基于人工智能的多模态数据对代谢性疾病的诊断及风险预测研究

注册号:

Registration number:

ChiCTR2300069400 

最近更新日期:

Date of Last Refreshed on:

2025-10-05 16:36:04 

注册时间:

Date of Registration:

2023-03-15 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于人工智能的多模态数据对代谢性疾病的诊断及风险预测研究

Public title:

The artificial intelligence supported system in the diagnosis and risk prediction of metabolic disorders based on multimodal data

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于人工智能的多模态数据对代谢性疾病的诊断及风险预测研究

Scientific title:

The artificial intelligence supported system in the diagnosis and risk prediction of metabolic disorders based on multimodal data

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:

李华婷 

研究负责人:

贾伟平 

Applicant:

Huating Li 

Study leader:

Weiping Jia 

申请注册联系人电话:

Applicant telephone:

+86 13916502465

研究负责人电话:

Study leader's
telephone:

+86 13916502465

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:

huarting99@sjtu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

wpjia@sjtu.edu.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:

上海徐汇区宜山路600号

研究负责人通讯地址:

上海徐汇区宜山路600号

Applicant address:

600 Yishan Road, Xuhui District, Shanghai, China

Study leader's address:

600 Yishan Road, Xuhui District, Shanghai, China

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:

上海交通大学医学院附属第六人民医院

Applicant's institution:

Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine

研究负责人所在单位:

上海交通大学医学院附属第六人民医院

Affiliation of the Leader:

Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine

是否获伦理委员会批准:

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

2022-KY-023(K)

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:

上海市第六人民医院伦理委员会

Name of the ethic committee:

Ethics Committee of Shanghai Sixth People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2022-03-07 00:00:00

伦理委员会联系人:

孙秀秀

Contact Name of the ethic committee:

Xiuxiu Sun

伦理委员会联系地址:

上海徐汇区宜山路600号

Contact Address of the ethic committee:

600 Yishan Road, Xuhui District, Shanghai, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

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:

上海交通大学医学院附属第六人民医院

Primary sponsor:

Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine

研究实施负责(组长)单位地址:

上海徐汇区宜山路600号

Primary sponsor's address:

600 Yishan Road, Xuhui District, Shanghai, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

上海

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

上海交通大学医学院附属第六人民医院

具体地址:

上海徐汇区宜山路600号

Institution
hospital:

Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine

Address:

600 Yishan Road, Xuhui District, Shanghai, China

经费或物资来源:

上海市政府糖尿病专项 (GWIV-3)

Source(s) of funding:

Shanghai Municipal Grants Award (GWIV-3)

研究疾病:

糖尿病及其微血管并发症、高血压及其靶器官损害、代谢相关脂肪性肝病、冠心病、脑血管病、慢性肾脏病  

Target disease:

Diabetes and microvascular complications, hypertension and target organ damage, metabolic associated fatty liver disease, coronary artery disease, cerebrovascular disease, chronic kidney disease

研究疾病代码:

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.在上海糖尿病预防项目(SDPP)队列、上海市代谢性疾病(糖尿病)预防和诊治服务体系建设(SIM)等项目中训练深度学习系统,在横断面数据中实现通过眼底图像+临床数据对糖尿病前期、糖尿病、糖尿病肾病、高血压及其靶器官损害、血脂异常、代谢相关脂肪性肝病、心脑血管病(冠心病、颈动脉粥样硬化、脑卒中等)、慢性肾脏病等代谢性疾病的识别。 2.在上海糖尿病预防项目(SDPP)等队列中训练深度学习系统,在前瞻数据中实现通过眼底图像+临床数据预测血糖、血脂、血压恶化风险,糖尿病及其微血管并发症(糖尿病视网膜病变、糖尿病肾病等)、高血压及其靶器官损害(高血压视网膜病变、大动脉硬化、高血压肾病等)、血脂异常及代谢相关脂肪性肝病、心脑血管疾病(冠心病、颈动脉粥样硬化、脑卒中等)、慢性肾脏病等的风险和进展速度预测。 3.在多个独立外部数据集中对深度学习系统进行外部验证,包括华东健康管理(ECHM)队列、上海市代谢性疾病(糖尿病)预防和诊治服务体系建设项目(SIM)、泥城研究(NDSP)、北京协和糖尿病管理(PUDM)队列、香港中文大学Sight-Threatening Diabetic Retinopathy (CUHK-STDR) 队列、同济健康管理 (THM) 队列、新加坡眼病流行病学 (SEED) 项目、新加坡综合糖尿病视网膜病变计划 (SiDRP) 等。 4.探索去中心化机器学习等隐私计算技术对多中心医疗数据联合训练的应用。  

Objectives of Study:

1. To train the deep learning system (DLS) in the Shanghai Diabetes Prevention Program (SDPP) cohort, Shanghai Integrated Diabetes Prevention and Care System (SIM), etc. to achieve the identification of metabolic disorders such as prediabetes, diabetes, diabetic kidney disease, hypertension and hypertension-mediated organ damage, dyslipidemia metabolic associated fatty liver disease and cardiovascular disease (coronary artery disease, carotid artery atherosclerosis, stroke, etc.) and chronic kidney disease, ect. through fundus images combined with clinical parameters in cross-sectional data. 2. To train the DLS to predict the risk of deterioration in blood glucose, blood pressure, and lipid profiles, and the onset and progression of diabetes and its microvascular complications (diabetic retinopathy, diabetic kidney disease, etc.), hypertension and hypertension-mediated organ damage (hypertensive retinopathy, large artery stiffening, hypertensive nephropathy, etc.), dyslipidemia and metabolic associated fatty liver disease, cardiovascular disease (coronary artery disease, carotid atherosclerosis and stroke, etc.) and chronic kidney disease, etc. through fundus images combined with clinical parameters. 3. To validate the DLS in multiple independent external datasets, including the Eastern China Health Management (ECHM) cohort, the Shanghai Integrated Diabetes Prevention and Care System (Shanghai Integration Model, SIM), Nicheng Diabetes Screening Project (NDSP), Peking Union Diabetes Management (PUDM) cohort, The Chinese University of Hong Kong-Sight-Threatening Diabetic Retinopathy (CUHK-STDR) cohort, Tongji Health Management (THM) cohort, Singapore Epidemiology of Eye Diseases (SEED) and Singapore Integrated Diabetic Retinopathy Programme (SiDRP), etc. 4. To explore the application of privacy-preserving computation techniques (such as decentralized machine learning) to joint training of multi-center medical data.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

Inclusion criteria

排除标准:

眼底摄片图像质量差。

Exclusion criteria:

Poor image quality of fundus photography.

研究实施时间:

Study execute time:

From 2022-01-20 00:00:00 To 2023-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2022-03-20 00:00:00 To 2023-12-31 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):

依据相关的权威国际指南或标准,结合病史、相关检查结果等资料,做出糖尿病、高血压、血脂异常等代谢性疾病的诊断。

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):

Metabolic disorders, including diabetes, hypertension and dyslipidemia, etc. are diagnosed base on medical history and relevant examinations, according to relevant recognized international guidelines or standards.

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):

深度学习系统对疾病的识别和预测结果。

Index test:

Disease identification and prediction results from deep learning systems.

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)

社区一般人群及糖尿病人群

例数:

Sample size:

370000

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):

Community-based general population and patients with diabetes

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):

上海 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

上海交通大学医学院附属第六人民医院 

单位级别:

三甲医院 

Institution
hospital:

Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of Medicine

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

糖尿病

指标类型:

主要指标

Outcome:

Diabetes

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

糖尿病前期

指标类型:

次要指标

Outcome:

Prediabetes

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

糖尿病视网膜病变

指标类型:

次要指标

Outcome:

Diabetic retinopathy

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

糖尿病肾病

指标类型:

次要指标

Outcome:

Diabetic kidney disease

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

高血压

指标类型:

次要指标

Outcome:

Hypertension

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

高血压靶器官损害

指标类型:

次要指标

Outcome:

Hypertension-mediated organ damage

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血脂异常

指标类型:

次要指标

Outcome:

Dyslipidemia

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

代谢相关脂肪性肝病

指标类型:

次要指标

Outcome:

Metabolic associated fatty liver disease

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

冠心病

指标类型:

次要指标

Outcome:

Coronary artery disease

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

脑血管病

指标类型:

次要指标

Outcome:

Cerebrovascular disease

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

慢性肾脏病

指标类型:

次要指标

Outcome:

Chronic kidney disease

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

心血管疾病

指标类型:

次要指标

Outcome:

Cardiovascular disease

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:

血清

组织:

Sample Name:

Serum

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

Note:

标本中文名:

血浆

组织:

Sample Name:

Plasma

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

Note:

标本中文名:

全血

组织:

Sample Name:

Whole blood

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

Note:

标本中文名:

尿液

组织:

Sample Name:

Urine

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation after use  

Note:

征募研究对象情况:

Recruiting status:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 11 years
最大 Max age 94 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):

不适用

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:

未说明

Blinding:

Not stated

是否共享原始数据:

IPD sharing

否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):

临床试验公共管理平台: http://www.medresman.org.cn

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

Clinical Trial Management Public Platform: http://www.medresman.org.cn

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:

数据表由研究负责单位保管

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

Research data should be saved by the responsible units

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2023-03-15 15:16:19