胰腺癌基于多模态的基因突变深度学习模型研究

注册号:

Registration number:

ChiCTR2600125371 

最近更新日期:

Date of Last Refreshed on:

2026-06-03 09:47:26 

注册时间:

Date of Registration:

2026-05-26 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

胰腺癌基于多模态的基因突变深度学习模型研究

Public title:

Research on a Multimodal-Based Deep Learning Model for Gene Mutation Prediction in Pancreatic Cancer

注册题目简写:

English Acronym:

研究课题的正式科学名称:

胰腺癌基于多模态的基因突变深度学习模型研究

Scientific title:

Research on a Multimodal-Based Deep Learning Model for Gene Mutation Prediction in Pancreatic Cancer

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:

朱春斌 

研究负责人:

虞先濬 

Applicant:

Chunbin Zhu 

Study leader:

Xianjun Yu 

申请注册联系人电话:

Applicant telephone:

+86 180 1704 6384

研究负责人电话:

Study leader's
telephone:

+86 183 0166 9875

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:

zhuchunbin@fudanpci.org

研究负责人电子邮件:

Study leader's E-mail:

yuxianjun@fudanpci.org

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:

上海市东安路270号

研究负责人通讯地址:

上海市东安路270号

Applicant address:

No. 270 Dong'an Road, Shanghai

Study leader's address:

No. 270 Dong'an Road, Shanghai

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:

复旦大学附属肿瘤医院

Applicant's institution:

Fudan University Shanghai Cancer Center

研究负责人所在单位:

复旦大学附属肿瘤医院

Affiliation of the Leader:

Fudan University Shanghai Cancer Center

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:

2510-Exp312

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:

复旦大学附属肿瘤医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Fudan University Shanghai Cancer Center

伦理委员会批准日期:

Date of approved by ethic committee:

2025-11-17 00:00:00

伦理委员会联系人:

张玮静

Contact Name of the ethic committee:

Weijing Zhang

伦理委员会联系地址:

上海市东安路270号

Contact Address of the ethic committee:

No. 270 Dong'an Road, Shanghai

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 21 3477 8299

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:

复旦大学附属肿瘤医院

Primary sponsor:

Fudan University Shanghai Cancer Center

研究实施负责(组长)单位地址:

上海市东安路270号

Primary sponsor's address:

No. 270 Dong'an Road, Shanghai

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):

Country:

China

Province:

Shanghai

City:

单位(医院):

复旦大学附属肿瘤医院

具体地址:

上海市东安路270号

Institution
hospital:

Department of Pancreatic Surgery

Address:

No. 270 Dong'an Road, Shanghai

经费或物资来源:

自筹

Source(s) of funding:

Self-funded

研究疾病:

胰腺癌  

Target disease:

pancreatic 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:

验证基于多模态数据的基因突变深度学习模型的预测性能  

Objectives of Study:

Validation of the Predictive Performance of the Multimodal Data-Based Deep Learning Model for Gene Mutation Prediction

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.伴有其它系统恶性肿瘤; 2.非初发胰腺癌患者; 3.病理证实为非胰腺腺癌患者; 4.患者没有术前一个月内增强CT的患者。

Exclusion criteria:

1. Patients with other systemic malignancies; 2. Non-primary pancreatic cancer patients; 3. Patients with pathology-confirmed non-pancreatic adenocarcinoma; 4. Patients lacking contrast-enhanced CT scans within one month prior to surgery.

研究实施时间:

Study execute time:

From 2026-06-01 00:00:00 To 2029-07-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-06-02 00:00:00 To 2029-06-01 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):

基因突变检测

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):

Gene mutation detection

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):

基于多模态的基因突变深度学习模型

Index test:

Deep Learning Model for Gene Mutation Based on Multimodality

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)

胰腺癌患者

例数:

Sample size:

400

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):

Pancreatic cancer patients

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):

上海 

市(区县):

 

Country:

China

Province:

Shanghai

City:

单位(医院):

复旦大学附属肿瘤医院 

单位级别:

三甲 

Institution
hospital:

Fudan University Shanghai Cancer Center

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

准确性

指标类型:

主要指标

Outcome:

Accuracy

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

敏感度

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:

指标中文名:

阴性预测值

指标类型:

主要指标

Outcome:

Negative Predictive Value

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

受试者工作特征曲线下面积

指标类型:

主要指标

Outcome:

Area Under the Receiver Operating Characteristic Curve

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:

肿瘤组织

组织:

Sample Name:

tumor sample

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 18 years
最大 Max age 80 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):

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:

1)病例记录表(CRF) CRF 将依据研究方案设计,涵盖所有关键信息,包括人口学资料、临床诊断、治疗、CTC 检测数据、随访记录及不良事件等。CRF 由研究中心经培训的研究人员根据原始医疗记录和检查报告,及时、准确、清晰地填写。CRF 的所有记录需由负责研究人员签字并注明日期,以确保可追溯性和责任明确。CRF 的任何修改需遵循规定流程,记录修改原因并签字确认。 2)本研究数据使用电子EDC 系统进行数据的采集和管理。原始数据由研究中心指定接受过数据录入培训的人员进行录入。数据进入EDC 后,数据管理人员和医学人员定期审核数据,审核过程中发现逻辑或医学上的潜在问题可通过EDC发送人工质疑。质疑包括EDC 逻辑核查产生的系统质疑和临床监查员、数据管理人员等角色发起的人工质疑。录入员需根据数据管理计划中规定的时限及时回复质疑/更新数据(如需)。如质疑为系统质疑,更新后的数据符合逻辑后将自动关闭;如不符合逻辑,数据管理人员将审核质疑回复内容,并决定关闭质疑或重启质疑。如质疑为人工质疑,数据管理人员、临床监查员等质疑发起人将分别审核本角色发起的质疑,并决定关闭质疑或重启质疑。重启质疑需要录入员再次回复/更新数据,相关角色需要再次审核质疑回复/数据更新,直至质疑所述问题解决。

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

1)The CRF will be designed in accordance with the study protocol, covering all key information including demographic data, clinical diagnosis, treatment details, CTC detection data, follow-up records, and adverse events. The CRF will be completed timely, accurately, and clearly by trained researchers at the study center based on original medical records and examination reports. All entries in the CRF must be signed and dated by the responsible researcher to ensure traceability and clear accountability. Any amendments to the CRF shall follow specified procedures, with the reasons for modification documented and confirmed by signature. 2)In this study, data will be collected and managed using an electronic EDC system. Original data will be entered by personnel designated by the study center who have received training on data entry. After data is entered into the EDC system, data managers and medical personnel will review the data regularly. During the review process, potential logical or medical issues identified can be raised as manual queries via the EDC system. Queries include system-generated queries from EDC logical checks and manual queries initiated by roles such as clinical monitors and data managers. Data entry personnel must respond to queries and update data (if necessary) within the time frame specified in the data management plan. For system-generated queries, the query will be automatically closed once the updated data meets logical requirements; if the data remains illogical, data managers will review the query response and decide whether to close or reinitiate the query. For manual queries, the initiators (such as data managers and clinical monitors) will review the queries initiated by their respective roles and decide whether to close or reinitiate them. Reinitiating a query requires data entry personnel to respond or update data again, and relevant roles must re-review the query response or data update until the issue stated in the query is resolved.

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:

 2026-05-26 11:15:25