用智能算法预测重症脑出血患者 3 个月后的康复情况

注册号:

Registration number:

ChiCTR2500101676 

最近更新日期:

Date of Last Refreshed on:

2025-04-28 11:48:56 

注册时间:

Date of Registration:

2025-04-28 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

用智能算法预测重症脑出血患者 3 个月后的康复情况

Public title:

Predict the rehabilitation status of patients wit'h severe intracerebral hemorrhage three months later using intelligent algorithms.

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于机器学习的重症脑出血患者90天功能预后预测模型的构建与多中心验证研究

Scientific title:

Construction and Multicenter Validation of a Machine Learning-Based Prediction Model for the 90-Day Functional Prognosis of Patients with Severe Intracerebral Hemorrhage

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:

王鹏举 

研究负责人:

王鹏举 

Applicant:

Pengju Wang 

Study leader:

Pengju Wang 

申请注册联系人电话:

Applicant telephone:

+86 15143171317

研究负责人电话:

Study leader's
telephone:

+86 431 88783351

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:

wangpengju87@jlu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

wangpengju87@jlu.edu.cn

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:

吉林省长春市新民大街1号

研究负责人通讯地址:

吉林省长春市新民大街1号

Applicant address:

No. 1, Xinmin Street, Changchun City, Jilin Province

Study leader's address:

No. 1, Xinmin Street, Changchun City, Jilin 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:

吉林大学第一医院

Applicant's institution:

The First Hospital of Jilin University

研究负责人所在单位:

吉林大学第一医院

Affiliation of the Leader:

The First Hospital of Jilin 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:

25K135-001

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:

吉林大学第一医院伦理委员会

Name of the ethic committee:

The IRB of the First Hospital of Jilin University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-04-14 00:00:00

伦理委员会联系人:

赵丽媛

Contact Name of the ethic committee:

Liyuan Zhao

伦理委员会联系地址:

吉林省长春市新民大街1号

Contact Address of the ethic committee:

No. 1, Xinmin Street, Changchun City, Jilin Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 431 88782013

伦理委员会联系人邮箱:

Contact email of the ethic committee:

18243006565@126.com

研究实施负责(组长)单位:

吉林大学第一医院

Primary sponsor:

The First Hospital of Jilin University

研究实施负责(组长)单位地址:

吉林省长春市新民大街1号

Primary sponsor's address:

No. 1, Xinmin Street, Changchun City, Jilin 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):

吉林

市(区县):

Country:

China

Province:

Jilin

City:

单位(医院):

吉林大学第一医院

具体地址:

吉林省长春市新民大街1号

Institution
hospital:

The First Hospital of Jilin University

Address:

No. 1, Xinmin Street, Changchun City, Jilin Province

经费或物资来源:

吉林省财政厅医疗卫生人才专项

Source(s) of funding:

Special Program for Medical and Health Talents in Jilin Province

研究疾病:

具体疾病: 1.高血压性脑出血 2.脑动脉瘤破裂出血 3.脑血管畸形出血 4.其他:包括脑淀粉样血管病变、血液病(白血病、血小板减少性紫癜等 )、梗死后出血、脑动脉炎、抗凝或溶栓治疗后出血等 症状: 1.颅内压增高:头痛,呕吐 2.意识障碍 3.神经功能缺损 运动障碍,共济失调,感觉障碍,疼痛,语言障碍,视力视野改变,眼球运动异常 4.生命体征改变 呼吸  

Target disease:

Specific diseases: 1. Hypertensive intracerebral hemorrhage 2. Rupture and bleeding of cerebral aneurysm 3. Hemorrhage due to cerebral vascular malformation 4. Others: Including cerebral amyloid angiopathy, hematological diseases (such as leukemia, thrombocytopenic purpura, etc.), hemorrhage after infarction, cerebral arteritis, hemorrhage after anticoagulant or thrombolytic therapy, etc. S

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:

队列研究 

Study design:

Cohort study 

研究目的:

精准构建预后预测模型:使用XGBoost、深度神经网络(DNN)等机器学习算法,深度整合重症脑出血患者的临床、影像、护理文书等多维度数据,克服传统预后预测工具仅依赖单维指标、难以综合分析复杂数据的局限。通过训练集、验证集和测试集分层设计,确保模型训练过程的科学性和有效性,精准预测重症脑出血患者的90天mRS评分,显著提升预后判断准确性,为临床医护人员提供可靠的决策依据。  

Objectives of Study:

Precisely construct a prognosis prediction model: Utilize machine learning algorithms such as XGBoost and Deep Neural Network (DNN) to deeply integrate multi-dimensional data of critically ill patients with intracerebral hemorrhage, including clinical data, imaging data, and nursing records. Overcome the limitations of traditional prognosis prediction tools that rely only on single-dimensional indicators and have difficulty in comprehensively analyzing complex data. Through the stratified design of the training set, validation set, and test set, ensure the scientificity and effectiveness of the model training process. Precisely predict the 90-day mRS score of critically ill patients with intracerebral hemorrhage, significantly improve the accuracy of prognosis judgment, and provide reliable decision-making basis for clinical medical staff.

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.合并严重心、肝、肾功能衰竭或晚期恶性肿瘤等影响预后独立性的其他严重疾病;
2.既往有严重神经功能缺损或长期严重依赖(mRS≥4)且不能明确此次出血导致功能变化的患者;
3.数据不完整或无法获得随访数据(90天mRS评分)的病例;

Exclusion criteria:

1.Have other serious diseases that affect the independence of prognosis, such as severe heart, liver, and kidney failure, or advanced malignant tumors; 2.Patients who had a history of severe neurological deficits or long-term severe dependence (Modified Rankin Scale (mRS) >= 4) and for whom the functional changes caused by this hemorrhage could not be clearly determined; 3.Cases with incomplete data or for which follow-up data (90-day mRS score) could not be obtained;

研究实施时间:

Study execute time:

From 2025-04-30 00:00:00 To 2027-12-30 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-04-30 00:00:00 To 2026-04-30 00:00:00

干预措施:

Interventions:

组别:

预后良好组与预后不良组

样本量:

1100

Group:

The group with good prognosis and the group with poor prognosis

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):

吉林 

市(区县):

 

Country:

China

Province:

Jilin

City:

单位(医院):

吉林大学第一医院 

单位级别:

三级甲等 

Institution
hospital:

The First Hospital of Jilin University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

吉林 

市(区县):

 

Country:

China

Province:

Jilin

City:

单位(医院):

延边大学附属医院(延边医院) 

单位级别:

三级甲等 

Institution
hospital:

The Affiliated Hospital of Yanbian University (Yanbian Hospital)

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

吉林 

市(区县):

 

Country:

China

Province:

Jilin

City:

单位(医院):

梅河口市中心医院 

单位级别:

三级甲等 

Institution
hospital:

Meihekou Central Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

90天mRS评分

指标类型:

主要指标

Outcome:

The mRS score at 90 days

Type:

Primary indicator

测量时间点:

90天后

测量方法:

评分通过电话随访或门诊复诊的方式收集,由经过培训的医护人员进行评估,以确保一致性和准确性。

Measure time point of outcome:

After 90 days

Measure method:

The scores are collected through telephone follow-ups or outpatient reexaminations, and evaluated by trained medical staff to ensure consistency and accuracy.

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:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 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):

No

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):

None

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:

数据采集crf表,数据管理epiinfo

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

Cry and epiinfo software

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2025-04-28 11:48:24