人工智能驱动的高血压风险预测与临床验证研究

注册号:

Registration number:

ChiCTR2600119398 

最近更新日期:

Date of Last Refreshed on:

2026-02-26 14:29:29 

注册时间:

Date of Registration:

2026-02-26 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

人工智能驱动的高血压风险预测与临床验证研究

Public title:

Artificial intelligence–driven hypertension risk prediction and clinical validation study

注册题目简写:

English Acronym:

研究课题的正式科学名称:

人工智能驱动的高血压风险预测与临床验证研究

Scientific title:

Artificial intelligence–driven hypertension risk prediction and clinical validation study

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:

苗孟丹 

研究负责人:

苗孟丹 

Applicant:

Mengdan Miao 

Study leader:

Mengdan Miao 

申请注册联系人电话:

Applicant telephone:

+86 180 3293 6267

研究负责人电话:

Study leader's
telephone:

+86 180 3293 6267

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:

m18032936267@163.com

研究负责人电子邮件:

Study leader's E-mail:

m18032936267@163.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:

邯郸市丛台路25号

研究负责人通讯地址:

邯郸市丛台路25号

Applicant address:

No. 25 Congtai Road, Handan City

Study leader's address:

No. 25 Congtai Road, Handan City

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:

邯郸市第一医院

Applicant's institution:

Handan First Hospital

研究负责人所在单位:

邯郸市第一医院

Affiliation of the Leader:

Handan First 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:

HDYY-KT-26003

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:

邯郸市第一医院伦理委员会

Name of the ethic committee:

Ethics Committee of the First Hospital of Handan

伦理委员会批准日期:

Date of approved by ethic committee:

2026-01-19 00:00:00

伦理委员会联系人:

杨雅璇

Contact Name of the ethic committee:

Yaxuan Yang

伦理委员会联系地址:

邯郸市丛台路25号

Contact Address of the ethic committee:

No. 25 Congtai Road, Handan City

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 310 863 7580

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:

邯郸市第一医院

Primary sponsor:

Handan First Hospital

研究实施负责(组长)单位地址:

邯郸市丛台路25号

Primary sponsor's address:

No. 25 Congtai Road, Handan City

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

河北省

市(区县):

邯郸市

Country:

China

Province:

Hebei

City:

单位(医院):

邯郸市第一医院

具体地址:

邯郸市丛台路25号

Institution
hospital:

Handan First Hospital

Address:

No. 25 Congtai Road, Handan City

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

高血压  

Target disease:

Hypertension

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:

诊断性病例对照试验 

Study design:

Diagnostic test: case-control 

研究目的:

本研究旨在开发并验证一个基于Transformer架构的深度学习模型,使其能够仅利用常规胸片这一最普及的影像检查,自动、准确地预测个体的高血压分级及其对应的整体心血管风险分层。本研究将利用大规模、多中心的回顾性数据,完成模型的构建、训练与内部验证,并在一系列独立的外部验证集中全面评估其分类性能与稳健性。 此外,研究将利用可解释性技术深入探索模型决策的影像学依据,,并评估其在不同人群中的性能公平性,最终为未来实现低成本、高通量的心血管风险初筛提供关键的技术基础与循证依据。  

Objectives of Study:

This research aims to develop and validate a deep learning model based on the Transformer architecture, enabling it to automatically and accurately predict an individual's hypertension classification and corresponding overall cardiovascular risk stratification using only conventional chest X-rays, the most widely available imaging examination. This study will leverage large-scale, multi-centre retrospective data to complete the model's construction, training, and internal validation, and comprehensively evaluate its classification performance and robustness across a series of independent external validation sets. Furthermore, the research will employ explainable AI techniques to investigate the radiological basis of the model's decisions and assess its performance fairness across diverse populations, ultimately providing a crucial technical foundation and evidence base for future low-cost, high-throughput cardiovascular risk screening.

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. 胸片质量不佳(严重旋转、吸气不足、金属伪影、图像不完整)。 2. 胸片显示急性心肺疾病(如大量胸腔积液、气胸、肺炎实变)可能显著影响心脏轮廓评估。 3. 已植入心脏起搏器、除颤器或存在其他显著影响纵隔轮廓的植入物(单纯冠状动脉支架不排除)。 4. 临床资料严重缺失,无法确定血压分级或ESC风险分层。 5. 怀孕或哺乳期妇女。 6. 与其他可能干扰血压评估的干预性临床试验。

Exclusion criteria:

1. Chest X-ray quality is inadequate (severe rotation, insufficient inspiration, metallic artefact, incomplete image). 2. Chest X-ray reveals acute cardiopulmonary disease (e.g., large pleural effusion, pneumothorax, pneumonic consolidation) that may significantly affect cardiac silhouette assessment. 3. An implanted cardiac pacemaker, defibrillator, or other significant implant affecting the mediastinal contour is present (coronary artery stents alone are not exclusionary). 4. Significant clinical data is missing, precluding determination of blood pressure grading or ESC risk stratification. 5. Pregnant or breastfeeding women. 6. Participation in other interventional clinical trials that could interfere with blood pressure assessment.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2026-06-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-02-01 00:00:00 To 2026-06-30 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):

心内科专家根据完整病历判定

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):

Cardiology experts make judgments based on complete medical records

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):

基于Transformer架构的深度学习模型

Index test:

Deep Learning Model Based on Transformer Architecture

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)

该人群来源于多中心、接受标准胸部X光片检查的成年人群

例数:

Sample size:

700

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 cohort was derived from a multi-centre adult population undergoing standard chest X-ray examination.

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):

河北省 

市(区县):

邯郸市 

Country:

China

Province:

Hebei

City:

单位(医院):

邯郸市第一医院 

单位级别:

三甲 

Institution
hospital:

Handan First Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

河北省 

市(区县):

石家庄市 

Country:

China

Province:

Hebei

City:

单位(医院):

河北医科大学第一医院 

单位级别:

三甲 

Institution
hospital:

The First Hospital of Hebei Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

额外检出率

指标类型:

次要指标

Outcome:

Additional detection rate

Type:

Secondary 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

指标类型:

主要指标

Outcome:

Sensitivity

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

受试者工作特征曲线下面积

指标类型:

主要指标

Outcome:

Area Under the Receiver Operating Characteristic Curve

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异性

指标类型:

主要指标

Outcome:

Specificity

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:

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 80 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:

公开/Public

盲法:

Blinding:

试验完成后的统计结果(上传文件):

Calculated Results after
the Study Completed(upload file):

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):

研究公开发表后半年,邮件联系研究负责人合理获取。

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

Six months after the publication of the research, contact the research leader via email to obtain reasonable information.

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:

病例记录表

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

Case Report Form, CRF

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-02-26 14:29:08