ChiCTR2400094303 版本V1.0 版本创建时间2024/12/19 17:11:29 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:

ChiCTR2400094303 

最近更新日期:

Date of Last Refreshed on:

2024-12-19 17:10:51 

注册时间:

Date of Registration:

2024-12-19 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于机器学习的儿童先心病术后不良结局预测模型

Public title:

Machine Learning-Based Prediction Model for Adverse Outcomes After Pediatric Congenital Heart Disease Surgery

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于机器学习的儿童先心病术后不良结局预测模型

Scientific title:

Machine Learning-Based Prediction Model for Adverse Outcomes After Pediatric Congenital Heart Disease Surgery

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:

章宇朕 

研究负责人:

成黎明 

Applicant:

Zhang Yuzhen 

Study leader:

Cheng Liming 

申请注册联系人电话:

Applicant telephone:

+86 183 1437 7764

研究负责人电话:

Study leader's telephone:

+86 138 8876 4840

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:

1005578089@qq.com

研究负责人电子邮件:

Study leader's E-mail:

medcheng@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:

云南省昆明市西山区前兴路288号

研究负责人通讯地址:

云南省昆明市西山区前兴路288号

Applicant address:

No. 288, Qianxing Road, Xishan District, Kunming City, Yunnan Province, China

Study leader's address:

No. 288, Qianxing Road, Xishan District, Kunming City, Yunnan Province, 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:

昆明市儿童医院

Applicant's institution:

Kunming Children's Hospital

研究负责人所在单位:

昆明市儿童医院

Affiliation of the Leader:

Kunming Children's Hospital

是否获伦理委员会批准:

是/Yes

Approved by ethic committee:

Yes

伦理委员会批件文号:

Approved No. of ethic committee:

IEC-C-008-A07-V3.0

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:

昆明市儿童医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Kunming Children's Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2024-10-24 00:00:00

伦理委员会联系人:

邱琦

Contact Name of the ethic committee:

Qiu Qi

伦理委员会联系地址:

云南省昆明市西山区前兴路288号

Contact Address of the ethic committee:

No. 288, Qianxing Road, Xishan District, Kunming City, Yunnan Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 871 6330 9095

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:

昆明市儿童医院

Primary sponsor:

Kunming Children's Hospital

研究实施负责(组长)单位地址:

云南省昆明市西山区前兴路288号

Primary sponsor's address:

No. 288, Qianxing Road, Xishan District, Kunming City, Yunnan Province, 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):

云南省

市(区县):

昆明市

Country:

China

Province:

Yunnan

City:

Kuming

单位(医院):

昆明市儿童医院

具体地址:

云南省昆明市西山区前兴路288号

Institution
hospital:

Kunming Children's Hospital

Address:

No. 288, Qianxing Road, Xishan District, Kunming City, Yunnan Province, China

经费或物资来源:

自筹

Source(s) of funding:

Self-raised

Target disease:

Congenital Heart Disease

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

回顾性研究 

Study phase:

Retrospective study

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

本研究采用患者易于获取的人口统计学数据;术前血常规数据、肝肾功能数据、心脏彩超数据及部分术中数据,利用机器学习算法构建包括决策树、随机森林、支持向量机、极致梯度提升算法、梯度提升机、轻量级梯度提升机算法、朴素贝叶斯、多重感知器在内的8种二分类预测模型,以预测CHD手术后可能出现的不良结局,并与传统多因素逻辑回归模型进行对比。通过混淆矩阵、ROC曲线、校准曲线和决策曲线,对模型性能进行全面评估并挑选出性能最佳的模型,最后将其线上部署为网页,提供一种方便快捷的预测方式。通过该模型,医生可以在出手术室之前就对患者的术后风险进行量化评估,从而根据患者个体情况制定更为个性化的术后管理和治疗方案,提升医疗效率。  

Objectives of Study:

This study utilizes easily accessible patient demographic data, preoperative routine blood test data, liver and kidney function data, echocardiography data, and intraoperative data to construct eight binary classification prediction models using machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine, Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LightGBM), Naive Bayes, and Multilayer Perceptron. These models aim to predict adverse outcomes following CHD surgery and are compared with traditional multivariate logistic regression models.The performance of the models is comprehensively evaluated using confusion matrices, ROC curves, calibration curves, and decision curves, selecting the best-performing model for deployment as an online web tool. This tool provides a fast and convenient prediction method, enabling clinicians to quantitatively assess postoperative risks before the patient leaves the operating room. By doing so, it supports the development of more personalized postoperative management and treatment plans tailored to individual patients, ultimately improving healthcare efficiency.

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

年龄小于18岁且接受体外循环辅助手术的患儿

Inclusion criteria

Children under 18 years old undergoing cardiopulmonary bypass-assisted surgery

排除标准:

1.结局数据缺失的患儿。 2.接受多次手术的患儿。

Exclusion criteria:

1.Children with missing outcome data. 2.Children undergoing multiple surgeries.

研究实施时间:

Study execute time:

From 2024-10-24 00:00:00 To 2025-10-24 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-12-31 00:00:00 To 2025-01-31 00:00:00  

干预措施:

Interventions:

组别:

训练组

样本量:

700

Group:

Training group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

测试组

样本量:

300

Group:

Testing 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):

云南省 

市(区县):

昆明市 

Country:

China 

Province:

Yunnan 

City:

Kunming 

单位(医院):

昆明市儿童医院 

单位级别:

三甲 

Institution
hospital:

Kunming Children's Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

术后不良结局

指标类型:

主要指标

Outcome:

Postoperative adverse outcomes

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

院内早期死亡

指标类型:

次要指标

Outcome:

Early in-hospital mortality

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

住院时间延长

指标类型:

次要指标

Outcome:

Prolonged hospitalization

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

机械通气时间延长

指标类型:

次要指标

Outcome:

Prolonged mechanical ventilation time

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

拔管后二次插管

指标类型:

次要指标

Outcome:

Reintubation after extubation

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

使用后销毁  

说明

Fate of sample:

Destruction 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 years
最大 Max age 18 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

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):

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:

CRF and EDC

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

CRF and EDC

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:

 2024-12-19 17:10:51