基于高危人群筛查的食管平扫CT人工智能识别技术准确性验证

注册号:

Registration number:

ChiCTR2600127047 

最近更新日期:

Date of Last Refreshed on:

2026-06-23 15:30:14 

注册时间:

Date of Registration:

2026-06-23 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于高危人群筛查的食管平扫CT人工智能识别技术准确性验证

Public title:

Accuracy Validation of an Artificial Intelligence Recognition Technique on Non-contrast Esophageal CT in High-Risk Population Screening

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于高危人群筛查的食管平扫CT人工智能识别技术准确性验证

Scientific title:

Accuracy Validation of an Artificial Intelligence Recognition Technique on Non-contrast Esophageal CT in High-Risk Population Screening

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:

张宁 

研究负责人:

曹凯 

Applicant:

Ning Zhang 

Study leader:

Kai Cao 

申请注册联系人电话:

Applicant telephone:

+86 153 8773 4237

研究负责人电话:

Study leader's
telephone:

+86 185 0211 3743

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:

2474508226@qq.com

研究负责人电子邮件:

Study leader's E-mail:

mdkaicao163@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:

上海杨浦区长海路168号

研究负责人通讯地址:

上海杨浦区长海路168号

Applicant address:

168 Changhai Road, Yangpu District, Shanghai, China

Study leader's address:

168 Changhai Road, Yangpu District, Shanghai, China

申请注册联系人邮政编码:

Applicant postcode:

200433

研究负责人邮政编码:

Study leader's postcode:

200433

申请人所在单位:

上海长海医院

Applicant's institution:

Shanghai Changhai Hospital

研究负责人所在单位:

上海长海医院

Affiliation of the Leader:

Shanghai Changhai 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:

CHEC2026-178

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:

上海长海医院医学伦理委员会

Name of the ethic committee:

Shanghai Changhai Hospital Medical Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2026-05-18 00:00:00

伦理委员会联系人:

张优琴

Contact Name of the ethic committee:

Youqin Zhang

伦理委员会联系地址:

上海杨浦区长海路168号

Contact Address of the ethic committee:

168 Changhai Road, Yangpu District, Shanghai, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 139 1835 5518

伦理委员会联系人邮箱:

Contact email of the ethic committee:

changhaiec@126.com

研究实施负责(组长)单位:

上海长海医院

Primary sponsor:

Shanghai Changhai Hospital

研究实施负责(组长)单位地址:

上海杨浦区长海路168号

Primary sponsor's address:

168 Changhai Road, Yangpu District, Shanghai, 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):

上海

市(区县):

杨浦区

Country:

China

Province:

Shanghai

City:

Yangpu District

单位(医院):

上海长海医院

具体地址:

上海杨浦区长海路168号

Institution
hospital:

Shanghai Changhai Hospital

Address:

168 Changhai Road, Yangpu District, Shanghai, China

经费或物资来源:

国家自然科学基金(82372045)、上海科学自然基金(23ZR1478400)、海军军医大学第一附属医院重点培育项目(2024XB001)

Source(s) of funding:

National Natural Science Foundation of China (82372045), Shanghai Natural Science Foundation (23ZR1478400), and Key Cultivation Project of the First Affiliated Hospital of Naval Medical University (2024XB001).

研究疾病:

食管癌  

Target disease:

Esophageal 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:

探索性研究/预试验 

Study phase:

0

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

主要目的:验证“基于胸部平扫CT联合人工智能的食管癌检测大模型”对于大规模真实世界人群的诊断准确性,评估其在真实世界机会性筛查中的阳性预测值(PPV)。 次要目的:在食管癌发病率低的中风险医院就诊人群中实现食管癌机会性发现,并探究该模型能否发现临床漏诊的食管癌。  

Objectives of Study:

Primary objective: To validate the diagnostic accuracy of a large model for esophageal cancer detection based on non‑contrast chest CT combined with artificial intelligence in a large real‑world population, and to evaluate its positive predictive value (PPV) in real‑world opportunistic screening. Secondary objective: To achieve opportunistic detection of esophageal cancer in a hospital‑visiting population with a low incidence of esophageal cancer (i.e., intermediate‑risk hospitals), and to investigate whether the model can identify clinically missed esophageal cancers.

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. 没有覆盖完整食管的胸部CT检查; 2. 扫描不规范的检查(如双手放在身体两边或上腹部、呼吸运动伪影大、灌注污染等); 3. 心脏支架等其他金属伪影存在可能影响的; 4. 影响或改变食管解剖显示的胸/腹手术/治疗操作的患者(食管/胃/心脏/血管/ERCP术后等); 5. 具有明确食管癌或胃癌病史及其治疗后复查的患者; 6.上消化道穿孔者,大量腹水、严重腹胀,或有重度食管静脉曲张者;妊娠期妇女。

Exclusion criteria:

1.Chest CT examinations that do not cover the entire esophagus; 2.Non‑standard scans (e.g., hands placed on both sides of the body or over the upper abdomen, large respiratory motion artifacts, perfusion contamination, etc.); 3.Presence of other metal artifacts (e.g., from cardiac stents) that may potentially affect interpretation; 4.Patients with prior thoracic/abdominal surgery or therapeutic procedures that alter or change the anatomical appearance of the esophagus (e.g., post‑esophageal/gastric/cardiac/vascular/ERCP procedures, etc.); 5.Patients with a definite history of esophageal or gastric cancer or those undergoing post‑treatment follow‑up; 6.Patients with upper gastrointestinal perforation, massive ascites, severe abdominal distension, or severe esophageal varices; Pregnant women.

研究实施时间:

Study execute time:

From 2026-05-20 00:00:00 To 2027-05-18 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-09-01 00:00:00 To 2027-05-18 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):

金标准:上消化道内镜;手术或活检病理; 对于因各种原因无法获取金标准者,以随访观察期内电话随访无"胸骨后疼痛、吞咽困难”等症状作为研究的参考标准。

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):

Upper gastrointestinal endoscopy; surgical or biopsy pathology For those in whom the gold standard could not be obtained for various reasons, the absence of symptoms such as retrosternal pain and dysphagia during telephone follow-up within the observation period was used as the reference standard for the study.

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):

基于胸部平扫 CT 的“食管恶性病变”人工智能辅助检测模型————EAGLE(Esophageal AI-Guided malignant Lesion Evaluation)

Index test:

Artificial intelligence‑assisted detection model for malignant esophageal lesions based on non‑contrast chest CT — EAGLE (Esophageal AI‑Guided malignant Lesion Evaluation)

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)

于医院就诊并进行了胸部平扫CT检查者。

例数:

Sample size:

41000

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 who visited the hospital and underwent a non‑contrast chest CT examination

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:

non

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

四川省 

市(区县):

成都市 

Country:

China

Province:

Sichuan

City:

Chengdu

单位(医院):

四川省肿瘤医院 

单位级别:

三甲 

Institution
hospital:

Sichuan Cancer Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

四川省 

市(区县):

遂宁市 

Country:

China

Province:

Sichuan

City:

Suining

单位(医院):

遂宁市中心医院 

单位级别:

三甲 

Institution
hospital:

Suining Central Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

上海 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

上海长海医院 

单位级别:

三甲 

Institution
hospital:

Shanghai Changhai Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

灵敏度

指标类型:

主要指标

Outcome:

sensitivity

Type:

Primary 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:

主要指标

Outcome:

specificity

Type:

Primary 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:

主要指标

Outcome:

Positive Predictive Value

Type:

Primary 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:

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:

正在进行

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):

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

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):

non

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:

各医疗机构的PACS系统、电子病历系统、随访;病历记录表

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

PACS systems, electronic medical record systems, follow-up, and medical record forms of various medical institutions.

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:

 2026-06-23 15:29:58