ChiCTR2300078811 版本V1.0 版本创建时间2023/12/19 12:04:39 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:

ChiCTR2300078811 

最近更新日期:

Date of Last Refreshed on:

2023-12-19 12:04:35 

注册时间:

Date of Registration:

2023-12-19 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

自身免疫性胃炎内镜图像人工智能辅助诊断系统的研发

Public title:

Development of artificial intelligence aided diagnosis system for autoimmune gastritis with endoscopic images

注册题目简写:

English Acronym:

研究课题的正式科学名称:

自身免疫性胃炎内镜图像人工智能辅助诊断系统的研发

Scientific title:

Development of artificial intelligence aided diagnosis system for autoimmune gastritis with endoscopic images

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:

罗皓 

研究负责人:

史济华 

Applicant:

Luo Hao 

Study leader:

Shi Jihua 

申请注册联系人电话:

Applicant telephone:

+86 159 0157 5870

研究负责人电话:

Study leader's telephone:

+86 159 0157 5870

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:

luohao4993@bjhmoh.cn

研究负责人电子邮件:

Study leader's E-mail:

shijihua1981@sina.com

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:

北京市东城区大华路1号

研究负责人通讯地址:

北京市东城区大华路1号

Applicant address:

No.1 Dahua Road, Dongcheng District, Beijing

Study leader's address:

No.1 Dahua Road, 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:

北京医院

Applicant's institution:

Beijing hospital

研究负责人所在单位:

北京医院

Affiliation of the Leader:

Beijing hospital

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:

2023BJYYEC-214-02

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:

北京医院伦理委员会

Name of the ethic committee:

Beijing Hospital Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2023-08-14 00:00:00

伦理委员会联系人:

徐苗

Contact Name of the ethic committee:

Xu Miao

伦理委员会联系地址:

北京市东城区大华路1号

Contact Address of the ethic committee:

No.1 Dahua Road, Dongcheng District, Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8513 8105

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:

北京医院

Primary sponsor:

Beijing hospital

研究实施负责(组长)单位地址:

北京市东城区大华路1号

Primary sponsor's address:

No.1 Dahua Road, 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):

东城区

Country:

China

Province:

Beijing

City:

Dongcheng District

单位(医院):

北京医院

具体地址:

北京市东城区大华路1号

Institution
hospital:

Beijing hospital

Address:

No.1 Dahua Road, Dongcheng District, Beijing

经费或物资来源:

2023年北京医院医工专项

Source(s) of funding:

Beijing Hospital Medical Project in 2023

Target disease:

Autoimmune gastritis

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

诊断试验新技术临床试验 

Study phase:

Diagnostic New Technique Clincal Study

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

目前国际上尚无统一的AIG诊断标准,由于患者的症状不特异和医生对疾病认识不足,临床确诊率很低,而内镜检查是发现和诊断AIG的重要契机。本研究对拟行内镜检查的慢性胃炎患者进行胃黏膜组织活检病理和血清学检查,确诊患者的胃炎类型后将内镜图片进行分类,通过人工智能深度学习内镜图片不断训练模型,建立AIG的AI辅助内镜识别系统并进行验证,达到接近高年资内镜医师的识别水平。通过本研究初步建立AI辅助下的慢性胃炎分类识别模型,以提高自身免疫性胃炎的诊断率。  

Objectives of Study:

At present, there is no unified diagnosis standard of AIG in the world. Because of the nonspecific symptoms of patients and the doctors' lack of understanding of the disease, the clinical diagnosis rate is very low, and endoscopy is an important opportunity to find and diagnose AIG. In this study, gastric mucosa biopsy and serological examination were carried out in patients with chronic gastritis who were going to undergo endoscopic examination. After the type of gastritis was diagnosed, the endoscopic pictures were classified. The model was continuously trained through deep learning of endoscopic pictures by artificial intelligence, and AIG's AI-assisted endoscopic identification system was established and verified, reaching the recognition level close to that of senior endoscopists. In order to improve the diagnostic rate of autoimmune gastritis, the classification and recognition model of chronic gastritis assisted by AI was initially established through this study.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

采用连续入组方式按照如下标准纳入研究对象。(1)临床疑诊AIG:①合并以下疾病之一:贫血、VitB12缺乏症、亚急性联合变性、胃神经内分泌瘤、自身免疫性甲状腺疾病、1型糖尿病、白癜风、自身免疫性肝病、Addison病;②AIG一级家族史。满足①中任意一条或②。(2)内镜疑诊AIG:①慢性萎缩性胃炎木村竹本分型为O1-O3或Op(胃体为主的萎缩)②胃底体粘稠粘液③胃息肉样病变④胃体黏膜水肿弥漫发红⑤残余胃底腺黏膜,满足①至⑤中任意一条。

Inclusion criteria

The subjects were included in the study by continuous grouping according to the following criteria. (1) clinically suspected AIG: ① complicated with one of the following diseases: anemia, VitB12 deficiency, subacute combined degeneration, gastric neuroendocrine tumor, autoimmune thyroid disease, type 1 diabetes, vitiligo, autoimmune liver disease and Addison disease; ②AIG's first-class family history. Satisfy any one of ① or ②. (2) Endoscopic suspected diagnosis of AIG: ① The subtype of chronic atrophic gastritis Kimura Bamboo is O1-O3 or Op (atrophy of stomach body mainly); ② Mucus of gastric fundus; ③ Polypoid lesion of stomach; ④ Edema of gastric mucosa is diffuse and red; ⑤ Residual glandular mucosa of gastric fundus, satisfies any one of ① to ⑤.

排除标准:

(1)依从性较差、不能规律就诊;(2)胃部分切除术后;(3)伴随严重的基础疾病;(4)处于妊娠或哺乳期;(5)研究者认为不能入组的其它情况。

Exclusion criteria:

(1) Poor compliance and irregular medical treatment; (2) After partial gastrectomy; (3) accompanied by serious underlying diseases; (4) Being pregnant or nursing; (5) Other circumstances that the researcher thinks can't be included in the group.

研究实施时间:

Study execute time:

From 2023-10-01 00:00:00 To 2024-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2023-10-01 00:00:00 To 2024-12-01 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):

以内镜+病理+血清学检查结果诊断为金标准

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):

Diagnosis based on endoscopic, pathological, and serological examination results as the gold standard

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):

人工智能对其内镜图像的特征进行识别

Index test:

Artificial intelligence identifies the features of its endoscopic image

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)

临床或者内镜疑诊AIG的慢性胃炎患者

例数:

Sample size:

630

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):

Chronic gastritis patients who are clinically or endoscopically suspected of AIG

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):

例数:

Sample size:

0

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

None

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:

Beijing 

City:

 

单位(医院):

北京医院 

单位级别:

三甲 

Institution
hospital:

Beijing hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

人工智能提取特征的准确度

指标类型:

主要指标

Outcome:

Accuracy of artificial intelligence to extract features

Type:

Primary 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、特异性

指标类型:

次要指标

Outcome:

Sensitivity, 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:

None

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:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 60 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):

N/A

是否公开试验完成后的统计结果:

Calculated Results after the Study Completed public access:

不公开/Private

盲法:

Blinding:

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):

Resman

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

Resman

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:

CRF

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

CRF

数据与安全监察委员会:

Data and Safety Monitoring Committee:

暂未确定/Not yet

注册人:

Name of Registration:

 2023-12-19 12:04:35