ChiCTR2500107709 版本V1.0 版本创建时间2025/08/18 09:52:44 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:

ChiCTR2500107709 

最近更新日期:

Date of Last Refreshed on:

2025-08-18 09:52:36 

注册时间:

Date of Registration:

2025-08-18 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于机器学习的术后降钙素原模型预测结直肠癌术后吻合口漏的临床研究

Public title:

Machine Learning-Based Procalcitonin Model for Predicting Anastomotic Leakage After Colorectal Cancer Surgery: A Clinical Study

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于机器学习的术后降钙素原模型预测结直肠癌术后吻合口漏的临床研究

Scientific title:

Machine Learning-Based Procalcitonin Model for Predicting Anastomotic Leakage After Colorectal Cancer Surgery: A Clinical Study

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:

苏永辉 

研究负责人:

苏永辉 

Applicant:

Yonghui Su 

Study leader:

Yonghui Su 

申请注册联系人电话:

Applicant telephone:

+86 13326699169

研究负责人电话:

Study leader's telephone:

+86 756 2528708

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:

suyh@mail.sysu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

suyh@mail.sysu.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:

广东省珠海市香洲区梅华东路52号

研究负责人通讯地址:

广东省珠海市香洲区梅华东路52号

Applicant address:

No. 52, Meihua East Road, Xiangzhou District, Zhuhai, Guangdong

Study leader's address:

No. 52, Meihua East Road, Xiangzhou District, Zhuhai, Guangdong

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:

中山大学附属第五医院

Applicant's institution:

Fifth Affiliated Hospital, Sun Yat-Sen University

研究负责人所在单位:

中山大学附属第五医院

Affiliation of the Leader:

Fifth Affiliated Hospital, Sun Yat-Sen University

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:

中大五院【2025】伦字第(K182-1)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:

中山大学附属第五医院医学伦理委员会

Name of the ethic committee:

The Fifth Affiliated Hospital Sun Yat sen University Committee on medical ethics

伦理委员会批准日期:

Date of approved by ethic committee:

2025-08-04 00:00:00

伦理委员会联系人:

傅雪婷

Contact Name of the ethic committee:

Fu Xueting

伦理委员会联系地址:

广东省珠海市香洲区梅华东路52号

Contact Address of the ethic committee:

No. 52, Meihua East Road, Xiangzhou District, Zhuhai, Guangdong

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 756 2528895

伦理委员会联系人邮箱:

Contact email of the ethic committee:

813510375@qq.com

研究实施负责(组长)单位:

中山大学附属第五医院

Primary sponsor:

Fifth Affiliated Hospital, Sun Yat-Sen University

研究实施负责(组长)单位地址:

广东省珠海市香洲区梅华东路52号

Primary sponsor's address:

No. 52, Meihua East Road, Xiangzhou District, Zhuhai, Guangdong

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):

中山大学附属第五医院

具体地址:

广东省珠海市香洲区梅华东路52号

Institution
hospital:

Fifth Affiliated Hospital, Sun Yat-Sen University

Address:

No. 52, Meihua East Road, Xiangzhou District, Zhuhai, Guangdong

经费或物资来源:

自筹

Source(s) of funding:

Self-finance

Target disease:

Anastomotic leakage

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:

1.接受了结直肠癌切除术的患者,将患者分为吻合口漏组和无吻合口漏组,比较两组患者人口特征、术后PCT的差异。 2.基于多种机器学习,运用患者人口特征联合术后第2天/术后第3天/术后第2+3天PCT构建预测吻合口漏模型。  

Objectives of Study:

1.Patients who underwent colorectal resection were divided into an anastomotic leakage group and a non-anastomotic leakage group. The demographic characteristics and postoperative procalcitonin (PCT) levels were compared between the two groups. 2.Using multiple machine learning algorithms, predictive models for anastomotic leakage were developed and constructed based on patient demographic characteristics combined with PCT levels on postoperative day 2, postoperative day 3, and both postoperative days 2 and 3.

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.性别为男性或女性; 2.年龄≥18岁; 3.接受过结肠癌切除手术治疗且进行肠道吻合者; 4.2022年05月-2026年06月就诊于中山大学附属第五医院; 5.经ACPGBI指南,规范诊断为结直肠癌术后吻合口漏的患者;

Inclusion criteria

1.Gender: Male or female; 2.Age >=18 years old; 3.Patients who had undergone surgical resection for colonic cancer with intestinal anastomosis. 4.Patients who were treated at The Fifth Affiliated Hospital of Sun Yat-sen University between May 2022 and June 2026; 5.Patients diagnosed with anastomotic leakage following colorectal cancer surgery according to the ACPGBI guidelines.

排除标准:

1.围手术期有活动性感染患者;
2.急诊手术患者;
3.缺少术后1-3天PCT及其他炎症指标患者;
4.经研究者判断认为不适合参与本研究的患者;

Exclusion criteria:

1.Patients with active infection during the perioperative period.
2.Patients undergoing urgent surgery;
3.Patients lacking complete procalcitonin (PCT) and other inflammatory marker measurements on postoperative days 1 to 3.
4.Patients deemed ineligible for participation by the investigator;

研究实施时间:

Study execute time:

From 2025-08-15 00:00:00 To 2025-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-09-01 00:00:00 To 2025-10-31 00:00:00  

干预措施:

Interventions:

组别:

训练集组

样本量:

226

Group:

Training cohort group

Sample size:

干预措施:

患者基线特征及术后炎症指标

干预措施代码:

Intervention:

Patient baseline characteristics and postoperative inflammatory markers

Intervention code:

组别:

验证集组

样本量:

97

Group:

Validation cohort group

Sample size:

干预措施:

患者基线特征及术后炎症指标

干预措施代码:

Intervention:

Patient baseline characteristics and postoperative inflammatory markers

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):

中山大学附属第五医院 

单位级别:

三甲 

Institution
hospital:

Fifth Affiliated Hospital, Sun Yat-Sen University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

广东 

市(区县):

 

Country:

China 

Province:

Guangdong 

City:

 

单位(医院):

中山大学附属第六医院 

单位级别:

三甲 

Institution
hospital:

The Sixth Affiliated Hospital , Sun Yat-sen University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

预测模型的AUC

指标类型:

主要指标

Outcome:

AUC of the Prediction Model

Type:

Primary indicator

测量时间点:

确诊吻合口漏后

测量方法:

使用 R 4.4.3 对患者基线特征和术后炎症指标进行计算

Measure time point of outcome:

After diagnosis of anastomotic leakage

Measure method:

Using R 4.4.3 for baseline characteristics and postoperative patients with inflammatory index to calculate

指标中文名:

模型的准确率

指标类型:

次要指标

Outcome:

The accuracy of the model

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

灵敏度

指标类型:

次要指标

Outcome:

Sensitivity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

特异度

指标类型:

次要指标

Outcome:

Specificity

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

阳性预测值

指标类型:

次要指标

Outcome:

Positive predictive value

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

阴性预测值

指标类型:

次要指标

Outcome:

Negative predictive value

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

FI分数

指标类型:

次要指标

Outcome:

FI score

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

校准度

指标类型:

次要指标

Outcome:

Degree of calibration

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

净收益

指标类型:

次要指标

Outcome:

Net income

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:

N/A

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 18 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):

研究者通过计算机随机数列随机以7:3 的比例分为训练集和验证集

Randomization Procedure (please state who generates the random number sequence and by what method):

Using a computer-generated random number sequence, investigators randomly assigned patients to the training set and validation set in a 7:3 ratio.

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:

开放标签

Blinding:

Open-label study

是否共享原始数据:

IPD sharing

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:

(一)数据记录 1.研究者必须保证数据真实、完整、准确。2.研究者在入组研究参与者后及时填写病例报告表或临床研究数据记录表,保证病例报告表或临床研究数据记录表上的内容与病历内容一致。3.研究者记录做任何更正时只能划线,旁注改后的数据,由研究者签名并注明日期,不得擦涂、覆盖原始记录。4.实验室检查项目齐全且均可溯源。5.每例研究参与者数据收集结束后,研究者应及时填写好病例报告表或临床研究数据记录表上相关数据,并交本中心主要研究者审核、签名确认。 (二)数据管理 1. 数据的临床研究数据记录表的填写与移交 原始记录(原始病历、检查报告单等)需妥善保存。临床研究数据记录表的数据均来源于原始病历,由研究者填写,每个入选获得编码的病例必须完成临床研究数据记录表。完成的临床研究数据记录表由主要研究者审查后交数据管理员,进行数据录入与管理工作。 2. 数据库的设计及建立 建立临床研究数据库,记录CRF表中所有的信息。数据库的格式将尽量与CRF表的格式相对应以方便录入的进行。

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

1. Data Recording (1).Researchers must ensure that the data is true, complete and accurate. (2). After enrolling the research participants, the researchers should promptly fill out the case report form or the clinical research data record form to ensure that the contents on the case report form or the clinical research data record form are consistent with the medical records. (3). When researchers make any corrections to their records, they can only underline the modified data, annotate it with the researcher's signature and date, and must not erase or cover the original records. (4). The laboratory inspection items are complete and all can be traced. (5). After the data collection for each study participant is completed, the researcher should promptly fill in the relevant data on the case report form or clinical research data record form and submit it to the principal researcher of this center for review and signature confirmation. 2.Data Management (1). Filling in and transferring the clinical research data record form Original records (such as original medical records, examination reports, etc.) should be properly kept. The data in the clinical research data record form are all derived from the original medical records and filled in by the researchers. Each case that is selected and encoded must complete the clinical research data record form. The completed clinical research data record form is reviewed by the principal investigator and then submitted to the data administrator for data entry and management. (2). Database design and establishment Establish a clinical research database and record all the information in the CRF form. The format of the database will correspond as much as possible to that of the CRF table to facilitate the input process.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-08-18 09:52:36