基于多维度信息融合的机器学习模型预测放射性肺炎的回顾性和前瞻性应用研究

注册号:

Registration number:

ChiCTR2500102055 

最近更新日期:

Date of Last Refreshed on:

2025-05-08 08:30:24 

注册时间:

Date of Registration:

2025-05-08 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于多维度信息融合的机器学习模型预测放射性肺炎的回顾性和前瞻性应用研究

Public title:

Retrospective and Prospective Application of a Machine Learning Model Integrating Multidimensional Data to Predict Radiation Pneumonitis

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多维度信息融合的机器学习模型预测放射性肺炎的回顾性和前瞻性应用研究

Scientific title:

Retrospective and Prospective Application of a Machine Learning Model Integrating Multidimensional Data to Predict Radiation Pneumonitis

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:

陈智 

研究负责人:

杨镇洲 

Applicant:

Zhi Chen 

Study leader:

Zhengzhou Yang 

申请注册联系人电话:

Applicant telephone:

+86 189 8292 8222

研究负责人电话:

Study leader's
telephone:

+86 138 8327 0881

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:

2023440076@stu.cqmu.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

2023440076@stu.cqmu.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:

重庆市南岸区天文大道288号

研究负责人通讯地址:

重庆市南岸区天文大道288号

Applicant address:

No. 288 Tianwen Road, Nan’an District, 400000, Chongqing, China

Study leader's address:

No. 288 Tianwen Road, Nan’an District, 400000, Chongqing, China

申请注册联系人邮政编码:

Applicant postcode:

610100

研究负责人邮政编码:

Study leader's postcode:

610100

申请人所在单位:

重庆医科大学附属第二医院

Applicant's institution:

The Second Affiliated Hospital of Chongqing Medical University

研究负责人所在单位:

重庆医科大学附属第二医院

Affiliation of the Leader:

The Second Affiliated Hospital of Chongqing Medical 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:

科[2024]393

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:

重庆医科大学附属第二医院伦理委员会

Name of the ethic committee:

the Institutional Ethics Committee, Second Affiliated Hospital of Chongqing Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2024-12-17 00:00:00

伦理委员会联系人:

方雄鹰

Contact Name of the ethic committee:

Xiongying Fang

伦理委员会联系地址:

重庆市南岸区天文大道288号

Contact Address of the ethic committee:

No. 288 Tianwen Road, Nan’an District, 400000, Chongqing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 23 6288 8436

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:

重庆医科大学附属第二医院

Primary sponsor:

The Second Affiliated Hospital of Chongqing Medical University

研究实施负责(组长)单位地址:

重庆市南岸区天文大道288号

Primary sponsor's address:

No. 288 Tianwen Road, Nan’an District

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

重庆

市(区县):

Country:

China

Province:

Chongqing

City:

单位(医院):

重庆医科大学附属第二医院

具体地址:

重庆市南岸区天文大道288号

Institution
hospital:

The Second Affiliated Hospital of Chongqing Medical University

Address:

No. 288 Tianwen Road, Nan’an District, 400000, Chongqing, China

经费或物资来源:

重庆医科大学附属第二医院项目经费

Source(s) of funding:

funding for the Second Affiliated Hospital of Chongqing Medical University

研究疾病:

放射性肺炎  

Target disease:

radiation pneumonitis

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:

其它 

Study phase:

N/A

研究设计:

横断面 

Study design:

Cross-sectional 

研究目的:

本研究通过回顾性分析接受胸部放射治疗的原发性肺癌患者数据,构建多维度信息融合的机器学习模型,预测放射性肺炎的风险。随后纳入前瞻性患者数据验证模型,评估其在临床中的预测准确性与应用价值,旨在为个性化放疗方案优化提供支持,减少放射性肺损伤的发生,提高治疗效果。  

Objectives of Study:

In this study, we retrospectively analyzed data from primary lung cancer patients who received thoracic radiotherapy to develop a machine-learning model that integrates multidimensional features for predicting the risk of radiation pneumonitis. We then prospectively enrolled a validation cohort to assess the model’s predictive accuracy and clinical utility. Our aim is to support personalized radiotherapy planning, reduce the incidence of radiation-induced lung injury, and ultimately improve treatment outcomes.

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:

排除标准为: 1.放疗中断一周以上或因其他原因未能完成标准治疗方案。 2.影像学检查资料不完整,或无法进行随访评估者。 3.放疗前已有严重的肺部疾病(如重度COPD、间质性肺病等),影响放射性肺炎的风险评估。 4.受试者撤回知情同意,要求退出; 5.研究者认为其他有必要退出研究的情况;

Exclusion criteria:

Exclusion Criteria 1. Interruption of radiotherapy for more than one week or inability to complete the prescribed radiotherapy course. 2. Incomplete imaging data or inability to perform follow-up assessments. 3. Pre-existing severe pulmonary disease (e.g., severe COPD, interstitial lung disease) that would confound risk assessment for radiation pneumonitis. 4. Participant withdrawal of informed consent. 5. Other circumstances deemed by the investigator to warrant discontinuation from the study.

研究实施时间:

Study execute time:

From 2025-05-12 00:00:00 To 2026-10-28 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-05-12 00:00:00 To 2026-10-28 00:00:00

干预措施:

Interventions:

组别:

回顾性队列

样本量:

500

Group:

Retrospective cohort

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

前瞻性队列

样本量:

100

Group:

Prospective cohort

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):

重庆 

市(区县):

南岸区 

Country:

China

Province:

chongqing

City:

单位(医院):

重庆医科大学附属第二医院 

单位级别:

三甲 

Institution
hospital:

the Second Affiliated Hospital of Chongqing Medical University

Level of the institution:

Tertiary A-level hospital

测量指标:

Outcomes:

指标中文名:

放射性肺炎发生率

指标类型:

主要指标

Outcome:

Incidence rate of radiation pneumonitis

Type:

Primary indicator

测量时间点:

放疗后1个月、3个月、6个月 此后每6个月随访,持续2年

测量方法:

根据CTCAE 5.0标准对症状分级(如咳嗽、气短、发热等)。 影像学评估:CT扫描,识别肺部毛玻璃影或实变影的变化。 诊断依据:结合影像学表现与临床症状,由肿瘤科专家确认。

Measure time point of outcome:

Follow-up visits are scheduled at 1, 3, and 6 months after radiotherapy, and thereafter every 6 months for a total follow-up duration of 2 years.

Measure method:

Symptom grading: Per CTCAE v5.0 (e.g., cough, dyspnea, fever). Imaging assessment: CT scans to detect changes in pulmonary ground-glass opacities or consolidations. Diagnostic criteria: Diagnosis is made by oncology specialists based on the combination of imaging findings and clinical symptoms.

指标中文名:

肿瘤治疗的疗效评估

指标类型:

次要指标

Outcome:

Independent contributions of radiomics, digital pathology, and dosimetric features to the prediction of radiation pneumonitis.

Type:

Secondary indicator

测量时间点:

放疗后1个月、3个月、6个月 此后每6个月随访,持续2年

测量方法:

实体瘤疗效评估标准RECIST v1.1

Measure time point of outcome:

Follow-up visits are scheduled at 1, 3, and 6 months after radiotherapy, and thereafter every 6 months for a total follow-up duration of 2 years.

Measure method:

Tumor response will be assessed according to the Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1.

指标中文名:

疗效评价的结局指标有时间类指标

指标类型:

次要指标

Outcome:

OS,PFS,DFS

Type:

Secondary indicator

测量时间点:

测量方法:

随访

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:

尚未开始

Not yet recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 85 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):

原始数据已做匿名化,仅供本研究使用;相关数据将以文章发表的方式共享。2035年5月后459509409@qq.com

The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url):

The original data have been anonymized and will be used solely for this study. Relevant datasets will be made available upon publication of the article. After May 2035, data requests can be directed to [459509409@qq.com](mailto:459509409@qq.com).

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:

本研究采用统一设计的病例报告表(CRF)收集所有临床、DVH、影像组学和数字病理数据。回顾性队列数据采用纸质CRF,由研究助理抽取后录入医院自主研发的电子数据采集(EDC)系统;前瞻性队列数据则直接在该EDC系统中以电子CRF方式实时录入。系统设置了双录入、范围和逻辑检查,所有数据定期备份,访问权限仅限核心研究人员,确保数据质量与安全。

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

A standard Case Report Form (CRF) was used to collect all clinical, dosimetric (DVH), radiomics, and digital pathology data. - Retrospective cohort data were first abstracted onto paper CRFs by trained research assistants and then entered into the institution’s in-house electronic data capture (EDC) system. - Prospective cohort data were directly entered into the same EDC via web-based eCRFs at each study visit.

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:

 2025-05-08 08:30:07