基于XG Boost算法与随机森林的胃癌患者术前衰弱风险预测模型的构建及其对比研究

注册号:

Registration number:

ChiCTR2600121634 

最近更新日期:

Date of Last Refreshed on:

2026-04-01 14:32:51 

注册时间:

Date of Registration:

2026-04-01 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于XG Boost算法与随机森林的胃癌患者术前衰弱风险预测模型的构建及其对比研究

Public title:

Construction and Comparative study of preoperative frailty risk Prediction Model for gastric cancer patients based on XG Boost Algorithm and Random Forest

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于XG Boost算法与随机森林的胃癌患者术前衰弱风险预测模型的构建及其对比研究

Scientific title:

Construction and Comparative study of preoperative frailty risk Prediction Model for gastric cancer patients based on XG Boost Algorithm and Random Forest

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:

张晓洁 

研究负责人:

张晓洁 

Applicant:

Xiaojie Zhang 

Study leader:

Xiaojie Zhang 

申请注册联系人电话:

Applicant telephone:

+86 571 8600 6951

研究负责人电话:

Study leader's
telephone:

+86 571 8600 6951

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:

zhangxiaojie@srrsh.com

研究负责人电子邮件:

Study leader's E-mail:

zhangxiaojie@srrsh.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:

浙江省杭州市上城区庆春东路3号

研究负责人通讯地址:

浙江省杭州市上城区庆春东路3号

Applicant address:

No.3 Qingchun East Road Hangzhou City Zhejiang Province

Study leader's address:

No.3 Qingchun East Road Hangzhou City Zhejiang 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:

浙江大学医学院附属邵逸夫医院

Applicant's institution:

Sir Run Run Shaw Hospital,Zhejiang University School of Medicine

研究负责人所在单位:

浙江大学医学院附属邵逸夫医院

Affiliation of the Leader:

Sir Run Run Shaw Hospital, School of Medicine, Zhejiang 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:

邵逸夫医院伦审2025研第0930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:

浙江大学医学院附属邵逸夫医院医学伦理委员会

Name of the ethic committee:

Ethics Committee,Sir Run Run Shaw Hospital,Zhejiang University School of Medicine

伦理委员会批准日期:

Date of approved by ethic committee:

2025-11-27 00:00:00

伦理委员会联系人:

杨漾池

Contact Name of the ethic committee:

Yang YangChi

伦理委员会联系地址:

浙江省杭州市上城区庆春东路3号

Contact Address of the ethic committee:

No.3 Qingchun East Road Hangzhou City Zhejiang Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 571 86006811

伦理委员会联系人邮箱:

Contact email of the ethic committee:

yyc261@foxmail.com

研究实施负责(组长)单位:

浙江大学医学院附属邵逸夫医院

Primary sponsor:

Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University

研究实施负责(组长)单位地址:

浙江省杭州市上城区庆春东路3号

Primary sponsor's address:

No.3 Qingchun East Road Hangzhou City Zhejiang 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):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江大学医学院附属邵逸夫医院

具体地址:

浙江省杭州市上城区庆春东路3号

Institution
hospital:

Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University

Address:

No.3 Qingchun East Road Hangzhou City Zhejiang Province

经费或物资来源:

Source(s) of funding:

None

研究疾病:

胃癌术前衰弱  

Target disease:

Preoperative frailty of gastric cancer

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

1. 了解胃癌患者术前衰弱发生特点和现状,并分析相关影响因素,基于XG Boost算法与随机森林两种机器学习算法,构建胃癌患者术前衰弱风险预测模型。 2.验证两种预测模型的预测效能并进行比较,以选择最优模型进行可视化处理。  

Objectives of Study:

1.To understand the characteristics and current situation of preoperative frailty in patients with gastric cancer, and analyze the related influencing factors, a preoperative frailty risk prediction model for patients with gastric cancer was constructed based on two machine learning algorithms, XG Boost algorithm and random forest. 2.Verify the predictive efficacy of the two prediction models and make a comparison to select the optimal model for visualization processing.

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.除老年人/文盲以外的弱势群体,包括精神疾病者、认知损伤者、危重患者、孕妇等;
2.合并心、肺、肝、肾等重要脏器功能不全者;
3.术前发生重大病情变化者;
4.正在参与其他干预性临床试验者;

Exclusion criteria:

1. Vulnerable groups other than the elderly and illiterates, including those with mental illnesses, cognitive impairments, critically ill patients, pregnant women, etc;
2. Those with impaired functions of important organs such as the heart, lungs, liver and kidneys;
3. Those who have experienced significant changes in their condition before the operation;
4. Those who are currently participating in other interventional clinical trials;

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-04-01 00:00:00 To 2026-12-31 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

衰弱表型(Frailty Phenotype, FP)是结合主观自我报告和客观测量的混合性测量工具,涉及5个方面的评估,每个方面满足1条则记1分,总分为0~5分,0分代表无衰弱,1~2分代表衰弱前期,≥3分为衰弱

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

The Frailty Phenotype (FP) is a hybrid measurement tool that combines subjective self-reporting and objective measurement. It involves the assessment of five aspects. One point is scored if each aspect is met, with a total score ranging from 0 to 5. no frailty:0;early stage of frailty:1~2;frailty≥3

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

胃癌患者术前衰弱风险预测模型

Index test:

Predictive Model for Preoperative Frailty Risk in Gastric Cancer Patients

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

年龄>=18周岁且病理学或细胞学诊断为原发性胃癌,入院拟行根治性切除手术且术前未接受放化疗等其他治疗措施的患者

例数:

Sample size:

443

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Patients aged 18 years or above with a pathological or cytological diagnosis of primary gastric cancer, who are admitted to the hospital for radical resection and have not received other treatment measures such as radiotherapy and chemotherapy before the operation

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

例数:

Sample size:

0

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

None

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江大学医学院附属邵逸夫医院 

单位级别:

三级甲等 

Institution
hospital:

Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

衰弱表型

指标类型:

主要指标

Outcome:

Frailty phenotype

Type:

Primary indicator

测量时间点:

术前

测量方法:

使用衰弱表型评估工具,从以下5个方面对患者进行评估,(1)不明原因体重下降:过去1年中,意外出现体重下降>4.5kg或>5.0%体重;(2)疲乏:采用流行病学调查中心抑郁自评量表(the Center for Epidemiologic Studies Depression Scale,CES-D)中的两个问题。条目1:我感觉做每一件事都需要经过努力;条目2:我提不起来劲做事。询问被调查者上述问题

Measure time point of outcome:

pre-operation

Measure method:

Using the frailty phenotype assessment tool, the patients will be evaluated in the following five aspects: (1) Unexplained weight loss: In the past year, unexpected weight loss of more than 4.5 kg or more than 5.0% of body weight occurred; (2) Fatigue: Two questions from the CES-D are used; (3) Low grip strength: The grip strength of the dominant hand is measured twice and the maximum value is taken; (4) Slower walking speed: The time taken to walk 4.57 meters is measured; (5) Low physical activ

指标中文名:

一般资料

指标类型:

次要指标

Outcome:

General Information

Type:

Secondary indicator

测量时间点:

术前

测量方法:

使用自制一般资料调查表,内容包括年龄、性别、体重、文化程度、婚姻状况、收入水平、日常锻炼、睡眠情况、既往史、用药史等相关信息。

Measure time point of outcome:

pre-operation

Measure method:

A self-made general information questionnaire was used, which included relevant information such as age, gender, weight, educational level, marital status, income level, daily exercise, sleep condition, past medical history, and medication history.

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:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 100 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

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:

EDC

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

EDC

数据与安全监察委员会:

Data and Safety Monitoring Committee:

有/Yes

注册人:

Name of Registration:

 2026-04-01 14:32:42