Task Force on Expert Consensus on the Construction and Clinical Application of Anesthesia Information Management Systems
黑子清,中山大学附属第三医院手术麻醉中心,广州 510630,Email: hei-ziqing@sina.com;俞卫锋,上海交通大学医学院附属仁济医院麻醉科,上海 200127,Email: ywf808@yeah.net;王天龙,首都医科大学宣武医院麻醉手术科,北京 100053,Email: w_tl5595@hotmail.com Hei Ziqing, Department of Anesthesiology, the Third Affiliated Hospital of Sun Yat-sen University, Guangzhou 510630, China, Email: heiziqing@sina.com;Yu Weifeng, Department of Anesthesiology, Renji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 200127, China, Email: ywf808@yeah.net;Wang Tianlong, Department of Anesthesiology and Operating Theater, Xuanwu Hospital, Capital Medical University, Beijing 100053, China, Email: w_tl5595@hotmail.com
围术期管理离不开多模态数据生成、监测以及数据驱动临床诊疗[1,2]。这些海量的多源性数据是麻醉信息学研究的基础,其中麻醉信息管理系统(anesthesia information management systems, AIMS)是自动采集和存储数据、记录诊疗活动的载体,承载着围术期全程且有价值的临床大数据[3,4]。2021年我国住院患者手术量高达8 103.1万例次,与之相应,AIMS需要管理海量的围术期数据[5]。基于AIMS的实时性或回顾性数据分析越来越受到临床医师的重视,包括质量控制、临床决策支持系统和机器学习研究等[6]。然而,目前AIMS的建设和数据分析能力有限,满足不了数智化转型和大数据、人工智能研究的需求,尤其是缺乏组织架构和激活围术期信息价值。为了紧跟学术发展前沿和帮助临床医师正确使用AIMS开展临床工作和研究,广东省麻醉医学临床医学研究中心特组织我国麻醉学科及相关领域专家组成工作组,制订本共识以期规范和推广AIMS建设与应用,提高基于AIMS的临床研究质量,并促进麻醉学科数据库的构建。
一、共识的制订方法
本共识由广东省麻醉医学临床医学研究中心发起和负责制订。共识制订小组由麻醉学科及相关领域专家共38人组成,主要成员来自中华医学会麻醉学分会麻醉围术期大数据学组和青年学组。基于共识相关问题在PubMed、Embase、Web of Science、万方数据库和中国知网检索相关文献,纳入来自指南与共识、系统评价、荟萃分析、随机对照试验、队列研究等证据。英文检索词以anesthesia information management systems/AIMS、health information management、informatics和operating room为主;中文检索词以麻醉信息管理系统、手术麻醉管理系统、临床信息学和手术室管理为主。检索时间为建库至2024年5月。工作组成员主要职责是筛选相关文献并凝练推荐意见,初拟解读与证据。然后,秘书组成员组织问卷调查,内容是针对每个推荐意见进行李克特量表(Likert scale)评分,并可自由填写的修改意见和建议。李克特量表评分:7分=非常同意,6分=同意,5分=一般同意,4分=不确定,3分=不太同意,2分=不同意,1分=完全不同意。当推荐意见评分≥6分的专家超过70%,则为该条推荐意见达成共识。本共识共凝练出16条拟推荐意见。专家推荐程度以"共识度"标注,共识度=评分≥6分的专家÷总参评专家人数×100%。
解读与证据:在二十世纪八十年代,美国杜克大学医学中心麻醉系率先研发了自动监测设备系统,用于临床自动采集并记录患者生命体征。这是术中记录的重要部分,也是AIMS的雏形。随着计算机科学发展,AIMS在40余年的临床应用中已实现从监护仪器、麻醉机和床旁检测设备等自动捕获生理和麻醉参数并且以图形或数值形式描记,从而促使麻醉记录从手写纸质版发展到电子无纸化[3,7]。研究表明,在2018年至2020年期间,约有84%的美国大学附属医院完成AIMS的部署,但是大部分美国非大学附属医院和欧洲医院依然尚未部署AIMS(约50%),主要原因是资金不足和缺乏对AIMS深入了解及认识[8,9]。二十一世纪初,我国才开始部署AIMS,也称为手术麻醉信息管理系统。根据《国家卫生健康委办公厅关于印发麻醉科医疗服务能力建设指南(2019年版)的通知》要求,二级及以上医院麻醉科应建立符合国家卫生健康委医院信息化相关要求的麻醉电子信息系统,并以此作为质量控制的技术平台。《国家卫生健康委关于印发〈三级医院评审标准(2022年版)〉及其实施细则的通知》中医疗服务能力与质量安全指标、运行数据等均要求麻醉科完善信息化建设和具备临床数据读取和分析能力。根据《2021-2022年度中国医院信息化状况调查报告》,国内66.1%的医院(二级和三级)已经部署独立AIMS或将其嵌合在医院信息管理系统(hospital information system, HIS)中作为一个子系统。
近年来,除了硬件和网络升级之外,AIMS重要发展是实现了与HIS、电子病历(electronic medical record, EMR)、实验室信息管理系统(laboratory information management system, LIS)、影像归档和通信系统(picture archiving and communication system, PACS)等互联互通,确保系统间的互操作性和集成[6,10]。AIMS可根据需求在不同层面和节点添加功能模块,例如临床决策支持系统、术前评估、麻醉复苏室(post-anesthsia care unit, PACU)管理、术后随访、计费管理、质量控制和统计分析等[10,11]。目前,医院也在稳步推进手术室外部署AIMS,例如在分娩和产房记录产科麻醉,床边手术记录和重症监护室中的急性疼痛服务和麻醉实施情况。基于此,AIMS已演变成为电子健康档案的重要组成部分,发挥提高医护人员和管理者的工作效率、提高手术安全性、增强质量控制等重要作用。这主要体现在:(1)提升医疗质量与安全;(2)提升麻醉记录的完整性及可靠性;(3)改善麻醉和手术流程,提升运行效率;(4)促进临床研究;(5)指引和约束住培麻醉医师医疗行为等;见表1。然而,围术期数据来源众多,具有多源、异构性特征,并且数据间缺乏统一标准约束,数据量大但质量良莠不齐。因此,如何更有效、实时地将AIMS大量的数据进行整合和处理、构建围术期大数据库、实现数智化转型、为不良事件预警及临床诊疗提供辅助证据支持等是AIMS建设和应用的重点内容。
基于AIMS实时采集的多模态数据,对围术期不良事件做出早期预警也是临床研发和应用重点。早在2018年,Lundberg等[53]基于集成模型的机器学习方法(命名为Prescience)可以实时预测全身麻醉期间低氧血症的风险。该解释型模型纳入了20余个静态特征和45个动态特征并且整合赋予不同优势比。在预知模型的辅助下,初始风险预测性能的受试者工作特征曲线下面积(area under the curve, AUC)从0.60提高到0.76,术中实时低氧血症预测(未来5 min)的AUC从0.66提高到0.78。Fang等[54]的研究纳入了1 160例患者术前信息(主要是基本信息和气道评估参数)和术中信息(如监护和用药信息)使用机器学习方法建立模型预测胃肠镜检查时低氧血症发生,结果显示模型预测性能显著优于传统STOP-BANG评分。另外,2018年Hatib等[55]研究表明,基于数千个高保真的有创动脉波形特征的机器学习算法可以提前15 min预测术中低血压事件[平均动脉压<65 mmHg(1 mmHg=0.133 kPa)],灵敏度为88%,特异度为87%。随后该模型衍生的早期预警系统在临床上得到验证,可以降低术中低血压的发生率,但有待更高级别的循证依据来佐证[56]。2022年Palla等[57]利用88 446例手术患者的术前和术中数据(来源于AIMS)开发了一个梯度增强机器学习模型预测PACU期间的低血压,预测模型的AUC为0.82,平均精确度为0.40,并且可以辅助麻醉医师预知低血压的发生。因此,基于机器学习、深度学习方法,可以单独或联合使用AIMS数据对围术期不良或危急事件做出早期预警并进行临床验证,辅助临床医师更有效地管理高危患者,改善患者预后。
推荐意见11:基于指南和临床路径,设计和部署嵌入或平行的临床决策支持系统(clinical decision support system, CDSS),有助于提高临床医师执行麻醉方案和重要干预措施的依从性。(共识度100%)
解读与证据:AIMS的日益普及和数据治理能力提升为开发和部署CDSS提供基础。CDSS是一种为临床医护人员提供临床决策帮助的计算机系统,常见类型主要是被动型(passive)、事后主动型(post hoc active)和实时型(real-time active)[58]。每个类型CDSS各有优缺点,既可以与AIMS整合,也可以独立部署(平行关系)。为了规范医疗机构CDSS应用管理,2023年7月国家卫生健康委办公厅颁布了《医疗机构临床决策支持系统应用管理规范(试行)》。CDSS在围术期扮演着"助手"的角色,可协助医护人员进行复杂的流程管理和诊疗活动。参考脓毒血症CDSS的研发和应用,目前多种CDSS能实时采集和分析临床数据并嵌合在HIS中发挥着"早期识别"的作用,灵敏度和特异度均表现良好[59]。但是究竟如何设计与部署CDSS存在相当大的考验,需要重点考虑数据接口、数据转换和延时、决策规则、报警疲劳、伦理和安全问题等[58,60]。另外,CDSS可尝试结合现有大型语言模型技术,实现术中AI助手,通过会话模式进行交互,提供更贴近患者的专有麻醉建议。
目前,针对某单一或相关事件的CDSS已开始应用到临床辅助决策,包括:(1)通过宣教、反馈、定期总结报告、实时提醒等多模式CDSS可以显著提高手术切皮前(0.5~1.0 h)预防性使用抗生素和术中再次使用抗生素的依从性[61,62];(2)实时监测与提醒调节新鲜气体流量,实现麻醉维持阶段的低流量麻醉(<1 L/min),从而减少吸入麻醉气体的消耗量和废气量[63];(3)实时识别肺损伤风险因素,监测和提醒实施肺保护通气策略[64];(4)基于指南,术前计算每例患者术后恶心呕吐(postoperative nausea and vomiting, PONV)的风险,实时提醒执行防治恶心呕吐的用药方案,显著提高用药规范性[65,66]。例如术前自动生成PONV风险程度并通知麻醉医师,并且每周向其发送前一周关于PONV的统计报告,两者结合明显降低高危患者PONV发生率;(5)实时提醒执行围术期血糖管理方案,规范定时测量血糖值和正确使用胰岛素剂量的行为,有利于维持围术期的血糖稳定,降低术后伤口感染的风险[67];(6)实时计费与反馈CDSS对准确、及时地完成麻醉收费有帮助[68];(7)自动捕捉麻醉不良事件,报告的时间节点设置应在交接班或转送PACU、病房前完成,有助于提升麻醉质量,但研究结论存在矛盾[69,70]。然而,以大数据为基础的CDSS尚处于研发阶段,建议未来基于围术期大数据库研发主动型、预测型CDSS覆盖涉及医疗质量与安全的每个环节,以满足不同的临床场景。
参考文献佘守章,俞卫锋. 加强临床监测智能化研究 提升患者围麻醉手术期安全性[J]. ,2023,43(7):778-780.DOI:10.3760/cma.j.cn131073.20230709.00703.ZhangS, LiH, JingQ, et al. Anesthesia decision analysis using a cloud-based big data platform[J]. ,2024,29(1):201.DOI:10.1186/s40001-024-01764-0.SimpaoAF, RehmanMA. Anesthesia information management systems[J]. ,2018,127(1):90-94.DOI:10.1213/ANE.0000000000002545.冯靖祎,陈华,祝胜美.麻醉信息管理系统的设计与临床实践[J].,2010,90(35):2514-2517.DOI:10.3760/cma.j.issn.0376-2491.2010.35.018.国家卫生健康委员会. [M]. 北京:中国协和医科大学出版社,2022:131.SimpaoAF, RehmanMA. Anesthesia Informatics in 2018[J]. ,2019,37:145-162.DOI:10.1016/j.aan.2019.08.006.RozentalO, WhiteRS. Anesthesia information management systems: evolution of the paper anesthetic record to a multisystem electronic medical record network that streamlines perioperative care[J]. ,2019,5(3):93-98.DOI:10.1016/j.janh.2019.04.001.StolIS, EhrenfeldJM, EpsteinRH. Technology diffusion of anesthesia information management systems into academic anesthesia departments in the United States[J]. ,2014,118(3):644-650.DOI:10.1213/ANE.0000000000000055.BruthansJ, BláhaJ. Usage of anesthesia information management systems in European countries in 2020 - a short survey[J]. ,2020,50 (4):127-131.DOI:10.14311/ctj.2020.4.01.GálvezJA, RothmanBS, DoyleCA, et al. A narrative review of meaningful use and anesthesia information management systems[J]. ,2015,121(3):693-706.DOI:10.1213/ANE.0000000000000881.MuravchickS, CaldwellJE, EpsteinRH, et al. Anesthesia information management system implementation: a practical guide[J]. ,2008,107(5):1598-1608.DOI:10.1213/ane.0b013e318187bc8f.刘凡,李宝伟,曹江北,等. 医院手术室麻醉智慧化管理系统的构成及功能浅析[J]. ,2023,10(2):6-10.DOI:10.19450/j.cnki.jcrh.2023.02.002.易斌,李洪. 围手术期大数据的应用与展望[J]. ,2023,45(8):725-731.DOI:10.16016/j.2097-0927.202302091.DetmerDE, ShortliffeEH. Clinical informatics: prospects for a new medical subspecialty[J]. ,2014,311(20):2067-2068.DOI:10.1001/jama.2014.3514.HoferIS, LevinMA, SimpaoAF, et al. Anesthesia informatics grows up[J]. ,2018,127(1):18-20.DOI:10.1213/ANE.0000000000003431.KristobakBM, JabautJM, DicksonCF, et al. Leveraging the existing anesthesia information management system to improve anesthesia quality assurance outcome reporting[J]. ,2021,186(9-10):1001-1009.DOI:10.1093/milmed/usab051.KazemiP, LauF, SimpaoAF, et al. The state of adoption of anesthesia information management systems in Canadian academic anesthesia departments: a survey[J]. ,2021,68(5):693-705.DOI:10.1007/s12630-021-01924-4.BouhenguelJT, PreissDA, UrmanRD. Implementation and use of anesthesia information management systems for non-operating room locations[J]. ,2017,35(4):583-590.DOI:10.1016/j.anclin.2017.07.001.KazemiP, LauF, MatavaC, et al. An environmental scan of anesthesia information management systems in the American and Canadian marketplace[J]. ,2021,45(12):101.DOI:10.1007/s10916-021-01781-0.中国卫生信息与健康医疗大数据学会.手术室麻醉信息系统基本功能规范T/CHIA 51-2024[S/OL].[2024-03-21].http://www.chim.org.cn/.中国卫生信息与健康医疗大数据学会重症医学分会,北京肿瘤学会重症医学专业委员会. 重症大数据应用中国专家共识(2022)[J]. ,2023,103(6): 404-424.DOI:10.3760/cma.j.cn112137-20221008-02098.赵宇卓,王俊梅,潘菲,等.急救数据库建设初探[J]. ,2018,30(6):609-612.DOI:10.3760/cma.j.issn.2095-4352.2018.06.022.中山大学附属第三医院.[M]. 北京:科学出版社,2021:1-311.中国老年医学学会.围术期数据规范T/CGSS 017-2021[S/OL].[2021-04-14]. https://www.ttbz.org.cn/StandardManage/Detail/46154/.毛中亮,冯莉,娄景盛等.围术期多中心数据中心的设计与应用[J]. ,2021,45(3):292-295.DOI:10.3969/j.issn.1671-7104.2021.03.013.EpsteinRH, DexterF. Database quality and access issues relevant to research using anesthesia information management system data[J]. ,2018,127(1):105-114.DOI:10.1213/ANE.0000000000003324.WilbanksBA. An integrative literature review on accuracy in anesthesia information management systems[J]. ,2014,32(2):56-63.DOI:10.1097/NXN.0b013e3182a041f7.SimpaoAF, GalvezJA, EnglandWR, et al. A technical evaluation of wireless connectivity from patient monitors to an anesthesia information management system during intensive care unit surgery[J]. ,2016,122(2):425-429.DOI:10.1213/ANE.0000000000001064.ArièsP, BensafiaK, MansourA, et al. Design and evaluation of a wireless electrocardiogram monitor in an operating room: a pilot study[J]. ,2019,129(4):991-996.DOI:10.1213/ANE.0000000000003972.PybusDA. Expanding the role of mobile devices in the operating room: direct wireless connection to the anesthesia monitor[J]. ,2015,29(3):785-790.DOI:10.1053/j.jvca.2014.10.009.国家市场监督管理局,中国国家标准化管理委员会. 信息安全技术-网络安全等级保护实施指南GB/T 25058-2019[S/OL].[2019-08-30]. https://std.samr.gov.cn/gb/search/gbDetailed?id=91890A0DA5F980C6E05397BE0A0A065D.国家市场监督管理局,中国国家标准化管理委员会. 信息安全技术-数据安全能力成熟度模型GB/T 37988-2019[S/OL].[2019-08-30].https://std.samr.gov.cn/gb/search/gbDetailed?id=91890A0DA63380C6E05397BE0A0A065D.SharmaM, KarkiD, DhungelS, et al. Manual anesthesia record keeping at a tertiary care center: a descriptive cross-sectional study[J]. ,2021,59(244):1262-1266.DOI:10.31729/jnma.7117.VigodaMM, LubarskyDA. Failure to recognize loss of incoming data in an anesthesia record-keeping system may have increased medical liability[J]. ,2006,102(6):1798-1802.DOI:10.1213/01.ane.0000217235.25350.5e.van SchalkwykJM, LowesD, FramptonC, et al. Does manual anaesthetic record capture remove clinically important data?[J]. ,2011,107(4):546-552.DOI:10.1093/bja/aer163.何伟,王涛,马艳凯,等.手术麻醉信息系统对麻醉文书质量的影响[J].,2018,19(1):37-39.DOI:10.3969/j.issn.1672-2566.2018.01.014.TayeMG, FentaE, TamireT, et al. Assessment of perioperative anesthesia record sheet completeness: a multi-center observational study[J]. ,2022, 79:104103.DOI:10.1016/j.amsu.2022.104103.WaxDB, BeilinY, HossainS, et al. Manual editing of automatically recorded data in an anesthesia information management system[J]. ,2008, 109(5):811-815.DOI:10.1097/ALN.0b013e3181895f70.HoorwegAJ, PasmaW, van WolfswinkelL, et al. Incidence of artifacts and deviating values in research data obtained from an anesthesia information management system in children[J]. ,2018,128(2):293-304.DOI:10.1097/ALN.0000000000001895.AvidanA, WeissmanC. Record completeness and data concordance in an anesthesia information management system using context-sensitive mandatory data-entry fields[J]. ,2012,81(3):173-181.DOI:10.1016/j.ijmedinf.2011.12.009.SandbergWS, SandbergEH, SeimAR, et al. Real-time checking of electronic anesthesia records for documentation errors and automatically text messaging clinicians improves quality of documentation[J]. ,2008,106(1):192-201.DOI:10.1213/01.ane.0000289640.38523.bc.TollincheLE, ShiR, HannumM, et al. The impact of real-time clinical alerts on the compliance of anesthesia documentation: a retrospective observational study[J]. ,2020,191:105399.DOI:10.1016/j.cmpb.2020.105399.国家麻醉专业质量控制中心.围术期患者低体温防治专家共识(2023版)[J].,2023,39(7):764-771.DOI:10.12089/jca.2023.07.018.黑子清,陈柄城,刘子锋,等.麻醉科围术期专科数据库的建设和应用[J].,2021,16(1):13-16,22.DOI:10.3969/j.issn.1673-7571.2021.01.003.LeeHC, ParkY, YoonSB, et al. VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients[J]. ,2022,9(1):279.DOI:10.1038/s41597-022-01411-5.SamadM, AngelM, RinehartJ, et al. Medical Informatics Operating Room Vitals and Events Repository (MOVER): a public-access operating room database[J]. ,2023,6(4):ooad084.DOI:10.1093/jamiaopen/ooad084.LeeHC, JungCW. Vital Recorder-a free research tool for automatic recording of high-resolution time-synchronised physiological data from multiple anaesthesia devices[J]. ,2018,8(1):1527.DOI:10.1038/s41598-018-20062-4.LamerA, MoussaMD, MarcillyR, et al. Development and usage of an anesthesia data warehouse: lessons learnt from a 10-year project[J]. ,2023,37(2):461-472.DOI:10.1007/s10877-022-00898-y.DuranHT, KingeterM, RealeC, et al. Decision-making in anesthesiology: will artificial intelligence make intraoperative care safer?[J]. ,2023,36(6):691-697.DOI:10.1097/ACO.0000000000001318.LopesS, RochaG, Guimarães-PereiraL. Artificial intelligence and its clinical application in Anesthesiology: a systematic review[J]. ,2024,38(2):247-259.DOI:10.1007/s10877-023-01088-0.ZhangY, YangD, LiuZ, et al. An explainable supervised machine learning predictor of acute kidney injury after adult deceased donor liver transplantation[J]. ,2021,19(1):321.DOI:10.1186/s12967-021-02990-4.ChenC, ChenB, YangJ, et al. Development and validation of a practical machine learning model to predict sepsis after liver transplantation[J]. ,2023,55(1):624-633.DOI:10.1080/07853890.2023.2179104.LundbergSM, NairB, VavilalaMS, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery[J]. ,2018,2(10):749-760.DOI:10.1038/s41551-018-0304-0.FangZ, ZouD, XiongW, et al. Dynamic prediction of hypoxemia risk at different time points based on preoperative and intraoperative features: machine learning applications in outpatients undergoing esophagogastroduodenoscopy[J]. ,2023,55(1):1156-1167.DOI:10.1080/07853890.2023.2187878.HatibF, JianZ, BuddiS, et al. Machine-learning algorithm to predict hypotension based on high-fidelity arterial pressure waveform analysis[J]. ,2018,129(4):663-674.DOI:10.1097/ALN.0000000000002300.WijnbergeM, GeertsBF, HolL, et al. Effect of a machine learning-derived early warning system for intraoperative hypotension vs standard care on depth and duration of intraoperative hypotension during elective noncardiac surgery: the HYPE randomized clinical trial[J]. ,2020,323(11):1052-1060.DOI:10.1001/jama.2020.0592.PallaK, HylandSL, PosnerK, et al. Intraoperative prediction of postanaesthesia care unit hypotension[J]. ,2022,128(4):623-635.DOI:10.1016/j.bja.2021.10.052.NairBG, GabelE, HoferI, et al. Intraoperative clinical decision support for anesthesia: a narrative review of available systems[J]. ,2017,124(2):603-617.DOI:10.1213/ANE.0000000000001636.AckermannK, BakerJ, GreenM, et al. Computerized clinical decision support systems for the early detection of sepsis among adult inpatients: scoping review[J]. ,2022,24(2):e31083.DOI:10.2196/31083.HarutyunyanR, JeffriesSD, Ramírez-GarcíaLunaJL, et al. Clinical performance of decision support systems in anesthesia, intensive care, and emergency medicine: a systematic review and meta-analysis[J]. ,2023,136(6):1084-1095.DOI:10.1213/ANE.0000000000006500.HinckerA, Ben AbdallahA, AvidanM, et al. Electronic medical record interventions and recurrent perioperative antibiotic administration: a before-and-after study[J]. ,2017,64(7):716-723.DOI:10.1007/s12630-017-0885-1.O′SullivanCT, RogersWK, AckmanM, et al. Implementation of a multifaceted program to sustainably improve appropriate intraoperative antibiotic redosing[J]. ,2019,47(1):74-77.DOI:10.1016/j.ajic.2018.06.007.OlmosAV, RobinowitzD, FeinerJR, et al. Reducing volatile anesthetic waste using a commercial electronic health record clinical decision support tool to lower fresh gas flows[J]. ,2023,136(2):327-337.DOI:10.1213/ANE.0000000000006242.BlumJM, StentzMJ, MaileMD, et al. Automated alerting and recommendations for the management of patients with preexisting hypoxia and potential acute lung injury: a pilot study[J]. ,2013,119(2):295-302.DOI:10.1097/ALN.0b013e3-182987af4.GrussCL, KappenTH, FowlerLC, et al. Automated feedback modestly improves perioperative treatment adherence of postoperative nausea and vomiting[J]. ,2023,86:111081.DOI:10.1016/j.jclinane.2023.111081.GabelE, ShinJ, HoferI, et al. Digital quality improvement approach reduces the need for rescue antiemetics in high-risk patients: a comparative effectiveness study using interrupted time series and propensity score matching analysis[J]. ,2019,128(5):867-876.DOI:10.1213/ANE.0000000000003828.EhrenfeldJM, WandererJP, TerekhovM, et al. A perioperative systems design to improve intraoperative glucose monitoring is associated with a reduction in surgical site infections in a diabetic patient population[J]. ,2017,126(3):431-440.DOI:10.1097/ALN.0000000000001516.NairBG, NewmanSF, PetersonGN, et al. Smart Anesthesia Manager™ (SAM)-a real-time decision support system for anesthesia care during surgery[J]. ,2013,60(1):207-210.DOI:10.1109/TBME.2012.2205384.WandererJP, GratchDM, JacquesPS, et al. Trends in the prevalence of intraoperative adverse events at two academic hospitals after implementation of a mandatory reporting system[J]. ,2018,126(1):134-140.DOI:10.1213/ANE.0000000000002447.SahaAK, SegalS. A quality improvement initiative to reduce adverse effects of transitions of anesthesia care on postoperative outcomes: a retrospective cohort study[J]. ,2024,140(3):387-398.DOI:10.1097/ALN.0000000000004839.RothmanBS, DexterF, EpsteinRH. Communication latencies of Apple push notification messages relevant for delivery of time-critical information to anesthesia providers[J]. ,2013,117(2):398-404.DOI:10.1213/ANE.0b013e318299a7f7.GörgesM, WestNC, PetersenCL, et al. Development and implementation of the portable operating room tracker app with vital signs streaming infrastructure: operational feasibility study[J]. ,2019,2(2):e13559.DOI:10.2196/13559.XiaoY, HuP, HuH, et al. An algorithm for processing vital sign monitoring data to remotely identify operating room occupancy in real-time[J]. ,2005,101(3):823-829.DOI:10.1213/01.ane.0000167948.81735.5b.LinCC, ChenYP, ChiangCC, et al. Real-time streaming of surgery performance and intraoperative imaging data in the hybrid operating room: development and usability study[J]. ,2020,8(4):e18094.DOI:10.2196/18094.BottaniE, BelliniV, MordoniniM, et al. Internet of things and new technologies for tracking perioperative patients with an innovative model for operating room scheduling: protocol for a development and feasibility study[J]. ,2023,12:e45477.DOI:10.2196/45477.WaxDB, AdeelA, HuangJ, et al. Click for help: an anesthesiology department messaging system[J]. ,2021,45(6):68.DOI:10.1007/s10916-021-01744-5.WongMJ, WangY, BlakeL, et al. Preventing controlled substance diversion in perioperative settings: a narrative review[J]. ,2023,70(12):1989-2001.DOI:10.1007/s12630-023-02574-4.ShahN, SinhaA, ThompsonA, et al. An automated software application reduces controlled substance discrepancies in perioperative areas[J]. ,2019,131(6):1264-1275.DOI:10.1097/ALN.0000000000002957.SpringSF, SandbergWS, AnupamaS, et al. Automated documentation error detection and notification improves anesthesia billing performance[J]. ,2007,106(1):157-163.DOI:10.1097/00000542-200701000-00025.ReichDL, KahnRA, WaxD, et al. Development of a module for point-of-care charge capture and submission using an anesthesia information management system[J]. ,2006,105(1):179-186.DOI:10.1097/00000542-200607000-00028.KahnRA, GalJS, HoferIS, et al. Visual analytics to leverage anesthesia electronic health record[J]. ,2022,135(5):1057-1063.DOI:10.1213/ANE.0000000000006175.EpsteinRH, DexterF, PatelN. Influencing anesthesia provider behavior using anesthesia information management system data for near real-time alerts and post hoc reports[J]. ,2015,121(3):678-692.DOI:10.1213/ANE.0000000000000677.MalaperoRJ, GabrielRA, GimlichR, et al. An anesthesia medication cost scorecard-concepts for individualized feedback[J]. ,2015,39(5):48.DOI:10.1007/s10916-015-0226-2.WetmoreD, GoldbergA, GandhiN, et al. An embedded checklist in the Anesthesia Information Management System improves pre-anaesthetic induction setup: a randomised controlled trial in a simulation setting[J]. ,2016, 25(10):739-746.DOI:10.1136/bmjqs-2015-004707.GhalyRF, KushnarevM, PirvulescuI, et al. A novel checklist for anesthesia in neurosurgical cases[J]. ,2021,12:184.DOI:10.25259/SNI_285_2021.乡汝浩,刘春燕,潘宝珊,等.广东省住院医师规范化培训回顾与展望[J].,2024,8(1):7-12.DOI:10.3969/j.issn.2096-4293.2024.01.002BhutianiM, JablonskiPM, EhrenfeldJM, et al. Decision support tool improves real and perceived anesthesiology resident relief equity[J]. ,2018,127(2):513-519.DOI:10.1213/ANE.0000000000003479.WandererJP, LaskoTA, CocoJR, et al. Visualization of aggregate perioperative data improves anesthesia case planning: a randomized, cross-over trial[J]. ,2021,68:110114.DOI:10.1016/j.jclinane.2020.110114.BeierJ, AhrensE, RufinoM, et al. The impact of residency training level on early postoperative desaturation: a retrospective multicenter cohort study[J]. ,2023,90:111238.DOI:10.1016/j.jclinane.2023.111238.