基于多模态数据与人工智能的眼病数字智能体开发与验证

注册号:

Registration number:

ChiCTR2600122801 

最近更新日期:

Date of Last Refreshed on:

2026-04-19 23:52:48 

注册时间:

Date of Registration:

2026-04-17 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于多模态数据与人工智能的眼病数字智能体开发与验证

Public title:

Development and Validation of an AI-Based Multimodal Digital Agent for Eye Diseases

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态数据与人工智能的眼病数字智能体开发与验证

Scientific title:

Development and Validation of an AI-Based Multimodal Digital Agent for Eye Diseases

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:

李笠 

研究负责人:

李笠 

Applicant:

Li Li 

Study leader:

Li Li 

申请注册联系人电话:

Applicant telephone:

+86 591 88618523

研究负责人电话:

Study leader's
telephone:

+86 591 88618523

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:

lili_js@fjsl.com.cn

研究负责人电子邮件:

Study leader's E-mail:

lili_js@fjsl.com.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:

中国福建省福州市鼓楼区东街134号

研究负责人通讯地址:

中国福建省福州市鼓楼区东街134号

Applicant address:

134 East Street, Gulou District, Fuzhou, Fujian, China

Study leader's address:

134 East Street, Gulou District, Fuzhou, Fujian, 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:

福州大学附属省立医院

Applicant's institution:

Fuzhou University Affiliated Provincial Hospital

研究负责人所在单位:

福州大学附属省立医院

Affiliation of the Leader:

Fuzhou University Affiliated Provincial 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:

K2025-12-007

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:

福州大学附属省立医院伦理委员会

Name of the ethic committee:

Ethics Committee of Fuzhou University Affiliated Provincial Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-12-05 00:00:00

伦理委员会联系人:

练发杨

Contact Name of the ethic committee:

Lian Fayang

伦理委员会联系地址:

中国福建省福州市鼓楼区东街134号

Contact Address of the ethic committee:

134 East Street, Gulou District, Fuzhou, Fujian, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 591 88216023

伦理委员会联系人邮箱:

Contact email of the ethic committee:

fjslec@163.com

研究实施负责(组长)单位:

福州大学附属省立医院

Primary sponsor:

Fuzhou University Affiliated Provincial Hospital

研究实施负责(组长)单位地址:

中国福建省福州市鼓楼区东街134号

Primary sponsor's address:

134 East Street, Gulou District, Fuzhou, Fujian, 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):

福建

市(区县):

Country:

China

Province:

Fujian

City:

单位(医院):

福州大学附属省立医院

具体地址:

中国福建省福州市鼓楼区东街134号

Institution
hospital:

Fuzhou University Affiliated Provincial Hospital

Address:

134 East Street, Gulou District, Fuzhou, Fujian, China

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

眼表疾病,屈光不正,视功能障碍,眼底病,眼眶病。  

Target disease:

Ocular surface diseases, refractive errors, visual dysfunction, fundus diseases, orbital diseases.

研究疾病代码:

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

横断面 

Study design:

Cross-sectional 

研究目的:

诊断与治疗决策辅助  

Objectives of Study:

Diagnostic and therapeutic decision support

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. 诊断不明。 2. 存在数据缺失、标注错误或无法溯源的记录; 3. 缺少影像学资料或影像资料质量不合格,无法用于模型训练或验证。

Exclusion criteria:

1. Unclear diagnosis. 2. Presence of missing data, labeling errors, or records that cannot be traced. 3. Absence of imaging data, or poor-quality imaging data that is unsuitable for model training or validation.

研究实施时间:

Study execute time:

From 2026-05-01 00:00:00 To 2029-05-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-05-01 00:00:00 To 2026-11-01 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

6000

Group:

Observational group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

福建 

市(区县):

 

Country:

China

Province:

Fujian

City:

单位(医院):

福州大学附属省立医院 

单位级别:

三级甲等 

Institution
hospital:

Fujian Provincial Hospital Affiliated to Fuzhou University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

福建 

市(区县):

 

Country:

China

Province:

Fujian

City:

单位(医院):

福州锐明爱尔眼科医院 

单位级别:

三级医院 

Institution
hospital:

Fuzhou Ruiming Aier Eye Hospital

Level of the institution:

Tertiary

国家:

中国

省(直辖市):

浙江 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

温州医科大学附属眼视光医院 

单位级别:

三级甲等 

Institution
hospital:

The Eye Hospital of Wenzhou Medical University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

福建 

市(区县):

 

Country:

China

Province:

Fujian

City:

单位(医院):

莆田眼科医院 

单位级别:

三级医院 

Institution
hospital:

Putian Eye Hospital

Level of the institution:

Tertiary

测量指标:

Outcomes:

指标中文名:

准确率

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

在诊断决策完成后进行评分

测量方法:

根据专家组的评估计算准确率

Measure time point of outcome:

Scored after the diagnostic decision is completed.

Measure method:

Calculated based on the evaluation of the expert panel.

指标中文名:

一致性

指标类型:

主要指标

Outcome:

Consistency (e.g., Kappa)

Type:

Primary indicator

测量时间点:

在诊断决策完成后进行评分

测量方法:

分析智能体在诊疗决策方面与专家组的一致性

Measure time point of outcome:

Scored after the diagnostic decision is completed.

Measure method:

Analyze the consistency of the agent's diagnosis and treatment decisions compared to the expert panel.

指标中文名:

ROC 曲线下面积(AUC)

指标类型:

主要指标

Outcome:

Area Under the ROC Curve (AUC)

Type:

Primary indicator

测量时间点:

智能体完成测试集测试后

测量方法:

由智能体在测试集上的表现分析出

Measure time point of outcome:

After the agent has completed testing on the test set.

Measure method:

Determined by analyzing the agent's performance on the test set.

指标中文名:

特异度

指标类型:

次要指标

Outcome:

Specificity

Type:

Secondary indicator

测量时间点:

智能体完成测试集测试后

测量方法:

由智能体在测试集上的表现分析出

Measure time point of outcome:

After the agent has completed testing on the test set

Measure method:

Determined by analyzing the agent's performance on the test set.

指标中文名:

灵敏度

指标类型:

次要指标

Outcome:

Sensitivity

Type:

Secondary indicator

测量时间点:

智能体完成测试集测试后

测量方法:

智能体完成测试集测试后

Measure time point of outcome:

After the agent has completed testing on the test set

Measure method:

Determined by analyzing the agent's performance on the test set.

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 NA years
最大 Max age NA 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:

不公开/Private

盲法:

Blinding:

None

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):

研究结束后半年;国家生物信息中心(https://www.cncb.ac.cn/)

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

Six months after the completion of the research; China National Center for Bioinformation (https://www.cncb.ac.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:

本研究为回顾性研究,不设专门的纸质病例记录表(CRF)。所有数据均来源于本院临床诊疗过程中常规收集和存储的标准化电子数据,包括:影像学数据(如OCT、角膜地形图等);电子病历文本数据(如诊断记录、病史、检查报告等)这些数据将被提取、脱敏并整合到一个统一的中央数据库中进行管理。数据的提取、存储和管理过程将在严格的信息安全与隐私保护协议下进行,确保数据的完整性与保密性。

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

This study employs a retrospective design and does not utilize a dedicated paper Case Report Form (CRF). All data are sourced from routinely collected and standardized electronic records generated during clinical care at our hospital, including imaging data (e.g., OCT and corneal topography) and electronic medical record text data (e.g., diagnosis records, medical history, and examination reports). The data will be extracted, de-identified, and integrated into a centralized database for management. The entire process will adhere to strict information security and privacy protection protocols to ensure data integrity and confidentiality.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-04-17 17:06:31