ChiCTR2600120511 版本V1.0 版本创建时间2026/03/16 14:51:49 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:

ChiCTR2600120511 

最近更新日期:

Date of Last Refreshed on:

2026-03-16 14:51:42 

注册时间:

Date of Registration:

2026-03-16 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于多模态数据的子宫内膜癌智能诊断模型研究

Public title:

Development and Validation of an Intelligent Diagnostic Model for Endometrial Cancer Based on Multimodal Data

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态数据的子宫内膜癌智能诊断模型研究

Scientific title:

Development and Validation of an Intelligent Diagnostic Model for Endometrial Cancer Based on Multimodal Data

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:

彭怡馨 

研究负责人:

张蕾 

Applicant:

Yixin Peng 

Study leader:

Lei Zhang 

申请注册联系人电话:

Applicant telephone:

+86 139 0385 0116

研究负责人电话:

Study leader's
telephone:

+86 186 0113 0459

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:

13903850116@163.com

研究负责人电子邮件:

Study leader's E-mail:

18601130459@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:

北京市昌平区立汤路168号

研究负责人通讯地址:

北京市昌平区立汤路168号

Applicant address:

No. 168, Litang Road, Changping District, Beijing

Study leader's address:

No. 168, Litang Road, Changping District, Beijing

申请注册联系人邮政编码:

Applicant postcode:

102218

研究负责人邮政编码:

Study leader's postcode:

102218

申请人所在单位:

北京清华长庚医院

Applicant's institution:

Beijing Tsinghua Changgung Hospital

研究负责人所在单位:

北京清华长庚医院

Affiliation of the Leader:

Beijing Tsinghua Changgung Hospital

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:

26125-4-01

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:

北京清华长庚医院医学伦理委员会

Name of the ethic committee:

Beijing Tsinghua Changgung Hospital Medical Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2026-02-04 00:00:00

伦理委员会联系人:

刘曼婷

Contact Name of the ethic committee:

Manting Liu

伦理委员会联系地址:

北京市昌平区立汤路168号

Contact Address of the ethic committee:

No. 168, Litang Road, Changping District, Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 5611 8567

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:

北京清华长庚医院

Primary sponsor:

Beijing Tsinghua Changgung Hospital

研究实施负责(组长)单位地址:

北京市昌平区立汤路168号

Primary sponsor's address:

No. 168, Litang Road, Changping District, Beijing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

北京

市(区县):

昌平

Country:

China

Province:

Beijing

City:

Changping

单位(医院):

北京清华长庚医院

具体地址:

北京市昌平区立汤路168号

Institution
hospital:

Beijing Tsinghua Changgung Hospital

Address:

No. 168, Litang Road, Changping District, Beijing

经费或物资来源:

本研究未获得任何机构、组织或企业的专项经费或物资资助。

Source(s) of funding:

This study received no specific financial or material support from any institution, organization, or company.

研究疾病:

子宫内膜癌  

Target disease:

Endometrial Cancer

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:

回顾性研究 

Study phase:

Retrospective study

研究设计:

连续入组 

Study design:

Sequential 

研究目的:

本研究旨在构建基于多模态数据的子宫内膜癌智能筛查模型,通过建立多模态数据库,构建细胞学诊断模型实现自动判读,建立高危人群筛查模型提升筛查效能。  

Objectives of Study:

This study aims to construct an intelligent screening model for endometrial cancer based on multimodal data. By establishing a multimodal database, a cytological diagnosis model will be built to achieve automatic interpretation, and a high-risk population screening model will be established to improve screening 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:

(1)符合高危人群或风险增加人群标准: 根据2020年发布的《子宫内膜癌筛查规范建议》,至少有以下一种情况的患者被认为是高危人群或风险增加人群: a.肥胖,体重指数(BMI)≥30kg/m2; b.多囊卵巢综合征(PCOS); c.无孕激素拮抗的雌激素使用者; d.绝经年龄晚(>55岁); e.无生育史或原发性不孕症; f.长期服用他莫昔芬(特别是50岁以上或绝经后继续服用他莫昔芬的患者); g.年龄≥45岁,患有糖尿病; h.Lynch综合征患者;三级亲属患有Lynch综合征,但未进行相关基因检测的;有结肠癌或结肠癌家族史者。 (2)接受子宫内膜细胞学检查,且留存有质量合格、染色完整的细胞学玻片; (3)具备明确的病理诊断结果,可作为细胞学判读的金标准; (4)子宫内膜细胞学取样与组织学取样时间间隔≤14天,期间未接受任何可能影响内膜状态的干预。

Inclusion criteria

1. Patients meeting the criteria for high-risk or increased-risk populations: According to the 2020 Recommendations for Endometrial Cancer Screening, patients are considered to be at high risk or increased risk if they have at least one of the following conditions: (1)Obesity, defined as body mass index (BMI) >=30 kg/m2; (2)Polycystic ovary syndrome (PCOS); (3)Use of estrogen without progestin opposition; (4)Late menopause (>55 years); (5)Nulliparity or primary infertility; (6)Long-term tamoxifen use, especially in patients older than 50 years or those who continue tamoxifen after menopause; (7)Age>= 45 years with diabetes mellitus; (8)Lynch syndrome; having a first-degree relative with Lynch syndrome without relevant genetic testing; or a personal or family history of colorectal cancer. 2.Underwent endometrial cytology examination, with retained cytology slides of qualified quality and complete staining; 3. Had a definite histopathological diagnosis that could serve as the gold standard for cytological interpretation; 4. The interval between endometrial cytology sampling and histological sampling was <=14 days, and no intervention that might affect the endometrial status was performed during this period.

排除标准:

(1)细胞学样本质量不合格,包括但不限于以下情形: a.玻片缺乏明确标记或严重破损无法修复; b.细胞严重重叠、血液或炎细胞覆盖腺细胞、标本固定不良或过度干燥; c.污染或其他因素导致≥75%的腺细胞无法判读; (2)细胞学与病理学取样时间间隔>14天,或期间存在可能干扰子宫内膜状态的因素(如宫腔操作、激素或内分泌治疗、放疗、化疗、靶向治疗等); (3)临床、超声信息不完整; (4)研究者认为不适合纳入本研究的其他情况。

Exclusion criteria:

1. Unqualified cytology samples, including but not limited to the following conditions: (1)Slides lacking clear identification labels or being severely damaged and irreparable; (2)Severe cell overlap, glandular cells obscured by blood or inflammatory cells, poor fixation, or excessive drying of the specimen; (3)Contamination or other factors resulting in >=75% of glandular cells being uninterpretable; 2.An interval of more than 14 days between cytological and histopathological sampling, or the presence of factors during this period that might interfere with the endometrial status, such as intrauterine procedures, hormonal or endocrine therapy, radiotherapy, chemotherapy, or targeted therapy; 3. Incomplete clinical or ultrasound information; 4. Any other conditions deemed unsuitable for inclusion in this study by the investigators.

研究实施时间:

Study execute time:

From 2026-04-01 00:00:00 To 2027-05-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-04-01 00:00:00 To 2027-05-01 00:00:00

干预措施:

Interventions:

组别:

观察组

样本量:

300

Group:

Observation 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):

北京市 

市(区县):

 

Country:

China

Province:

Beijing

City:

单位(医院):

北京清华长庚医院 

单位级别:

三级 

Institution
hospital:

Beijing Tsinghua Changgung Hospital

Level of the institution:

Tertiary

测量指标:

Outcomes:

指标中文名:

多模态智能诊断模型诊断子宫内膜癌的曲线下面积(AUC)

指标类型:

主要指标

Outcome:

Area under the receiver operating characteristic curve (AUC) of the multimodal intelligent diagnostic model for endometrial cancer

Type:

Primary indicator

测量时间点:

模型构建完成后,于独立测试集验证时评估

测量方法:

基于独立测试集,以病理诊断结果为金标准,计算多模态模型诊断子宫内膜癌的ROC曲线下面积(AUC)。

Measure time point of outcome:

At the time of model validation on the independent test set after model development

Measure method:

Using histopathological diagnosis as the reference standard, the area under the receiver operating characteristic curve (AUC) of the multimodal model for detecting endometrial cancer will be calculated on the independent test set.

指标中文名:

细胞学智能诊断模型诊断子宫内膜癌的曲线下面积(AUC)

指标类型:

主要指标

Outcome:

Area under the receiver operating characteristic curve (AUC) of the cytology-based intelligent diagnostic model for endometrial cancer

Type:

Primary indicator

测量时间点:

模型构建完成后,于独立测试集验证时评估

测量方法:

基于独立测试集,以细胞学专家判读结果为金标准,计算细胞学智能诊断模型诊断子宫内膜癌的ROC曲线下面积(AUC)。

Measure time point of outcome:

At the time of model validation on the independent test set after model development

Measure method:

Using expert cytological interpretation as the reference standard, the AUC of the cytology-based intelligent diagnostic model for detecting endometrial cancer will be calculated on the independent test set.

指标中文名:

多模态智能诊断模型的敏感度和特异度

指标类型:

次要指标

Outcome:

Sensitivity and specificity of the multimodal intelligent diagnostic model

Type:

Secondary indicator

测量时间点:

模型构建完成后,于独立测试集验证时评估

测量方法:

以病理诊断结果为金标准,在独立测试集中计算模型的敏感度和特异度。

Measure time point of outcome:

At the time of model validation on the independent test set after model development

Measure method:

Using histopathological diagnosis as the reference standard, sensitivity and specificity of the multimodal model will be calculated on the independent test set.

指标中文名:

模型判读与细胞学专家判读的一致性

指标类型:

次要指标

Outcome:

Agreement between model-based interpretation and expert cytological interpretation

Type:

Secondary indicator

测量时间点:

模型构建完成后,于独立测试集验证时评估

测量方法:

采用Kappa统计量评估模型判读结果与细胞学专家判读结果之间的一致性。

Measure time point of outcome:

At the time of model validation on the independent test set after model development

Measure method:

Agreement between model predictions and expert cytological interpretation will be assessed using the kappa statistic.

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:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 45 years
最大 Max age years

性别:

女性

Gender:

Female

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:

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:

本研究数据采集和管理包括病例报告表(Case Report Form, CRF)和电子数据管理。研究数据来源于医院既往病历系统、影像资料、子宫内膜细胞学玻片及病理诊断结果。研究者按照统一纳入与排除标准进行病例筛选和信息提取,采用标准化CRF收集临床资料、超声信息、细胞学及病理结果。所有研究数据在录入前进行去标识化处理,并由专人进行数据核对、清洗和质量控制。电子数据采用权限分级管理,仅授权研究成员可访问,数据存储于院内受控环境中,以确保数据安全性、完整性和可追溯性。

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

Data collection and management in this study include case report forms (CRFs) and electronic data management. Study data are derived from existing hospital medical records, imaging data, endometrial cytology slides, and histopathological results. Eligible cases will be identified according to predefined inclusion and exclusion criteria, and relevant information will be extracted using standardized CRFs, including clinical characteristics, ultrasound findings, cytological results, and pathological diagnoses. All data will be de-identified before entry, and data verification, cleaning, and quality control will be performed by designated study personnel. Electronic data will be managed under role-based access control, and stored in a secure institutional environment to ensure data security, integrity, and traceability.

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:

 2026-03-16 14:51:42