosta JN , Falcone GJ , Rajpurkar P , et al . Multimodal biomedical AI [J]. Nat Med , 2022 , 28 ( 9 ): 1773 - 1784 .
Harris J , Matthews J . Artificial intelligence: predicting perioperative problems [J]. Br J Hosp Med (Lond) , 2024 , 85 ( 8 ): 1 - 4 .
Bignami E , Panizzi M , Bellini V . Artificial intelligence for personalized perioperative medicine [J]. Cureus , 2024 , 16 ( 1 ): e53270 .
Singam A . Revolutionizing patient care: a comprehensive review of artificial intelligence applications in anesthesia [J]. Cureus , 2023 , 15 ( 8 ): e49887 .
Xia M , Ma W , Zuo M , et al . Expert consensus on difficult airway assessment [J]. Hepatobiliary Surg Nutr , 2023 ( 4 ): 12 .
Cuendet GL , Schoettker P , Yuce A , et al . Facial image analysis for fully-automatic prediction of difficult endotracheal intubation [J]. IEEE Trans Biomed Eng , 2016 , 63 ( 2 ): 328 - 339 .
Hayasaka T , Kawano K , Kurihara K , et al . Creation of an artificial intelligence model for intubation difficulty classification by deep learning using face images: an observational study [J]. J Intensive Care , 2021 , 9 ( 1 ): 38 .
Ji C , Ni Q , Chen W . Diagnostic accuracy of radiology (CT, X-ray, US) for predicting difficult intubation in adults: a meta-analysis [J]. J Clin Anesth , 2018 , 45 : 79 - 87 .
李玲 , 钟海燕 . 阻塞性睡眠呼吸暂停综合征患者围术期气道管理的研究进展 [J]. 临床麻醉学杂志 , 2023 , 39 ( 9 ): 969 - 972 .
Li L , Zhong HY . Research progress of perioperative airway management in patients with obstructive sleep apnea syndrome [J]. J Clin Anesthesiol , 2023 , 39 ( 9 ): 969 - 972 .
Manlises CO , Chen JW , Huang CC . A gated recurrent unit model based on ultrasound images of dynamic tongue movement for determining the severity of obstructive sleep apnea [J]. Ultrasonics , 2024 , 141 : 107320 .
Turan EH , Baydemir AE , Gümüşcan F , et al . Evaluating the accuracy of ChatGPT-4 in predicting ASA scores: a prospective multicentric study [J]. J Clin Anesth , 2024 , 96 : 111475 .
Elik E , Turgut MA , Aydoğan M , et al . Comparison of AI applications and anesthesiologist's anesthesia method choices [J]. BMC Anesthesiol , 2025 , 25 ( 1 ): 2 .
Shen L , Jin YP , Pan A , et al . Machine learning-based predictive models for perioperative major adverse cardiovascular events in patients with stable coronary artery disease undergoing noncardiac surgery [J]. Comput Methods Programs Biomed , 2025 , 260 : 108561 .
Wang YJ , Yang K , Wen Y , et al . Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging [J]. Nat Med , 2024 , 30 ( 5 ): 1471 - 1480 .
Saugel B , Fletcher N , Gan TJ , et al . PeriOperative quality initiative (POQI) international consensus statement on perioperative arterial pressure management [J]. Br J Anaesth , 2024 , 133 ( 2 ): 13 .
Chen B , Pang QY , An R , et al . A systematic review of risk factors for postinduction hypotension in surgical patients undergoing general anesthesia [J]. Eur Rev Med Pharmacol Sci , 2021 , 25 ( 22 ): 7044 - 7050 .
Katsin M , Glebov M , Berkenstadt H , et al . Developing a machine learning-based prediction model for postinduction hypotension [J/OL]. J Clin Monit Comput , 2025 .[ 2025-09-08 ]. https://doi.org/10.1007/s10877-025-01295-x https://doi.org/10.1007/s10877-025-01295-x .
Jian ZP , Liu XF , Kouz K , et al . Deep learning model to identify and validate hypotension endotypes in surgical and critically ill patients [J]. Br J Anaesth , 2025 , 134 ( 2 ): 308 - 316 .
Coeckelenbergh S , Boelefahr S , Alexander B , et al . Closed-loop anesthesia: foundations and applications in contemporary perioperative medicine [J]. J Clin Monit Comput , 2024 , 38 ( 2 ): 487 - 504 .
Yun WJ , Shin MJ , Jung S , et al . Deep reinforcement learning-based propofol infusion control for anesthesia: a feasibility study with a 3000-subject dataset [J]. Comput Biol Med , 2023 , 156 : 106739 .
Tu Z , Jeffries S , Pelletier E , et al . Deep reinforcement learning for multi-targets propofol dosing [J]. J Clin Monit Comput , 2025 , 39 ( 3 ): 613 - 623 .
Joosten A , Rinehart J , Bardaji A , et al . Anesthetic management using multiple closed-loop systems and delayed neurocognitive recovery: a randomized controlled trial [J]. Anesthesiology , 2020 , 132 ( 2 ): 253 - 266 .
Chandler D , Mosieri C , Kallurkar A , Pham AD , et al . Perioperative strategies for the reduction of postoperative pulmonary complications [J]. Best Pract Res Clin Anaesthesiol , 2020 , 34 ( 2 ): 153 - 166 .
Chen Z , Gu S , Zeng S . Utilising intraoperative respiratory dynamic features for developing and validating an explainable machine learning model for postoperative pulmonary complications. Comment on Br J Anaesth 2024; 132: 1315-26 [J/OL]. Br J Anaesth , 2024 . ( 2024-07-15 )[ 2025-09-08 ]. https://doi.org/10.1016/j.bja.2024.05.035 https://doi.org/10.1016/j.bja.2024.05.035 .
Dodsworth BT , Reeve K , Falco L , et al . Development and validation of an international preoperative risk assessment model for postoperative delirium [J]. Age Ageing , 2023 , 52 ( 6 ): afad086 .
Reeve KA , Schmutz Gelsomino N , Venturini M , et al . Prospective external validation of the automated PIPRA multivariable prediction model for postoperative delirium on real-world data from a consecutive cohort of non-cardiac surgery inpatients [J]. BMJ Health Care Inform , 2025 , 32 : e101291 .
Buros C , Dave AA , Furlan A . Immediate and late complications after liver transplantation [J]. Radiol Clin North Am , 2023 , 61 ( 5 ): 785 - 795 .
Rabindranath M , Sun Y , Khalili K , et al . Utilizing machine learning to predict liver allograft fibrosis by leveraging clinical and imaging data [J]. Clin Transplant , 2025 , 39 ( 4 ): e70148 .
Abdelhameed A , Bhangu H , Feng J , et al . Deep learning-based prediction modeling of major adverse cardiovascular events after liver transplantation [J]. Mayo Clin Proc Digit Health , 2024 , 2 ( 2 ): 221 - 230 .
Zhang JT , Hu XY , Duan W , et al . Application of deep learning-based facial pain recognition model for postoperative pain assessment [J]. J Clin Anesth , 2025 , 105 : 111898 .
Al-Nafjan A , Alshehri H , Aldayel M . Objective pain assessment using deep learning through EEG-based brain-computer interfaces [J]. Biology , 2025 , 14 ( 2 ): 210 .
邓虹 , 黄镇伟 , 许彦君 , 等 . 基于人工智能构建影像增强检查静脉穿刺位点定位模型的临床研究 [J]. 新医学 , 2025 , 56 ( 10 ): 968 - 976 .
Deng H , Huang ZW , Xu YJ , et al . Clinical study of construction of artificial intelligence-based localization model for venous puncture sites in contrast-enhanced imaging examination [J]. J New Med , 2025 , 56 ( 10 ): 968 - 976 .
Bowness JS , Burckett-St Laurent D , Hernandez N , et al . Assistive artificial intelligence for ultrasound image interpretation in regional anaesthesia: an external validation study [J]. Br J Anaesth , 2023 , 130 ( 2 ): 217 - 225 .
0
浏览量
419
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621
