ChiCTR2600116106 版本V1.0 版本创建时间2026/01/05 17:56:53 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:

ChiCTR2600116106 

最近更新日期:

Date of Last Refreshed on:

2026-01-05 17:56:41 

注册时间:

Date of Registration:

2026-01-05 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

基于面部视频的非接触式心血管疾病诊断方法

Public title:

Facial Video-based Remote cardiovascular Disease Measurement via Self-supervised Learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于面部视频的非接触式心血管疾病诊断方法

Scientific title:

Facial Video-based Remote Cardiovascular Disease Measurement via Self-supervised Learning

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:

高艳华 

研究负责人:

刘学波 

Applicant:

Yanhua Gao 

Study leader:

Xuebo Liu 

申请注册联系人电话:

Applicant telephone:

+86 188 1821 1510

研究负责人电话:

Study leader's
telephone:

+86 138 0192 6702

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:

gaoyanhua123@163.com

研究负责人电子邮件:

Study leader's E-mail:

Lxb70@hotmail.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:

上海市新村路389号同济医院

研究负责人通讯地址:

上海市新村路389号同济医院

Applicant address:

Tongji hospital, No. 389 Xincun road,Shanghai,China

Study leader's address:

Tongji hospital, No. 389 Xincun road,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:

同济大学附属同济医院

Applicant's institution:

Tongji hospital, Tongji University

研究负责人所在单位:

同济大学附属同济医院

Affiliation of the Leader:

Tongji hospital, Tongji University

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:

(同)伦审第(K-2023-030)号

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:

同济大学附属同济医院伦理委员会

Name of the ethic committee:

Ethics Committee of Tongji Hospital, Tongji University

伦理委员会批准日期:

Date of approved by ethic committee:

2023-11-15 00:00:00

伦理委员会联系人:

李紫薇

Contact Name of the ethic committee:

Miao Xuan

伦理委员会联系地址:

同济大学附属同济医院伦理办公室

Contact Address of the ethic committee:

Ethics Office of Tongji Hospital, Tongji University

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 21 6611 1243

伦理委员会联系人邮箱:

Contact email of the ethic committee:

tongjilunli2020@163.com

研究实施负责(组长)单位:

同济大学附属同济医院心内科

Primary sponsor:

Department of Cardiology Tongji Hospital

研究实施负责(组长)单位地址:

上海市新村路389号

Primary sponsor's address:

Tongji hospital, No. 389 Xincun road,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

市(区县):

Country:

China

Province:

Shanghai

City:

单位(医院):

同济大学附属同济医院

具体地址:

上海市新村路389号

Institution
hospital:

Tongji Hospital, Tongji University

Address:

No. 389 Xincun road,Shanghai,China

经费或物资来源:

国家自然科学基金,中国博士后科学基金,同济大学“医学+X”交叉项目

Source(s) of funding:

National Natural Science Foundation of China China Postdoctoral Science Foundation Cross-disciplinary Foundation on Medicine and X of Tongji Univesity

研究疾病:

心律失常  

Target disease:

Arrhythmia

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:

心律失常是心血管系统中的常见病,由不良的生活习惯以及慢性病引发的心律失常的发病率呈现逐年升高趋势。心律失常可导致多种并发症,包括体循环栓塞/卒中、心动过速相关心力衰竭、短暂性脑缺血发作甚至恶性心律失常相关猝死,显著威胁患者生命健康,降低生活质量,增加社会及家庭经济负担。因此,心律失常的早期准确诊断和定期监测至关重要。 心电图是确诊心律失常的金标准,但是,由于大多数心律失常呈现出间歇性发作的特点,异常心电波形的捕捉依赖于专业医师对长期 ECG 记录的分析;现有穿戴式、接触式设备存在诊断流程复杂、便捷性差、患者体验差、适用人群受限等问题,极大限制了医疗机构对心律失常的筛查能力。为此,亟需研发成本低廉、流程便捷、结果可靠的智能化心律失常诊断新方法,为心律失常的早期发现、精准诊疗和个体化管理提供有力支持。 本研究以研发基于面部视频的非接触式心律失常诊断方法为总体目标,重点攻克现有技术中普遍存在的“检测不精,诊断不足”等难题。实现心房颤动、室性早搏、房速等心律失常类型的非接触式诊断。  

Objectives of Study:

Arrhythmia is series of common cardiovascular diseases, and their incidences are increasing annually, particularly when triggered by unhealthy human lifestyle habits and chronic diseases. Arrhythmias can lead to a range of complications, including systemic embolism/stroke, tachycardia-induced heart failure, transient ischemic attacks (TIA), and even sudden cardiac death. These complications pose significant threats to patients’ lives, reduce quality of life, and increase both social and familial economic burdens. Therefore, early and accurate diagnosis of arrhythmias is critically important. The electrocardiogram (ECG) remains the gold standard for diagnosing arrhythmias. However, most arrhythmias occur intermittently, and detecting abnormal ECG patterns requires specialists to analyze long-term ECG recordings. Current wearable or contact-based devices often suffer from complex diagnostic workflows, limited convenience, poor user experience, and restricted applicability across populations, which greatly limits the capacity of healthcare systems to screen for arrhythmias effectively. Thus, there is an urgent need to develop a low-cost, convenient, and reliable intelligent diagnostic method for arrhythmias. This study aims to develop a facial video-based non-contact arrhythmia diagnosis method. It aims to achieve accurate diagnosis for most types of arrhythmias, such as atrial fibrillation, ventricular premature beats, and atrial tachycardia.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

年龄>=18岁、生命体征平稳、能够配合1min数据检查与收集

Inclusion criteria

Age>=18 y Vital signs stable Able to cooperate with 1min of fascial data collection

排除标准:

年龄<18岁,血流动力学不稳定、NYHA心功能III-IV级、偏瘫及不能配合检查的情况

Exclusion criteria:

Age less than 18y Vital signs instable NYHA III-IV grade paralyzed or any other conditions that cannot cooperate with data collection

研究实施时间:

Study execute time:

From 2024-01-01 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-02-16 00:00:00 To 2026-01-31 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):

心电图

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):

Electrocardiogram

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):

本研究待评估的诊断试验为基于面部视频的非接触式心律失常诊断方法。该方法首先研究基于对比与对抗学习机制的个体-心动特征解耦框架,通过比较不同面部视频集合中个体特征的共性与差异,实现多样化个体特征的精准挖掘,并以此将其与心动特征解耦,提升算法检测rPPG信号的准确性与泛化性;然后,以检测的rPPG信号和视频表观视觉特征为基础,搭建基于合作竞争机制的多任务学习框架,实现心房颤动、室性早搏、房速等多种心律失常的非接触式诊断。

Index test:

The diagnostic test to be evaluated in this study is a facial video-based non-contact arrhythmia diagnosis method. This method first proposes an individual-cardiac feature disentanglement framework based on contrastive and adversarial learning mechanisms. By analyzing the commonalities and differences of individual features across diverse facial video sets, the framework effectively extracts discriminative individual features and disentangles them from cardiac-related features, thereby enhancing the accuracy and generalizability of remote photoplethysmography (rPPG) signal regression. Subsequently, based on the detected rPPG signals and visual appearance features from the facial video, a multi-task learning framework with a cooperative-competitive mechanism is constructed to enable the non-contact diagnosis of various arrhythmia types, such as atrial fibrillation, ventricular premature beats, and atrial tachycardia.

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)

心律失常患者(心房颤动、心房扑动、房早、室早、房室传导阻滞)

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):

Patient with arrhythmia (Atrial fibrillation, Atrial Flutter, Premature Atrial Contraction, Premature Ventricular Contraction and Atrial ventricular Block)

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:

No

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

上海市 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

复旦大学附属金山医院 

单位级别:

三乙 

Institution
hospital:

Jinshan Hospital, Fudan University

Level of the institution:

Tertiary B

国家:

中国

省(直辖市):

上海市 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

同济大学附属同济医院 

单位级别:

三甲 

Institution
hospital:

Tongji Hospital, Tongji University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

心电图

指标类型:

主要指标

Outcome:

ECG

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

动态心电图

指标类型:

次要指标

Outcome:

Holter

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

心超

指标类型:

次要指标

Outcome:

UCG

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 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

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):

2027-12-31,国家生物信息中心 China National center for Bioinformation (https://ngdc.cncb.ac.cn/gsub/)

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

Dec. 31st 2027, China National center for Bioinformation (https://ngdc.cncb.ac.cn/gsub/)

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:

 2026-01-05 17:56:41