|
注册号: Registration number: |
ChiCTR2400089949 |
|
最近更新日期: Date of Last Refreshed on: |
2024-09-20 09:33:03 |
|
注册时间: Date of Registration: |
2024-09-20 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
NEC识图:AI辅助的X光图像解读 |
|
Public title: |
NEC image recognition: AI assisted interpretation of X-ray images |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
坏死性小肠结肠炎腹部X光平片的深度学习诊断模型 |
|
Scientific title: |
A deep learning diagnostic model for abdominal X-ray plain films of necrotizing enterocolitis |
|
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: |
冯周善 |
研究负责人: |
吴繁 |
|
Applicant: |
Feng Zhoushan |
Study leader: |
Wu Fan |
|
申请注册联系人电话: Applicant telephone: |
+86 18218343184 |
研究负责人电话:
Study leader's |
+86 20 81292251 |
|
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: |
1354920907@qq.com |
研究负责人电子邮件: Study leader's E-mail: |
gdwufan@126.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: |
广东省广州市荔湾区多宝路63号 |
研究负责人通讯地址: |
广州市荔湾区多宝路63号 |
|
Applicant address: |
No. 63 Duobao Road, Liwan District, Guangzhou City, Guangdong Province |
Study leader's address: |
63 Duobao Road, Liwan District, Guangzhou |
|
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: |
广州医科大学附属第三医院 |
||
|
Applicant's institution: |
Third Affiliated Hospital of Guangzhou Medical University |
||
|
研究负责人所在单位: |
广州医科大学附属第三医院 |
||
|
Affiliation of the Leader: |
The Third Affiliated Hospital of Guangzhou Medical University |
||
|
是否获伦理委员会批准: |
是 |
||
|
Approved by ethic committee: |
Yes |
||
|
伦理委员会批件文号: Approved No. of ethic committee: |
临伦审研[2024]第 102 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: |
广州医科大学附属第三医院临床研究与应用伦理委员会 |
||
|
Name of the ethic committee: |
Clinical Research and Application Ethics Committee of the Third Affiliated Hospital of Guangzhou Medical University |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2024-07-17 00:00:00 | ||
|
伦理委员会联系人: |
刘巍 |
||
|
Contact Name of the ethic committee: |
Liu Wei |
||
|
伦理委员会联系地址: |
广州市荔湾区多宝路63号 |
||
|
Contact Address of the ethic committee: |
63 Duobao Road, Liwan District, Guangzhou |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 20 81292726 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
19958348@qq.com |
|
研究实施负责(组长)单位: |
广州医科大学附属第三医院 |
||||||||||||||||||||||
|
Primary sponsor: |
The Third Affiliated Hospital of Guangzhou Medical University |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
广州市荔湾区多宝路63号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
63 Duobao Road, Liwan District, Guangzhou |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
自选课题(自筹) |
||||||||||||||||||||||
|
Source(s) of funding: |
Self selected topic (self funded) |
||||||||||||||||||||||
|
研究疾病: |
NEC 是一种严重的肠道疾病,主要发生在早产儿和出生时体重较轻的婴儿身上。 |
||||||||||||||||||||||
|
Target disease: |
NEC is a serious intestinal condition that mainly occurs in premature babies and those born with low weight. It's linked to poor blood supply and can be triggered by birth asphyxia, blood issues, or certain bacteria. Symptoms include a swollen belly, vomiting, bloody stools, and signs of illness like being slow to move or feed. Diagnosis is done with X-rays and ultrasounds to check for gas in the |
||||||||||||||||||||||
|
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: |
3.1 主要研究目的 提高诊断效率和准确性:开发基于深度学习的自动诊断系统,提升坏死性小肠结肠炎的诊断速度和准确度,以辅助医生,缓解医疗资源紧张。 3.2 次要研究目的 深度学习与传统方法的比较:探索深度学习在数据驱动、自动特征提取和模型复杂性方面与传统方法的不同。 深度学习的优势:强调深度学习在处理大数据、准确性、通用性和端到端学习方面的优势。 模型的可靠性和稳定性评估:确保深度学习模型在不同数据集和环境中的稳定性和可靠性,特别是在临床应用中。 局限性和优化方向分析:识别深度学习在自动诊断中的潜在局限,并提出未来研究和优化的方向。 |
||||||||||||||||||||||
|
Objectives of Study: |
3.1 Main research objectives Improve diagnostic efficiency and accuracy: Develop an automatic diagnostic system based on deep learning to enhance the diagnostic speed and accuracy of necrotizing enterocolitis, to assist doctors and alleviate the shortage of medical resources. 3.2 Secondary Research Objectives Comparison between Deep Learning and Traditional Methods: Exploring the Differences between Deep Learning and Traditional Methods in Data Driven, Automatic Feature Extraction, and Model Complexity. The advantages of deep learning: Emphasize the strengths of deep learning in handling big data, accuracy, generality, and end-to-end learning. Model reliability and stability assessment: Ensure the stability and reliability of deep learning models in different datasets and environments, especially in clinical applications. Limitations and Optimization Direction Analysis: Identify potential limitations of deep learning in automatic diagnosis and propose future research and optimization directions. |
||||||||||||||||||||||
|
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.染色异常的新生儿 (2)有肠道闭锁等畸形的新生儿 (3)其他肠道异常疾病患者 (4)X光检查不清晰; |
||||||||||||||||||||||
|
Exclusion criteria: |
1. Newborns with abnormal staining (2) Newborns with intestinal atresia and other deformities (3) Patients with other intestinal disorders (4) Unclear X-ray examination; |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2024-10-01 00:00:00至 To 2025-09-30 00:00:00 |
征募观察对象时间: Recruiting time: |
从 From 2024-10-01 00:00:00 至 To 2024-10-31 00:00:00 |
|
诊断试验: Diagnostic Tests: |
|
||||||||||||||||||||||||||||
|
研究实施地点: Countries of recruitment and research settings: |
|
||||||||||||||||||||||||||||
|
测量指标: Outcomes: |
|
|
采集人体标本:
Collecting sample(s)
|
|
|
征募研究对象情况: Recruiting status: |
尚未开始 Not yet recruiting |
年龄范围: Participant age: |
|
||||||
|
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): |
无 |
||||||||
|
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: |
无 |
|
Blinding: |
None |
|
是否共享原始数据: IPD sharing |
是Yes |
|
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): |
(1)去隐私处理: ·确保所有数据已经经过脱敏处理,移除任何可能识别个体的信息。 ·确保数据符合相关法律和伦理标准。 (2)数据上传: ·将去隐私处理后的X腹部光片原始数据上传到选择的数据存储平台。 ·提供详细的数据描述和元数据,以便其他研究人员理解和使用这些数据。 ·获取数据集的持久DOI(数字对象标识符)。 (3)代码上传: ·将研究代码上传到选择的代码存储平台。 ·提供详细的代码文档和使用说明,确保其他研究人员可以复现研究结果。 ·获取代码库的持久DOI或URL。 (4)文章提交: ·在提交文章时,注明数据和代码的存储平台,并提供相应的DOI或URL链接。 ·在文章的补充材料或数据可用性声明中详细说明数据和代码的获取方式。 (5)审稿和发布: ·经过同行评审后,文章正式发表。 ·数据和代码链接与文章一起发布,确保读者可以方便地访问和使用这些资源。 |
|
The way of sharing IPD”(include metadata and protocol, If use web-based public database, please provide the url): |
(1) Privacy processing: ·Ensure that all data has been desensitized and any information that may identify individuals has been removed. ·Ensure that the data complies with relevant laws and ethical standards. (2) Data upload: ·Upload the raw data of the X-ray after privacy processing to the selected data storage platform. ·Provide detailed data descriptions and metadata for other researchers to understand and use. ·Retrieve the persistent DOI (Digital Object Identifier) of the dataset. (3) Code upload: ·Upload the research code to the selected code storage platform. ·Provide detailed code documentation and usage instructions to ensure that other researchers can reproduce the research results. ·Retrieve the persistent DOI or URL of the code repository. (4) Article submission: ·When submitting the article, indicate the storage platform for the data and code, and provide the corresponding DOI or URL link. ·Provide detailed instructions on how to obtain data and code in the supplementary materials or data availability statement of the article. (5) Review and Publication: ·After peer review, the article was officially published. ·The data and code links are published together with the article to ensure that readers can easily access and use these resources. |
|
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: |
5.数据管理 5.1数据采集方式 本项目采用电子病历系统(Electronic Medical Record System, EMRS)进行数据采集。并利用专门的数据抽取工具,从EMRS中提取研究所需的患者信息和相关的医疗数据。 5.2数据库访问权限,访问数据库权限分为三个级别: (1)管理员权限:可以访问所有数据,负责维护和管理数据库,处理系统故障。 (2)研究员权限:仅可访问与其研究相关的数据,不能进行数据修改或删除。 (3)数据录入员权限:只能录入和修改数据,不能删除数据。 5.3操作痕迹保留 是的,系统采用了高级的审计跟踪功能,可以跟踪并记录每个用户的所有操作,确保数据的完整性和透明度。 5.4电子病例报告表 (eCRF) 的建立 根据研究方案,我们已经建立了专门的eCRF,用于详细、系统地记录研究数据。 5.5数据管理过程 (1)录入:数据录入员根据原始医疗记录和其他相关文档,录入数据到eCRF中。 (2)锁定:每月数据录入完成后,由项目负责人或数据管理负责人进行数据审核。确保数据准确无误后,数据会被锁定,以防止进一步修改。 (3)导出:数据导出由项目负责人操作,数据将导出为DICOM格式,并且通过文件命名给病人的病情进行标注,以供后续分析。 (4)储存:所有数据存储在加密的、有冗余备份的服务器上。同时,每季度会进行一次完整的数据备份,备份数据保存在安全的物理存储设备中。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
5. Data management 5.1 Data collection method This project uses the Electronic Medical Record System (EMRS) for data collection. And use specialized data extraction tools to extract patient information and related medical data required for the study from EMRS. 5.2 Database access permissions, which are divided into three levels: (1) Administrator privileges: Can access all data, responsible for maintaining and managing databases, and handling system failures. (2) Researcher permissions: Only access to data related to their research is allowed, and data modification or deletion cannot be performed. (3) Data entry personnel permissions: can only enter and modify data, cannot delete data. 5.3 Retention of Operation Traces Yes, the system adopts advanced audit tracking function, which can track and record all operations of each user, ensuring data integrity and transparency. 5.4 Establishment of Electronic Case Report Form (eCRF) According to the research plan, we have established a dedicated eCRF for detailed and systematic recording of research data. 5.5 Data Management Process (1) Input: The data entry personnel input the data into eCRF based on the original medical records and other relevant documents. (2) Locking: After monthly data entry is completed, the project leader or data management manager will conduct data review. After ensuring the accuracy of the data, it will be locked to prevent further modifications. (3) Export: The data export is operated by the project leader. The data will be exported in DICOM format and labeled with the patient's condition through file naming for subsequent analysis. (4) Storage: All data is stored on encrypted servers with redundant backups. At the same time, a complete data backup will be conducted every quarter, and the backup data will be saved in a secure physical storage device. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
有/Yes |