智能消化内镜质控系统在胃镜检查中的应用价值研究

目的:评价智能消化内镜质控系统在胃镜检查中的质量控制作用。方法:将来自武汉大学人民医院的14例内镜医师按随机数字法分配到质控组和对照组。在质控前阶段（2019年4月20日—2019年5月31日）,回顾性收集入组内镜医师的胃镜检查资料信息。在质控培训阶段（2019年6月1—30日）,质控组内镜医师培训质控相关知识和智能消...     

丙泊酚在结肠镜检查中的应用

结肠镜广泛应用在结肠疾病的诊断和治疗中,但在操作中人为肠拌或肠痉挛等因素,给患者带来不同程度的痛苦,完全没有痛苦的操作是医患双方共同追求的目标。2001年8月～12月,我院消化内科和麻醉科共同合作,把短效麻醉剂丙泊酚应用在结肠镜检查中,并观察和总结其镇痛作用及安全性。 一、资料和方法 1.病例选择:A组169例,年龄17～72岁,自愿接受丙泊酚全身麻醉后进行肠镜检查,且没有丙泊酚使用禁忌症。B组170例,年龄 20～70岁,同时期未经全身麻醉接受肠镜检查者,条件与A组相似。 2.方法:两组患者检查前20 min肌注阿托品1mg后,A组按丙泊酚2mg/kg缓慢静脉注射,并同时进镜至意识消失后以1～4.5mg·kg-1·h-1速度维持,肠镜进至回盲部停药,全程总用量（98.5±12.75）mg。接受丙泊酚静脉注射者,一般在停药3～5 min后清醒,再1～2 min后恢复定向力和自知力。     

西甲硅油乳剂在结肠镜检查中的应用与研究

目的 研究西甲硅油乳剂在结肠镜检查术前肠道准备中的应用价值.方法 将200例接受结肠镜检查的患者随机分为两组,实验组100例,对照组100例.实验组给予聚乙二醇电解质散+西甲硅油乳剂,对照组给予口服聚乙二醇电解质散.观察二组的效果.结果 实验组肠腔内气泡存在量明显少于对照组,术后腹胀程度明显轻于对照组,内镜医师操作满意度优于对照组(P＜0.05),而两组肠道清洁程度无差异(P＞0.05).结论 在结肠镜检查术前肠道准备中应用西甲硅油乳剂能够消除泡沫,提高视野清晰度,减少术后腹胀等不良反应,提高术者操作舒适度,缩短操作时间.     

氧化亚氮吸入在结肠镜检查中的应用

结肠镜检查往往给患者带来不同程度的痛苦,2002年1月-12月,我院开展氧化亚氮吸入下结肠镜检查,效果满意,现总结如下。     

实时肠道准备评估系统(ENDOANGEL)在结肠镜检查肠道准备质量评估中的应用

目的 探讨实时肠道准备评估系统(ENDOANGEL)在结肠镜检查肠道准备质量评估中的应用价值。方法 前瞻性纳入2021年3—12月湖北医药学院附属襄阳市第一人民医院消化内镜检查患者1 360例,随机分为ENDOANGEL辅助结肠镜检查组(680例)和常规结肠镜检查组(680例),进行肠道清洁度的判断和评价。在常规结肠镜检查组中,内镜医师和护士在退镜阶段使用BBPS量表的肠道清洁质量评分评估肠道准备的质量。在内镜辅助系统(ENDOANGEL)结肠镜检查组退镜阶段增加了内镜系统辅助技术,其他技术保持不变。结果 ENDOANGEL内镜辅助结肠镜组肠道准备质量评分的准确度明显优于常规结肠镜组,差异有统计学意义(P<0.05),两组在3分的准确度上无显著性差异(P> 0.05),但ENDOANGEL内镜辅助结肠镜组的0分、1分和2分评分准确度高于常规结肠镜组,差异有统计学意义(P<0.05)。结论 ENDOANGEL可用于评价结肠镜的准备质量,具有较好的特异性和敏感性。它可以帮助内镜医师在结肠镜检查过程中进行实时监测,积极提示肠道清洁度评分,避免观察者的判断偏差,提高结肠镜检查...     

腹带在困难结肠镜检查中的临床应用研究

为评估腹带在低体重指数（body mass index ,BMI）（BMI<18.5 kg/m²）及有腹部手术史患者结肠镜检查中的效果,针对门诊结肠镜检查患者进行随机对照试验。纳入2018年1月至2022年1月在苏州大学附属第二医院接受结肠镜检查的低BMI或有腹部手术史患者,按是否使用腹带分为腹带组和无腹带组。比较两组在盲肠插管时间、结肠镜插入盲肠长度、翻身情况、压腹情况及腹胀程度方面的差异。共有296例患者（98例低BMI患者和198例腹部手术史患者）入组,有无腹带组各148例。结果显示,腹带组相较于无腹带组,盲肠插管时间［（4.35±1.85）min比（7.99±3.86）min,t=35.624 ,P<0.001］和结肠镜插入盲肠长度［（72.03±10.35）cm比（86.42±17.71）cm,t=38.442 ,P<0.001］显著减少,患者需要翻身的百分比［18.9%（28/148）比71.6%（106/148）,χ2=82.959 ,P<0.001］、压腹的百分比［6.1%（9/148）比52.7%（78/148）,χ2=77.504,P<0.001］显著减少,检查中和检查后两组患者腹胀程度差异有统计学意义（P<0.001）。综上,对于低BMI和腹部手术史的困难结肠镜患者,使用腹带能显著提高结肠镜插入的效率和效果。     

窄带成像系统在结肠镜检查中的应用

结肠镜检查目前广泛应用于下消化道疾病的诊断，不仅能直接观察结，直肠病变，还能活检病变进行病理学诊断，开展各种内镜下的微创治疗。随着内镜技术的提高和染色内镜、放大内镜的普及，大部分结、直肠病变都能及早发现。近年来开发的窄带成像（narrow-band imaging,NBI）系统被认为能提高消化道黏膜表面结构的观察水平。     

异丙酚静脉麻醉辅助结肠镜检查的应用研究

目的 探讨应用异丙酚作镇静麻醉辅助结肠镜检查的可行性，评价其效果和安全性。方法 将2210例结肠镜检查患者随机分为2组：麻醉组（2000例）静脉注射异丙酚至患者进入4级镇静状态后进行结肠镜检查。对照组（210例）按常规进行结肠镜检查。观察2组检查前，检查开始后1，5，20min和检查结束后的血压，脉搏，血氧饱和度以及检查反应和入镜时间。结果 检查过程中，麻醉组的平均收缩压各时段无明显变化（P＞0．05），对照组变化明显（P＜0．01）。2组的平均舒张压，脉搏和血氧饱和度在相应各时段的变化均无显著性差异（P＞0．05）。麻醉组的入镜时间和检查反应明显优于对照组（P＜0．01）。结论 异丙酚辅助结肠镜检查是安全有效，其入镜时间和检查反应优于普通检查。     

注水法在婴幼儿结肠镜检查中的应用

目的比较注气法和注水法在婴幼儿结肠镜检查中的达盲时间、麻醉药物剂量等，探索注水法结肠镜检查在婴幼儿中的应用价值。 方法收集2019年1月至2020年9月经吉林大学第一医院小儿消化科行无痛结肠镜检查的71例患儿，年龄为月龄≤72个月，其中，观察组为注水法35例，对照组为同期行传统注气法36例。应用SPSS统计学软件分析比较两组患者的达盲率、达盲时间、达盲时丙泊酚用量等差异，并探讨注水法中注水量的影响因素。 结果观察组的达盲率为100%，对照组的达盲率为94.4%，差异无统计学意义；观察组的达盲时间(8.66±4.20)min，显著少于对照组达盲时间(16.69±9.22)min(P<0.05)；观察组达盲时丙泊酚用量(64.00±18.50)mg显著少于对照组丙泊酚用量(83.33±25.72)mg(P<0.05)。对注水法结肠镜注水量的相关因素分析中，发现肠道准备程度与注水量之间具有显著相关性(P<0.05)。 结论注水法在婴幼儿结肠镜中安全、可靠，适合在临床推广、应用。     

Audit and feedback interventions to improve endoscopist performance: Principles and effectiveness

There is considerable variation in the quality of colonoscopy, attributable in part to endoscopist performance. Audit and feedback (A&F) provides health professionals with a summary of their performance over a period of time and is a common strategy used to improve provider performance. In this review, we discuss current understanding of the mechanism of A&F and describe specific features of effective A&F. To date, trials of A&F to improve colonoscopy performance report heterogeneous results, in part because colonoscopy is a complex procedural skill but also because the quality improvement interventions were sub-optimally implemented or inadequately evaluated. Nonetheless, evidence from a wide range of literature suggests that A&F has the potential to improve endoscopist performance. We discuss future directions for research in this area and provide guidance for providers or health system planners wishing to implement A&F to address quality of colonoscopy in their practice and/or jurisdiction.     

基于深度学习的消化内镜检查辅助质量控制系统研究（含视频）

目的构建智能消化内镜质控系统并评估其在胃肠镜检查中的质量监控作用。方法基于医学数字成像与通信协议,获取武汉大学人民医院消化内镜中心2016年12月—2018年10月胃肠镜检查患者的电子医疗记录和图像,采用深度卷积神经网络和深度强化学习方法开发智能消化内镜质控系统。该系统运用回盲部识别模型、体内外图像识别模型以及胃的26个部位识别模型,监控达盲率、肠镜退镜时间、胃镜检查时间、胃镜检查覆盖部位数等质控指标。随机选取武汉大学人民医院消化内镜中心2019年3—11月83例胃镜检查和205例肠镜检查患者的图像,测试智能消化内镜质控系统质量控制功能的准确性。结果智能消化内镜质控系统由胃镜质量分析、肠镜质量分析组成,可随时自动生成包含各质控指标的内镜医师胃肠镜检查质控报告。该系统监控的达盲率、肠镜退镜时间、胃镜检查时间和胃镜检查覆盖部位数的准确率分别为92.5%（172/186）、91.7%（188/205）、100.0%（83/83）和89.3%（1 928/2 158）。结论智能消化内镜质控系统可实现胃肠镜检查的质量监控作用,以便内镜医师了解自身的工作情况,从而提升胃肠镜检查质量。     

Establishing a model to measure and predict the quality of gastrointestinal endoscopy

BACKGROUND Tens of millions of gastrointestinal endoscopic procedures are performed every year in China,but the quality varies significantly and related factors are complex.Individual endoscopist-and endoscopy division-related factors may be useful to establish a model to measure and predict the quality of endoscopy.AIM To establish a model to measure and predict the quality of gastrointestinal endoscopic procedures in China's Mainland.METHODS Selected data on endoscopy experience,equipment,facility,qualification of endoscopists,and other relevant variables were collected from the National Database of Digestive Endoscopy of China.The multivariable logistic regression analysis was used to identify the potential predictive variables for occurrence of medical malpractice and patient disturbance.Linear and nonlinear regressions were used to establish models to predict incidence of endoscopic complications.RESULTS In 2012,gastroscopy/colonoscopy-related complications in China's Mainland included bleeding in 4,359 cases(0.02%)and perforation in 914(0.003%).Endoscopic-retrograde-cholangiopancreatography-related complications included severe acute pancreatitis in 593 cases(0.3%),bleeding in 2,151(1.10%),perforation in 257(0.13%)and biliary infection in 4,125(2.11%).Moreover,1,313(5.0%)endoscopists encountered with medical malpractice,and 5,243(20.0%)encountered with the disturbance from patients.The length of endoscopy experience,weekly working hours,weekly night shifts,annual vacation days and job satisfaction were predictors for the occurrence of medical malpractice and patient disturbance.However,the length of endoscopy experience and the ratio of endoscopists to nurses were not adequate to establish an effective predictive model for endoscopy complications.CONCLUSION The workload and job satisfaction of endoscopists are valuable predictors for medical malpractice or patient disturbance.More comprehensive data are needed to establish quality-predictive models for endoscopic complications.     

A prospective intervention study of colonoscopy reporting among patients screened or surveilled for colorectal neoplasia

BACKGROUND:

The impact of modifying electronic colonoscopy reporting software for improving adherence to guidelines regarding quality standards documentation remains poorly characterized.

METHODS:

Consecutive colonoscopy reports of patients undergoing screening or surveillance for colorectal neoplasia were reviewed. Following a pre-intervention quality audit conducted in 2009, some modifications were made to the reporting software (Endoworks, Olympus Corporation, USA), including changes to field navigation, drop-down menus and visual cues, to optimize all compulsory items identified by existing guidelines in the report-generating template. Results from both audits were compared. Independent validation of 10% of all data was completed.

RESULTS:

In 250 patient reports (mean [± SD] age 61.7±10.2 years, 51.2% female, February to May 2011) of five endoscopists (mean 11.6±7.8 years in practice), procedural indication was always present, as was informed consent. Seventy-six per cent of patients had undergone previous colonoscopy, 41% provided a previous colonoscopy date, with details on past polyp removal in 42.9%. Most procedural indicators were recorded (examination date 100%, medications given 100%, difficulty level 96.4%, preparation quality 100%). All reports noted extent of visualization (cecal intubation in 97.6%, photo documentation in 96.8%). Total procedural time was recorded in 8.2% and withdrawal time in 44%. Polyps were reported in 112 patients (44.8%), with polyp size (5.01±4.42 mm) reported in 95.5%, morphology in 88.4% and anatomical location in all. The method of polyp removal was missing in 2.7% of reports. Significant improvements were noted in the documentation of withdrawal and total time, cecal landmarks, type of bowel preparation, completeness of removal, morphology and method of polyp removal, and photo documentation compared with the 2009 audit.

CONCLUSION:

These results illustrate the value of targeted modifications to an electronic colonoscopic reporting system in significantly enhancing the quality of reporting.     

结肠镜人工智能辅助诊断模型的构建

目的 运用临床结肠镜检查图像和视频,构建结肠镜辅助诊断人工智能深度学习模型。 方法 收集浙江大学医学院附属第二医院内镜中心2014年至2018年的结肠镜图像60余万幅,内镜专家录制大量高质量的结肠镜手术操作视频,以此作为分析数据。训练集样本的每个细分类别图像由6位内镜专家阅片,讨论确定细分类别病变特征,并删减部分模糊和易混淆的分类图像,最终的阅片结果大约为4选1。后再由自主开发的软件逐一标注。采用公信力最高的Google公司TensorFlow平台,对其深度学习算法进行二次开发。 结果 经过机器训练结果与内镜专家结合病理的判断结果进行反复的对比分析,在实验室条件下,该模型对部分疾病（如结肠息肉）的灵敏度为99%。在临床结肠镜操作实验中,该模型对结肠息肉的灵敏度为9830%（4 187/4 259）,特异度为8810%（17 620/20 000）,诊断结肠息肉的总体准确率为9292%[2×（9830%×8810%）/(9830%+8810%)]。对溃疡性结肠炎的灵敏度为7832%（2 671/3 410）,特异度为6706%（13 412/20 000）。单张图像的诊断时长为（05±003）s,此时长为实时应用的时间,包括系统识别、视频图像中文字提示、后台记录和存储三个部分。 结论 本团队研发的人工智能辅助诊断模型能够识别的病灶有结肠息肉、结直肠癌、结直肠隆起性病变、结肠憩室、溃疡性结肠炎等。结肠病辅助诊断模型一方面能够指导肠镜初学者进行肠镜检查,另一方面提高了病灶检出率、并降低漏诊率,而且内镜中心整体的运行效率得以提升,有利于结肠镜检查的质量控制。     

基于智能追溯信息系统的内镜集中管理效果评价

目的　以肠镜为例,研究消毒供应中心基于智能追溯信息系统对内镜集中管理的效果。方法　选取2021年1月至2022年6月内镜中心常规肠镜检查使用后肠镜252条次,观察组和对照组各126条次,均采用智能追溯信息系统进行消洗、回收、取用环节的信息录入、读取。对照组采用内镜中心负责的分散管理,观察组采用消毒供应中心负责的集中管理。采用三磷酸腺苷（ATP）生物荧光检测法比较两组内镜表面、阀门、腔道相对光单位值;比较两组内镜表面、内腔、活检口、注水注气口、负压吸引口采样物微生物培养阳性率;比较两组内镜清洗环境气溶胶颗粒物含量;比较两组工作人员回收满意度和使用满意度;比较集中管理与分散合理人力成本、运营成本及内镜维修率。结果　观察组内镜阀门及腔道清洗合格率［94.4%（119/126）、93.7%（118/126）］高于对照组［90.5%（114/126）、88.9%（112/126）,χ2=5.686、χ2=8.841,P均<0.05］;观察组内镜内腔、活检口、注水注气口、负压吸引口微生物菌落生长阳性率［19.0%（24/126）、17.5%（22/126）、1.6%（2/126）、12.7%（16/126）］均低于对照组［30.2%（38/126）、24.6%（31/126）、4.8%（6/126）、19.8%（25/126）,χ2=12.215、χ2=9.003、χ2=6.446、χ2=9.106,P均<0.05］。观察组洗消环境中空气产生的0.5 μm及2.5 μm气溶胶颗粒［（40 706 874±12 563 749）个/ｍ3、（226 530±87 632）个/ｍ3］均低于对照组［（46 892 654±13 209 872）个/ｍ3、（263 281±45 219）个/ｍ3,t=8.223、t=4.265,P均<0.05］。观察组人力成本63 128.45元、运营成本56 320.13元,少于对照组人力成本208 258.25元、运营成本208 415.22元。观察组回收、使用满意度［96.1%（98/102）、97.1%（100/103）］均高于对照组［78.4%（80/102）、82.5%（85/103）,χ2=13.211、χ2=15.223,P均<0.05］。观察组无内镜维修,对照组维修内镜2条。结论　基于智能追溯信息系统的内镜集中管理可提高内镜清洗消毒、存放保管水平,减少人力消耗及运营成本,提高消毒供应中心及内镜使用科室工作效率及使用满意度,降低内镜的医源性感染风险。     

人工智能技术在结肠镜退镜速度实时监控中的应用

目的构建一种基于计算机视觉的结肠镜退镜速度实时监控系统,并验证其可行性和性能。方法从武汉大学人民医院消化内镜中心数据库选取2018年5—10月期间的35938张肠镜图片和63个结肠镜检查视频。肠镜图片分成体外/体内/不合格和回盲部/非盲肠两个数据集,分别从第一个、第二个数据集中选取3594张和2000张图片用于深度学习模型的测试,其余图片用于训练模型;选取3个结肠镜检查视频资料评价实时监控系统自动监控退镜速度的可行性,剩余60个结肠镜检查视频资料用于评估实时监控系统的性能。结果深度学习模型对于结肠镜检查图片分类识别体外/体内/不合格图片的准确率分别为90.79%(897/988)、99.92%(1300/1301)、99.08%(1293/1305),总体准确率为97.11%(3490/3594);分类识别回盲部/非盲肠图片的准确率分别为96.70%(967/1000)、94.90%(949/1000),总体准确率为95.80%(1916/2000)。在其可行性评价方面,3个结肠镜视频资料显示退镜速度与图片处理间隔时间呈线性关系,提示该监控系统可在结肠镜退出过程中自动监控退镜速度。在其性能评价方面,结肠镜退镜速度实时监控系统正确预测了所有60个肠镜检查的开始时间和结束时间,分析显示结肠镜平均退镜速度和退镜时间呈明显负相关(R=-0.661,P<0.001),退镜时间不足5 min、5~6 min和超过6 min视频的平均退镜速度的95%置信区间分别为43.90~49.74、40.19~45.43和34.89~39.11,故将39.11设为安全退镜速度,将45.43设为预警退镜速度。结论构建的结肠镜退镜速度实时监控系统可用于实时监控结肠镜退镜速度,可在结肠镜检查中辅助内镜医师进行实时监测,以提高结肠镜检查质量。     

Colometer: A real-time quality feedback system for screening colonoscopy

AIM:To investigate the performance of a new software-based colonoscopy quality assessment system.METHODS:The software-based system employs a novel image processing algorithm which detects the levels of image clarity,withdrawal velocity,and level of the bowel preparation in a real-time fashion from live video signal.Threshold levels of image blurriness and the withdrawal velocity below which the visualization could be considered adequate have initially been determined arbitrarily by review of sample colonoscopy videos by two experienced endoscopists.Subsequently,an overall colonoscopy quality rating was computed based on the percentage of the withdrawal time with adequate visualization(scored 1-5;1,when the percentage was 1%-20%;2,when the percentage was 21%-40%,etc.).In order to test the proposed velocity and blurriness thresholds,screening colonoscopy withdrawal videos from a specialized ambulatory colon cancer screening center were collected,automatically processed and rated.Quality ratings on the withdrawal were compared to the insertion in the same patients.Then,3 experienced endoscopists reviewed the collected videos in a blinded fashion and rated the overall quality of each withdrawal(scored 1-5;1,poor;3,average;5,excellent) based on 3 major aspects:image quality,colon preparation,and withdrawal velocity.The automated quality ratings were compared to the averaged endoscopist quality ratings using Spearman correlation coefficient.RESULTS:Fourteen screening colonoscopies were assessed.Adenomatous polyps were detected in 4/14(29%) of the collected colonoscopy video samples.As a proof of concept,the Colometer software rated colonoscope withdrawal as having better visualization than the insertion in the 10 videos which did not have any polyps(average percent time with adequate visualization:79% ± 5% for withdrawal and 50% ± 14% for insertion,P 0.01).Withdrawal times during which no polyps were removed ranged from 4-12 min.The median quality rating from the automated system and the reviewers was 3.45 [interquartile range(IQR),3.1-3.68] and 3.00(IQR,2.33-3.67) respectively for all colonoscopy video samples.The automated rating revealed a strong correlation with the reviewer's rating(ρ coefficient= 0.65,P = 0.01).There was good correlation of the automated overall quality rating and the mean endoscopist withdrawal speed rating(Spearman r coefficient= 0.59,P = 0.03).There was no correlation of automated overall quality rating with mean endoscopists image quality rating(Spearman r coefficient= 0.41,P = 0.15).CONCLUSION:The results from a novel automated real-time colonoscopy quality feedback system strongly agreed with the endoscopists' quality assessments.Further study is required to validate this approach.     

A literature review of quality in lower gastrointestinal endoscopy from the patient perspective

BACKGROUND:

Given the limited state of health care resources, increased demand for colorectal cancer (CRC) screening raises concerns about the quality of endoscopy services. Little is known about quality in colonoscopy and endoscopy from the patient perspective.

OBJECTIVE:

To systematically review the literature on quality that is relevant to patients who require colonoscopy or endoscopy services.

METHODS:

A systematic PubMed search was performed on articles that were published between January 2000 and February 2011. Keywords included “colonoscopy” or “sigmoidoscopy” or “endoscopy” AND “quality”; “colonoscopy” or “sigmoidoscopy” or “endoscopy” AND “patient satisfaction” or “willingness to return”. The included articles were qualitative and quantitative English language studies regarding aspects of colonoscopy and/or endoscopy services that were evaluated by patients in which data were collected within one year of the colonoscopy/endoscopy procedure.

RESULTS:

In total, 28 quantitative studies were identified, of which eight (28.6%) met the inclusion criteria (four cross-sectional, three prospective cohort and one single-blinded controlled study). Aspects of quality included comfort, management of pain and anxiety, endoscopy unit staff manner, skills and specialty, procedure and results discussion with the doctor, physical environment, wait times for the appointment and procedure, and discharge. Qualitative studies eliciting the patient perspective on what constituted quality in colonoscopy/endoscopy were not found.

CONCLUSIONS:

Factors related to comfort, staff, communication and the service environment were evaluated from the patient perspective using closed-ended questions that were designed by clinicians and researchers. Future research using qualitative methodology to elicit the patient perspective on quality in colonoscopy and/or endoscopy services is needed.