ChiCTR2500108420 版本V1.0 版本创建时间2025/08/29 16:02:00 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:

ChiCTR2500108420 

最近更新日期:

Date of Last Refreshed on:

2025-08-29 16:01:43 

注册时间:

Date of Registration:

2025-08-29 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

使用随机森林回归预测普通病房患者转入ICU的风险:基于改良早期预警评分(MEWS)的前瞻性分析

Public title:

Using random forest regression to predict the risk of general ward patients transferring to the ICU: a prospective analysis based on the Modified Early Warning Score (MEWS)

注册题目简写:

English Acronym:

研究课题的正式科学名称:

使用随机森林回归预测普通病房患者转入ICU的风险:基于改良早期预警评分(MEWS)的前瞻性分析

Scientific title:

Using random forest regression to predict the risk of general ward patients transferring to the ICU: a prospective analysis based on the Modified Early Warning Score (MEWS)

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:

幸莉萍 

研究负责人:

幸莉萍 

Applicant:

Liping Xing 

Study leader:

Liping Xing 

申请注册联系人电话:

Applicant telephone:

+86 152 7975 3685

研究负责人电话:

Study leader's
telephone:

+86 152 7975 3685

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:

gyfyxlp@163.com

研究负责人电子邮件:

Study leader's E-mail:

gyfyxlp@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:

江西省赣州市章贡区赣南医科大学第一附属医院黄金院区北楼4楼

研究负责人通讯地址:

江西省赣州市章贡区赣南医科大学第一附属医院黄金院区北楼4楼

Applicant address:

4th floor, North Building, Golden District, First Affiliated Hospital of Gannan Medical University, Zhanggong District, Ganzhou City, Jiangxi Province

Study leader's address:

4th floor, North Building, Golden District, First Affiliated Hospital of Gannan Medical University, Zhanggong District, Ganzhou City, Jiangxi Province

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:

赣南医科大学第一附属医院

Applicant's institution:

The First Affiliated Hospital of Gannan Medical University

研究负责人所在单位:

赣南医科大学第一附属医院

Affiliation of the Leader:

The First Affiliated Hospital of Gannan Medical 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:

LLSC-2025357

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:

赣南医科大学第一附属医院科学研究伦理委员会

Name of the ethic committee:

Ethics Committee of the First Affiliated Hospital of Gannan Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-07-03 00:00:00

伦理委员会联系人:

张国玺

Contact Name of the ethic committee:

Guoxi Zhang

伦理委员会联系地址:

江西省赣州市章贡区赣南医科大学第一附属医院黄金院区

Contact Address of the ethic committee:

First Affiliated Hospital of Gannan Medical University, Huangjin District, Zhanggong District, Ganzhou City, Jiangxi Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 797 868 9034

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:

赣南医科大学第一附属医院

Primary sponsor:

The First Affiliated Hospital of Gannan Medical University

研究实施负责(组长)单位地址:

江西省赣州市章贡区赣南医科大学第一附属医院黄金院区

Primary sponsor's address:

First Affiliated Hospital of Gannan Medical University, Huangjin District, Zhanggong District, Ganzhou City, Jiangxi Province

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

江西省

市(区县):

赣州

Country:

China

Province:

Jiangxi

City:

Ganzhou

单位(医院):

赣南医科大学第一附属医院

具体地址:

江西省赣州市章贡区金岭路128号

Institution
hospital:

The First Affiliated Hospital of Gannan Medical University

Address:

No. 128 Jinling Road, Zhanggong District, Ganzhou City, Jiangxi Province

经费或物资来源:

2024年江西省卫生健康委科技计划项目

Source(s) of funding:

2024 Jiangxi Provincial Health Commission Science and Technology Program Project

研究疾病:

重症监护病房  

Target disease:

ICU

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:

连续入组 

Study design:

Sequential 

研究目的:

为普通病房患者的风险评估和管理提供一种基于机器学习的新颖、有效、可解释的方法,有助于提高患者的安全性和生存率,降低医疗资源的浪费和成本。我们希望通过建立一个基于随机森林分类的预测模型,能够准确地判断普通病房患者是否需要转入ICU,并且能够识别出影响风险的重要变量和交互效应。我们还希望通过解释模型的预测机制和逻辑,能够为临床决策提供有用的指导,并为未来的研究提供新的思路和方向。  

Objectives of Study:

Provide a novel, effective, and interpretable machine learning-based method for risk assessment and management of general ward patients, which helps improve patient safety and survival rates, and reduce waste and costs of medical resources. We aim to establish a predictive model based on random forest classification that can accurately determine whether general ward patients need to be transferred to the ICU, and identify important variables and interaction effects that influence risks. We also hope that by explaining the predictive mechanisms and logic of the model, we can offer useful guidance for clinical decision-making and provide new ideas and directions for future research.

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≥16岁; (2)入院后预计住院时间≥48小时; (3)签署知情同意书

Inclusion criteria

(1) Age >= 16 years; (2) Expected length of stay after admission >= 48 hours; (3) Sign the informed consent form

排除标准:

(1)术后转入ICU观察者(避免混杂术后常规监护); (2)终末期疾病(预计生存期≤3天,如晚期多器官衰竭、不可逆性休克); (3)妊娠期或哺乳期妇女(生理状态干扰生命体征解读); (4)临床资料缺失率≥30%者(如电子病例未记录MEWS评分);

Exclusion criteria:

(1) Patients transferred to the ICU for observation (to avoid confounding factors associated with routine postoperative monitoring); (2) Terminal illness (expected survival <=3 days, such as advanced multi-organ failure or irreversible shock); (3) Pregnant or lactating women (physiological state interfering with vital sign interpretation); (4) Patients with a clinical data deficiency rate of >=30% (e.g., electronic medical records lacking MEWS scores)

研究实施时间:

Study execute time:

From 2024-01-01 00:00:00 To 2026-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-05-13 00:00:00 To 2025-03-29 00:00:00

干预措施:

Interventions:

组别:

转入组

样本量:

526

Group:

Transfer to group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

未转入组

样本量:

1474

Group:

Not transferred to the 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):

江西 

市(区县):

赣州 

Country:

China

Province:

Jiangxi

City:

Ganzhou

单位(医院):

赣南医科大学第一附属医院 

单位级别:

三甲 

Institution
hospital:

Gannan Medical University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

改良早期预警评分

指标类型:

主要指标

Outcome:

Modified Early Warning Score(MEWS)

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

急性生理与慢性健康评分

指标类型:

主要指标

Outcome:

Acute Physiology and Chronic Health EvaluationⅡ(APACHEⅡ)

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

格拉斯哥昏迷评分

指标类型:

主要指标

Outcome:

Glasgow coma scale(GCS)

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:

结束

/Completed

年龄范围:

Participant age:

最小 Min age 16 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

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):

邮箱:gyfyxlp@163.com 2025.7.1

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

Email:gyfyxlp@163.com date:2025.7.1

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:

数据收集:从医院的电子病历系统中提取所有入选患者的基本信息、生理参数、主要诊断、ICU类别、APACHE II评分等数据,并计算每位患者入院后24小时内最高MEWS评分作为自变量之一; 数据管理:完成所有入选患者的数据提取和录入,形成完整的数据集;检查数据的完整性和准确性,使用数据质量控制工具进行数据审核;

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

Data collection: Extract basic information, physiological parameters, primary diagnoses, ICU categories, APACHE II scores, and other data of all selected patients from the hospital's electronic medical record system, and calculate the highest MEWS score within 24 hours of each patient's admission as one of the independent variables; Data management: Complete the data extraction and entry for all selected patients to form a complete dataset; check the integrity and accuracy of the data, and use data quality ;

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:

 2025-08-29 16:01:43