ChiCTR2600126239 版本V1.0 版本创建时间2026/06/05 11:28:09 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:

ChiCTR2600126239 

最近更新日期:

Date of Last Refreshed on:

2026-06-05 11:27:58 

注册时间:

Date of Registration:

2026-06-05 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

多模态数据驱动的脓毒症早期诊断及免疫分型智能模型开发与应用

Public title:

Development and Application of Intelligent Models for Early Diagnosis of Sepsis and Immunological Subtyping Driven by Multimodal Data

注册题目简写:

English Acronym:

研究课题的正式科学名称:

多模态数据驱动的脓毒症早期诊断及免疫分型智能模型开发与应用

Scientific title:

Development and Application of Intelligent Models for Early Diagnosis of Sepsis and Immunological Subtyping Driven by Multimodal Data

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:

胡林辉 

研究负责人:

胡林辉 

Applicant:

Hu Linhui 

Study leader:

Hu Linhui 

申请注册联系人电话:

Applicant telephone:

+86 13580013426

研究负责人电话:

Study leader's
telephone:

+86 668 2922131

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:

linchuangyjzx@163.com

研究负责人电子邮件:

Study leader's E-mail:

hulihuihong@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:

中国广东省茂名市茂南区为民路103号大院194号

研究负责人通讯地址:

中国广东省茂名市茂南区为民路101号

Applicant address:

103 Weimin Road, Compound 194, Maonan District, Maoming, Guangdong, China

Study leader's address:

101 Weimin Road, Maonan District, Maoming, 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:

茂名市人民医院

Applicant's institution:

Maoming People's Hospital

研究负责人所在单位:

茂名市人民医院

Affiliation of the Leader:

Maoming 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:

PJ2025MI-K073-01

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:

茂名市人民医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Maoming People's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2025-06-24 00:00:00

伦理委员会联系人:

陈西燕

Contact Name of the ethic committee:

Chen Xiyang

伦理委员会联系地址:

中国广东省茂名市茂南区为民路101号

Contact Address of the ethic committee:

101 Weimin Road, Maonan District, Maoming, Guangdong, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 668 2922871

伦理委员会联系人邮箱:

Contact email of the ethic committee:

13432351502@163.com

研究实施负责(组长)单位:

茂名市人民医院

Primary sponsor:

Maoming People's Hospital

研究实施负责(组长)单位地址:

中国广东省茂名市茂南区为民路101号

Primary sponsor's address:

101 Weimin Road, Maonan District, Maoming, 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

市(区县):

Country:

China

Province:

Guangdong

City:

单位(医院):

茂名市人民医院

具体地址:

中国广东省茂名市茂南区为民路101号

Institution
hospital:

Maoming People's Hospital

Address:

101 Weimin Road, Maonan District, Maoming, Guangdong, China

经费或物资来源:

茂名市科技计划

Source(s) of funding:

Maoming Municipal Techological Programme

研究疾病:

脓毒症相关性急性肾损伤  

Target disease:

Sepsis-induced acute kidney injury

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:

病例对照研究 

Study design:

Case-Control study 

研究目的:

本研究旨在基于多模态数据和机器学习技术,构建脓毒症的精准免疫分型与早期预警系统,通过整合临床指标、基因组学和代谢组学等多源信息,开发高精度预测模型,实现脓毒症的早期诊断与个体化治疗,最终提升识别率、降低病死率,并优化医疗资源配置。  

Objectives of Study:

The aim of this study is to develop a precise immune typing and early warning system for sepsis based on multimodal data and machine learning technologies. By integrating multi-source information such as clinical indicators, genomics, and metabolomics, the project seeks to create high-precision predictive models for early diagnosis and personalized treatment of sepsis. The ultimate goals are to improve early detection rates, reduce mortality, and optimize the allocation of medical resources.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

1. 年龄18岁及以上; 2. 入住ICU的患者; 3. 脓毒症风险:qSOFA(快速序贯器官衰竭评估)评分至少满足以下三个指标中的两个:呼吸频率 >= 22次/分钟;意识水平:GCS(格拉斯哥昏迷评分)< 15;收缩压 <= 100 mmHg。

Inclusion criteria

1. Aged 18 years or older; 2. Patients admitted to the ICU; 3. Sepsis Risk: A qSOFA (Quick Sequential Organ Failure Assessment) score meeting at least two of the following three criteria: Respiratory Rate >= 22 breaths per minute; Level of Consciousness: GCS (Glasgow Coma Scale) score < 15; Systolic Blood Pressure <= 100 mmHg.

排除标准:

1. 特定生理阶段:处于妊娠期或哺乳期的女性患者。

Exclusion criteria:

1. Specific Physiological Status: Female patients who are pregnant or lactating.

研究实施时间:

Study execute time:

From 2025-08-01 00:00:00 To 2027-07-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-10-01 00:00:00 To 2025-12-31 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

296

Group:

Observation 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):

广东 

市(区县):

 

Country:

China

Province:

Guangdong

City:

单位(医院):

茂名市人民医院 

单位级别:

三级甲等 

Institution
hospital:

Maoming People's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

脓毒症早期诊断模型的 AUC 值

指标类型:

主要指标

Outcome:

AUC of early sepsis diagnosis model

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

免疫分型模型的 AUC 值

指标类型:

主要指标

Outcome:

AUC of immune profiling model

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

模型预测的灵敏度

指标类型:

次要指标

Outcome:

Sensitivity of model prediction

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

模型预测的特异度

指标类型:

次要指标

Outcome:

Specificity of model prediction

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

患者住院死亡率

指标类型:

次要指标

Outcome:

In-hospital mortality 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:

住院时间缩短率

指标类型:

次要指标

Outcome:

Rate of hospital length of stay reduction

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

ICU 再入住率

指标类型:

次要指标

Outcome:

Re-admission rate to ICU

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:

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:

结束

/Completed

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:

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:

1. 数据采集 (Data Collection): 数据来源: 建立多中心ICU临床数据库。数据来源于合作医院的ICU。 数据类型: 收集多模态数据,包括: 临床数据: 生命体征(心率、血压、呼吸频率等)、实验室指标(白细胞计数、乳酸水平等)、病历记录、影像学资料。 组学数据: 基因组学数据(通过血液样本基因组测序)、代谢组学数据(对血液、尿液等生物样本进行代谢组学分析)。 免疫分型数据: 通过流式细胞术分析免疫细胞亚群(T细胞、B细胞等);检测细胞因子水平(TNF-α, IL-6, IL-10);检测免疫检查点分子(PD-1, CTLA-4)。 采集标准: 制定并统一多中心数据采集标准,确保数据一致性。 2. 数据管理 (Data Management): 数据清洗与预处理: 对收集的数据进行清洗、去噪、标准化处理,确保数据的完整性和一致性。 数据整合: 统一多模态数据的格式和标准,进行数据融合,为分析与建模做准备。 隐私与安全: 数据安全与隐私保护将严格遵循医疗数据管理规范。采用技术手段(如匿名化)保护患者隐私。 数据库建设: 项目团队已成功建立了多中心临床数据库和重症患者专病库,收集了超过5000例ICU患者的临床数据。

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

1. Data Collection: Data Source: Establishment of a multicenter ICU clinical database. Data is sourced from ICUs of partner hospitals. Data Types: Collection of multimodal data, including: Clinical Data: Vital signs (heart rate, blood pressure, respiratory rate, etc.), laboratory parameters (white blood cell count, lactate level, etc.), medical records, imaging data. Omics Data: Genomic data (via genomic sequencing of blood samples), metabolomic data (metabolomic analysis of biological samples such as blood and urine). Immune Phenotyping Data: Analysis of immune cell subsets (T cells, B cells, etc.) via flow cytometry; detection of cytokine levels (TNF-α, IL-6, IL-10); detection of immune checkpoint molecules (PD-1, CTLA-4). Collection Standards: Development and unification of multicenter data collection standards to ensure data consistency. 2. Data Management: Data Cleaning & Preprocessing: Collected data undergoes cleaning, denoising, and standardization to ensure completeness and consistency. Data Integration: Unification of data formats and standards for multimodal data, followed by data fusion to prepare for analysis and modeling. Privacy & Security: Data security and privacy protection will strictly comply with medical data management regulations. Technical measures (e.g., anonymization) are employed to protect patient privacy. Database Development: The project team has successfully established a multicenter clinical database and a specialized critical patient database, containing clinical data from over 5,000 ICU patients.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-06-05 11:27:58