糖尿病视网膜病变筛查中人工智能模型的真实临床诊断水平研究

注册号:

Registration number:

ChiCTR1800019875 

最近更新日期:

Date of Last Refreshed on:

2018-12-05 09:32:04 

注册时间:

Date of Registration:

2018-12-05 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

糖尿病视网膜病变筛查中人工智能模型的真实临床诊断水平研究

Public title:

A study for real-world efficiency of artificial intelligence technology in diabetic retinopathy screening

注册题目简写:

English Acronym:

研究课题的正式科学名称:

糖尿病视网膜病变筛查中人工智能模型的真实临床诊断水平研究

Scientific title:

A study for real-world efficiency of artificial intelligence technology in diabetic retinopathy screening

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:

胡吉英 

研究负责人:

牟丽莎 

Applicant:

Jiying Hu 

Study leader:

Lisha Mou 

申请注册联系人电话:

Applicant telephone:

+86 18086481821

研究负责人电话:

Study leader's
telephone:

+86 15899876015

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:

18086481821@163.com

研究负责人电子邮件:

Study leader's E-mail:

lishamou@gmail.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:

广东省深圳市福田区笋岗西路3002号

研究负责人通讯地址:

广东省深圳市福田区笋岗西路3002号

Applicant address:

3002 Sungang Road West, Futian District, Shenzhen, Guangdong, China

Study leader's address:

3002 Sungang Road West, Futian District, Shenzhen, Guangdong, 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:

深圳市第二人民医院

Applicant's institution:

Shenzhen Second People's Hospital

研究负责人所在单位:

深圳市第二人民医院

Affiliation of the Leader:

Shenzhen Second People's Hospital

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:

20180926005

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:

深圳市第二人民医院医学伦理委员会

Name of the ethic committee:

Medical ethics committee of Shenzhen Second People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2018-09-26 00:00:00

伦理委员会联系人:

蔡学泳

Contact Name of the ethic committee:

Xueyong Cai

伦理委员会联系地址:

广东省深圳市福田区笋岗西路3002号

Contact Address of the ethic committee:

3002 Sungang Road West, Futian District, Shenzhen, Guangdong, 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:

深圳市第二人民医院

Primary sponsor:

Shenzhen Second People's Hospital

研究实施负责(组长)单位地址:

广东省深圳市福田区笋岗西路3002号

Primary sponsor's address:

3002 Sungang Road West, Futian District, Shenzhen, Guangdong, 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):

广东省

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

深圳市第二人民医院

具体地址:

广东省深圳市福田区笋岗西路3002号

Institution
hospital:

Shenzhen Second People's Hospital

Address:

3002 Sungang Road West, Futian District, Shenzhen, Guangdong, China

经费或物资来源:

自筹

Source(s) of funding:

self-financing

研究疾病:

糖尿病视网膜病变  

Target disease:

Diabetic Retinopathy

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:

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:

1.系统评价眼底照相诊断效率,确定适合大规模DR筛查的拍照方法 2.建立基于人工智能技术的自动DR筛查平台,评估人工智能技术与临床金标准相比时在DR筛查中的真实临床诊断水平 3.提高糖尿病患者眼健康意识以及眼部检查的依从性,实现对该病的早发现、早治疗,降低致盲率和致残率  

Objectives of Study:

1. To evaluate the efficiency of fundus photography diagnosis systematically, and determine the specific suitable for large-scale DR screening 2. To establish an automatic DR screening platform based on artificial intelligence technology, and evaluate the actual clinical diagnosis level of artificial intelligence technology in DR screening 3. To improve the eye health awareness and the compliance of eye examination of patients with diabetes, improve the early detection and treatment of the disease, and reduce the rate of blindness and disability

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:

1.确诊为糖网病以外的眼底疾病患者。
2.确诊为黄斑水肿、严重的非增殖性视网膜病变、增生性视网膜病变、放射性视网膜病变或视网膜静脉阻塞。
3.孕妇、散瞳剂过敏、屈光介质不清、有青光眼家族史、诊断为房角窄。
4.有激光治疗,视网膜手术或抗血管内皮生长因子注射治疗历史。
5.光过敏或正在服用导致光敏感性的药物。

Exclusion criteria:

1. Diagnosed as fundus disease patients other than DR;
2. Diagnosed as macular edema, severe non-proliferative retinopathy, proliferative retinopathy, radioactive retinopathy or retinal vein obstruction;
3. Pregnant women, hypersensitivity to dilating agents, unclear refractive media, family history of glaucoma, and narrow atrial Angle;
4. History of laser therapy, retinal surgery or injection of anti-vascular endothelial growth factor;
5. Photosensitivity or taking medication that causes photosensitivity.

研究实施时间:

Study execute time:

From 2019-03-01 00:00:00 To 2021-03-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2019-03-01 00:00:00 To 2020-06-01 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):

3位具有15-20年诊断经验的眼底病医师根据标准7视野眼底照相结果得出的一致性诊断结论,一致性≧2.

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):

The diagnostic result of three ophthalmologists with 15-20 years of experience based on 7SF photography, and the diagnostic results confirmed by at least 2 ophthalmologists.

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):

人工智能技术基于双视野眼底照相的诊断结果

Index test:

Diagnostic result of artificial intelligence technology based on two-field fundus photography

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)

确诊为糖尿病的眼科门诊就诊人群

例数:

Sample size:

1000

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):

The ophthalmic outpatient patients diagnosed 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:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东省 

市(区县):

 

Country:

China

Province:

Guangdong Province

City:

单位(医院):

深圳市第二人民医院 

单位级别:

三甲 

Institution
hospital:

Shenzhen Second People's Hospital

Level of the institution:

Tertiary A Hospital

测量指标:

Outcomes:

指标中文名:

敏感度,特异度,ROC曲线下的面积

指标类型:

主要指标

Outcome:

Sensitivity, Specificity, AUC

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

糖尿病视网膜病分期

指标类型:

主要指标

Outcome:

Diabetic retinopathy staging

Type:

Primary 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:

眼底图片

组织:

Sample Name:

Fundus image

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:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 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):

N/A

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:

先后采集糖尿病患者双视野免散瞳以及标准七视野照相眼底图像,由3名有15-20年诊断经验的眼科医师采用盲法进行阅片并得出结论,来自同一眼底的双视野免散瞳眼底图片同时进行人工智能评估。

Blinding:

Two-field nonmydriatic fundus photography and standard seven-field photography fundus images are successively collected. Three ophthalmologists with 15-20 years of experience were blind to read the film and drew a conclusion. Meanwhile, artificial intelligence assessment was conducted on the two-field images.

是否共享原始数据:

IPD sharing

是Yes

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):

学术期刊

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

Academic journal

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:

临床试验机构应当保存临床试验资料至临床试验结束后 10 年;申办者应当保存临床试验资料至无该医疗器械使用时。这些数据交由有资质的数据管理方按照与申办方协商制定的《数据管理计划》进行数据管理和清理。

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

All raw data should be preserved at their respective clinical trial sites for up to 10 years and by the study sponsor until such medical device is no longer in use. Data will be processed and managed by a qualified third-party data management provider in accordance with Data Management Plan agreed upon by both parties.

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:

 2018-12-05 09:32:04