ChiCTR2400089153 版本V1.0 版本创建时间2024/09/03 08:44:45 中国临床试验注册中心

审核状态:

Project audit state:

通过审核

Successful

注册号:

Registration number:

ChiCTR2400089153 

最近更新日期:

Date of Last Refreshed on:

2024-09-03 08:44:41 

注册时间:

Date of Registration:

2024-09-03 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

AI辅助上消化道病变内镜识别和分级诊断系统

Public title:

An artificial intelligence-assisted diagnostic system for endoscopic recognition and grading of gastroscopy

注册题目简写:

English Acronym:

研究课题的正式科学名称:

AI辅助上消化道病变内镜识别和分级诊断系统

Scientific title:

An artificial intelligence-assisted diagnostic system for endoscopic recognition and grading of gastroscopy

研究课题代号(代码):

Study subject ID:

在二级注册机构或其它机构的注册号:

The registration number of the Partner Registry or other register:

申请注册联系人:

廖婉滢 

研究负责人:

杨爱明;杨莹韵 

Applicant:

Wanying Liao 

Study leader:

Aiming Yang; Yingyun Yang 

申请注册联系人电话:

Applicant telephone:

+86 188 1005 2516

研究负责人电话:

Study leader's telephone:

+86 185 1003 1805

申请注册联系人传真 :

Applicant Fax:

研究负责人传真:

Study leader's fax:

申请注册联系人电子邮件:

Applicant E-mail:

liaowy17@mails.tsinghua.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

yangyingyun@pumch.cn

申请单位网址(自愿提供):

Applicant website(voluntary supply):

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

申请注册联系人通讯地址:

北京市东城区帅府园1号

研究负责人通讯地址:

北京市东城区帅府园1号

Applicant address:

No.1 Shuaifuyuan, Dongcheng District, Beijing

Study leader's address:

No.1 Shuaifuyuan, Dongcheng District, Beijing

申请注册联系人邮政编码:

Applicant postcode:

研究负责人邮政编码:

Study leader's postcode:

申请人所在单位:

中国医学科学院北京协和医学院,北京协和医院

Applicant's institution:

Peking Union Medical College Hospital (PUMCH), Chinese Academy of Medical Sciences & Peking Union Medical College (CAMS & PUMC)

研究负责人所在单位:

中国医学科学院北京协和医学院,北京协和医院

Affiliation of the Leader:

Peking Union Medical College Hospital (PUMCH), Chinese Academy of Medical Sciences & Peking Union Medical College (CAMS & PUMC)

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

I-24PJ0272

伦理委员会批件附件:

Approved file of Ethical Committee:

查看附件View

批准本研究的伦理委员会名称:

中国医学科学院北京协和医学院,北京协和医院

Name of the ethic committee:

Ethical Committee of Peking Union Medical College Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2024-02-02 00:00:00

伦理委员会联系人:

李佳月

Contact Name of the ethic committee:

Jiayue Li

伦理委员会联系地址:

北京市东城区帅府园1号

Contact Address of the ethic committee:

No.1 Shuaifuyuan, Dongcheng District, Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 6915 6874

伦理委员会联系人邮箱:

Contact email of the ethic committee:

研究实施负责(组长)单位:

中国医学科学院北京协和医院,北京协和医学院

Primary sponsor:

Peking Union Medical College Hospital (PUMCH), Chinese Academy of Medical Sciences & Peking Union Medical College (CAMS & PUMC)

研究实施负责(组长)单位地址:

北京市东城区帅府园1号

Primary sponsor's address:

No.1 Shuaifuyuan, Dongcheng District, Beijing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

北京

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

北京协和医院

具体地址:

北京市东城区帅府园1号

Institution
hospital:

Peking Union Medical College Hospital

Address:

No.1 Shuaifuyuan, Dongcheng District, Beijing

经费或物资来源:

中国医学科学院医学与健康科技创新工程项目 2022-I2M-CT-B-012及北京协和医院中央高水平医院临床科研专项2022-PUMCH-B-024

Source(s) of funding:

CAMS Innovation Fund for Medical Sciences (CIFMS 2022-I2M-C&T-B-012) and National High Level Hospital Clinical Research Funding (2022-PUMCH-B-024)

Target disease:

gastric mucosal lesion

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

(1)回顾性应用我科早期胃癌及癌前病变患者的白光和放大内镜图像、随访数据和临床病理数据库,结合强化学习并生成对抗网络训练,适应图像数据,建立医科院系统自主研发的早期胃癌及癌前病变的消化内镜人工智能辅助诊断系统; (2)在回顾性病例的测试集和前瞻性队列中应用该人工智能辅助诊断系统,对白光和放大胃镜检查中的慢性萎缩性胃炎、低级别上皮内瘤变、高级别上皮内瘤变和早期胃癌病灶进行识别、空间演变范围描记、辅助诊断建议,以病理和复盘病理范 围为金标准,评估诊断系统的诊断效能和便捷性并与内镜专科医师的相应表现对比; (3)初步应用该诊断系统进一步对白光胃镜和放大胃镜中的低级别上皮内瘤变的进展进行预判,并通过建立前瞻性队列并随访,以随访结局(是否进展为 HGIN 或肿瘤)为金标准验证其预判效果。  

Objectives of Study:

1) retrospective application I early gastric cancer and precancerous lesions in patients with white light and magnifying endoscope image, and follow-up data and clinical pathological database, combined with reinforcement learning and generate against network training, to adapt to image data, establishing Chinese acad med sci system independent research and development of early gastric cancer and precancerous lesions of digestive endoscopy assisted artificial intelligence diagnosis system; (2) In a test set of retrospective cases and a prospective cohort, the AI-assisted diagnosis system was applied to identify chronic atrophic gastritis, low-grade intraepithelial neoplasia, high-grade intraepithelial neoplasia, and early gastric cancer lesions in white light and magnification gastroscopy, tracing the spatial evolution scope, and suggesting auxiliary diagnosis, with pathological and review pathological range as the gold standard. The diagnostic efficiency and convenience of the diagnostic system were evaluated and compared with the corresponding performance of endoscopists. (3) The diagnostic system was preliminarily applied to further predict the progression of low-grade intraepithelial neoplasia under white light endoscopy and magnifying endoscopy, and the predictive effect was verified by establishing a prospective cohort and follow-up, with the follow-up outcome (whether it progressed to HGIN or neoplasia) as the gold standard.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

回顾性研究: 1. 2012年至今在北京协和医院消化内科进行上消化道内镜筛查的患者 2. 年龄:18到85岁 3. 有完整的临床、内镜和病理信息 前瞻性研究: 1.年龄:18到85岁,进行上消化道内镜筛查的患者 2.签署知情同意书

Inclusion criteria

Retrospective study: 1. Patients who have undergone upper gastrointestinal endoscopy screening at the Department of Gastroenterology, Peking Union Medical College Hospital from 2012 to present. 2. Age range: 18 to 85 years old. 3. Complete clinical, endoscopic, and pathological information available. Prospective study: 1. Age range: 18 to 85 years old who will undergo upper gastrointestinal endoscopy screening 2. Informed consent was obtained

排除标准:

回顾性研究: 1. 上消化道手术史 2. 内镜图像质量差 3. 患者拒绝参加本项目 前瞻性研究: 1.无法配合内镜检查 2.上消化道手术史 3. 患者拒绝参加本项目

Exclusion criteria:

Retrospective study: 1. History of upper gastrointestinal surgery 2. Poor quality of endoscopic images 3. Patient refusal to participate in this project Prospective study: 1.Unable to cooperate with endoscopy procedure 2. History of upper gastrointestinal surgery 3. Patient refusal to participate in this project

研究实施时间:

Study execute time:

From 2022-10-01 00:00:00 To 2026-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-09-10 00:00:00 To 2026-12-31 00:00:00  

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

胃黏膜活检病理结果

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

Pathological results of gastric mucosal biopsy.

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

早期胃癌和癌前病变的消化内镜人工智能诊断系统

Index test:

artificial intelligence-assisted diagnostic system for endoscopic recognition and grading of gastroscopy

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

胃黏膜病变为低级别上皮内瘤变、高级别上皮内瘤变、胃早癌或胃癌的患者(回顾性研究纳入1900人,回顾性研究按比例预计纳入100人)

例数:

Sample size:

2900

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Patients with gastric mucosal lesions of low grade intraepithelial neoplasia, high grade intraepithelial neoplasia, early gastric cancer or gastric cancer

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

胃黏膜病变为慢性萎缩性胃炎或肠化生的患者(回顾性研究纳入1100例,前瞻性研究预计按比例预计纳入500例)

例数:

Sample size:

1600

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Patients with gastric mucosal lesions of chronic atrophic gastritis or intestinal metaplasia

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京 

市(区县):

 

Country:

China 

Province:

Beijng 

City:

 

单位(医院):

北京协和医院 

单位级别:

三甲 

Institution
hospital:

Peking Union Medical College Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

诊断准确率

指标类型:

主要指标

Outcome:

Diagnostic accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

诊断精确率

指标类型:

次要指标

Outcome:

Precision

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

敏感性

指标类型:

次要指标

Outcome:

Sensitivity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异性

指标类型:

次要指标

Outcome:

Specificity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

Tissue:

人体标本去向

其它  

说明

Fate of sample:

0thers  

Note:

征募研究对象情况:

Recruiting status:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 85 years

性别:

男女均可

Gender:

Both

随机方法(请说明由何人用什么方法产生随机序列):

Randomization Procedure (please state who generates the random number sequence and by what method):

None

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

公开/Public

盲法:

Blinding:

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

是否共享原始数据:

IPD sharing

No

共享原始数据的方式(说明:请填入公开原始数据日期和方式,如采用网络平台,需填该网络平台名称和网址):

不共享

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

NA

数据采集和管理(说明:数据采集和管理由两部分组成,一为病例记录表(Case Record Form, CRF),二为电子采集和管理系统(Electronic Data Capture, EDC),如ResMan即为一种基于互联网的EDC:

内镜检查由至少有5年内镜操作经验的医师进行,严格遵照规范操作,完整留取操作过程中消化道部各区域的图片。患者检测的各组学原始数据将保存为电子化数据,文件将以患者病案号为标题保存在同一台计算机中。课题将设置数据管理小组,仅有小组成员可以接触全部数据。研究人员进行数据提取和分析时,需经过数据管理小组成员的批准,且对数据进行匿名化处理。资料严格保密,以受试者的编号作为记录,受试者信息将严格保密,数据仅供本研究使用。 建立试验指导委员会(Steering Committee)和数据和安全监控委员会(Data and Safety Monitoring Committee, DSMC)。指导委员会由本领域资深专家、医生和工程师共同组成,定期举行会议对研究进行评估和监查。与本研究无关的临床研究方法学专家和伦理学专家组成DSMC,定期审核数据并保证受试者安全。 电子采集和管理系统:ResMan(http://www.medresman.org.cn/)

Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture:

Endoscopy is performed by a physician with at least 5 years of experience in endoscopy, in strict accordance with the standard operation, and the complete picture of each area of the digestive tract during the operation is obtained. The original data of each group of patient tests will be stored as electronic data, and the file will be stored in the same computer with the title of patient medical record number. The project will set up a data management team, and only the team members will have access to all the data. Data extraction and analysis by researchers are subject to approval by members of the data management team, and the data is anonymized. The data shall be kept strictly confidential. The number of the subject shall be used as the record. The information of the subject shall be kept strictly confidential and the data shall be used only for this study. Establish a Steering Committee and a Data and Safety Monitoring Committee (DSMC). The Steering Committee, made up of senior experts in the field, doctors and engineers, meets regularly to evaluate and monitor research. The DSMC consists of clinical research methodologists and ethics experts not associated with the study who regularly review the data and ensure subject safety.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2024-09-03 08:44:41