ChiCTR2500114908 版本V1.0 版本创建时间2025/12/18 17:13:51 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:

ChiCTR2500114908 

最近更新日期:

Date of Last Refreshed on:

2025-12-18 17:13:33 

注册时间:

Date of Registration:

2025-12-18 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

机器学习驱动的急性心梗后心力衰竭精准管理策略构建

Public title:

Construction of a Precision Management Strategy for Heart Failure after Acute Myocardial Infarction Driven by Machine Learning

注册题目简写:

English Acronym:

研究课题的正式科学名称:

机器学习驱动的急性心梗后心力衰竭精准管理策略构建

Scientific title:

Construction of a Precision Management Strategy for Heart Failure after Acute Myocardial Infarction Driven by Machine 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:

丰冠鹏 

研究负责人:

丰冠鹏 

Applicant:

Feng Guanpeng 

Study leader:

Feng Guanpeng 

申请注册联系人电话:

Applicant telephone:

+86 18358250769

研究负责人电话:

Study leader's
telephone:

+86 574 8665 7807

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:

fgpeng@126.com

研究负责人电子邮件:

Study leader's E-mail:

Guanpeng.Feng@chccilin.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:

浙江省宁波市镇海区南二西路718号

研究负责人通讯地址:

宁波市镇海区骆驼街道南二西路718号

Applicant address:

No. 718, South Second West Road, Zhenhai District, Ningbo City, Zhejiang Province

Study leader's address:

No. 718, South Second West Road, Luotuo Street, Zhenhai District, Ningbo

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:

宁波市镇海区人民医院

Applicant's institution:

Ningbo Zhenhai District People's Hospital

研究负责人所在单位:

宁波市镇海区人民医院

Affiliation of the Leader:

Ningbo Zhenhai District 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:

镇海区人民医院伦审2025研第022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:

宁波市镇海区人民医院医学伦理委员会

Name of the ethic committee:

The Medical Ethics Committee of Ningbo Zhenhai District People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-10-20 00:00:00

伦理委员会联系人:

包兴洁

Contact Name of the ethic committee:

Bao Xingjie

伦理委员会联系地址:

宁波市镇海区骆驼街道南二西路718号

Contact Address of the ethic committee:

No. 718, South Second West Road, Luotuo Street, Zhenhai District, Ningbo

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 574 86655003

伦理委员会联系人邮箱:

Contact email of the ethic committee:

18289762113@163.com

研究实施负责(组长)单位:

宁波市镇海区人民医院

Primary sponsor:

Ningbo Zhenhai District People's Hospital

研究实施负责(组长)单位地址:

宁波市镇海区骆驼街道南二西路718号

Primary sponsor's address:

No. 718, South Second West Road, Luotuo Street, Zhenhai District, Ningbo

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

宁波市镇海区人民医院

具体地址:

宁波市镇海区骆驼街道南二西路718号

Institution
hospital:

Ningbo Zhenhai District People's Hospital

Address:

No. 718, South Second West Road, Luotuo Street, Zhenhai District, Ningbo

经费或物资来源:

浙江省医药卫生科技项目

Source(s) of funding:

Zhejiang Provincial Medical and Health Science and Technology Project

研究疾病:

心力衰竭  

Target disease:

Heart failure

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:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

主要目的: 1.验证模型的预测效能,通过整合电子病历、穿戴设备时序数据、影像学特征及多组学数据,实现 AUC≥0.85、敏感性≥89%的跨中心稳定性能,显著优于传统静态模型(AUC 0.62-0.75); 2.开发轻量化 AI 决策支持系统,5 分钟内生成个性化干预方案(如β受体阻滞剂剂量优化),并嵌入医院信息系统与可穿戴设备实现实时预警。 次要目的: 1.评估临床适用性,分析医生对模型预警阈值与干预建议的接受度,目标降低基层误诊率40%; 2.前瞻性观察模型对患者结局的影响,目标减少 HF 发生率 12%-15%及再住院率; 3.建立标准化“动态监测-风险预警-干预”闭环管理流程,推动智慧医疗落地。  

Objectives of Study:

Primary Objectives: 1. Validate the predictive performance of the model by integrating electronic medical records, wearable device time-series data, imaging features, and multi-omics data, achieving cross-center stable performance with AUC>=0.85 and sensitivity>=89%, significantly outperforming traditional static models (AUC 0.62-0.75); 2. Develop a lightweight AI decision support system that generates personalized intervention plans (e.g., β-blocker dose optimization) within 5 minutes, and embed it into hospital information systems and wearable devices for real-time alerts. Secondary Objectives: 1. Assess clinical applicability by analyzing physicians' acceptance of model alert thresholds and intervention recommendations, aiming to reduce misdiagnosis rates in primary care by 40%; 2. Prospectively observe the impact of the model on patient outcomes, targeting a 12%-15% reduction in HF incidence and rehospitalization rates; 3. Establish a standardized 'dynamic monitoring–risk alert–intervention' closed-loop management process to promote the implementation of smart healthcare.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

要求患者符合2023年ESC指南确诊的急性心肌梗死(STEMI/NSTEMI),年龄18-85岁,并能配合穿戴设备完成动态监测;签署相关知情同意书。

Inclusion criteria

Patients are required to meet the following criteria: they must have been diagnosed with acute myocardial infarction (STEMI/NSTEMI) according to the 2023 ESC guidelines and have undergone reperfusion therapy (TIMI flow grades 2-3), be aged between 18 and 85 years, have a baseline LVEF of ≥40%, and be able to cooperate with wearing a device for dynamic monitoring; they must also sign the relevant informed consent form.

排除标准:

严重肝肾功能不全(eGFR<30mL/min或Child-Pugh C级)、活动性恶性肿瘤、妊娠期及关键数据缺失者,同时排除无法耐受穿戴设备监测或参与其他干预性试验的干扰因素。

Exclusion criteria:

Patients with end-stage heart failure (NYHA IV), severe hepatic and renal insufficiency (eGFR < 30 mL/min or Child-Pugh C), active malignancy, pregnancy, and missing key data were excluded. Interfering factors such as inability to tolerate wearable device monitoring or participation in other intervention trials were also excluded.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2028-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-01-01 00:00:00 To 2026-12-31 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):

患者出现典型的心力衰竭症状和体征;心衰的关键生物标志物BNP持续升高≥50%;心脏超声提示左室射血分数(LVEF)较基线值下降≥15%。

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 patient exhibited typical symptoms and signs of heart failure; the key biomarker for heart failure, BNP, continued to rise by >=50%; and the cardiac ultrasound indicated a decrease in left ventricular ejection fraction (LVEF) by >=15% compared to the baseline value.

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-GRU-GCN 的混合模型

Index test:

Hybrid Model Based on Transformer-GRU-GCN

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)

急性心梗后出现典型的心力衰竭症状和体征(如呼吸困难、乏力、体液潴留等)。

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):

After acute myocardial infarction, typical symptoms and signs of heart failure (such as dyspnea, fatigue, fluid pond, etc.) appear.

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):

慢性肺疾病急性加重或肺栓塞。

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:

Acute exacerbation of chronic lung disease or pulmonary embolism.

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

宁波市镇海区人民医院 

单位级别:

三级 

Institution
hospital:

Ningbo Zhenhai District People's Hospital

Level of the institution:

Tertiary

测量指标:

Outcomes:

指标中文名:

心衰发生率预测准确性

指标类型:

主要指标

Outcome:

Accuracy of heart failure incidence prediction

Type:

Primary indicator

测量时间点:

出院前48h;出院后第1-12个月

测量方法:

通过穿戴设备持续采集动态生理参数(心率变异性、血压昼夜节律等),结合门诊随访记录心衰症状(NYHA分级变化)、超声心动图(LVEF、E/e'值)及6分钟步行试验。

Measure time point of outcome:

48 hours before discharge;1st to 12th month after discharge

Measure method:

Continuous acquisition of dynamic physiological parameters (heart rate variability, circadian rhythm of blood pressure, etc.) through wearable devices, combined with outpatient follow-up records of heart failure symptoms (changes in NYHA classification), echocardiography (LVEF, E/e' ratio), and 6-minute walk test.

指标中文名:

再住院率

指标类型:

次要指标

Outcome:

Readmission 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:

医生采纳率

指标类型:

次要指标

Outcome:

Physician adoption rate

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:

血液

组织:

Sample Name:

Blood

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 85 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):

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

N/A

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,电子采集和管理系统

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

A CRF and an electronic data capture.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-12-18 17:13:33