|
审核状态: Project audit state: |
通过审核 Successful |
|
注册号: Registration number: |
ChiCTR2600116492 |
|
最近更新日期: Date of Last Refreshed on: |
2026-01-12 08:43:35 |
|
注册时间: Date of Registration: |
2026-01-12 00:00:00 |
|
注册号状态: |
预注册 |
|
Registration Status: |
Prospective registration |
|
注册题目: |
基于人工智能算法融合多模态数据构建不良妊娠结局的预测模型 |
|
Public title: |
Developing an AI-based predictive model for adverse pregnancy outcomes by integrating multimodal data |
|
注册题目简写: |
|
|
English Acronym: |
|
|
研究课题的正式科学名称: |
基于人工智能算法融合多模态数据构建不良妊娠结局的预测模型 |
|
Scientific title: |
Developing an AI-based predictive model for adverse pregnancy outcomes by integrating 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: |
刘玉东 |
研究负责人: |
石玉华 |
|
Applicant: |
Liu Yudong |
Study leader: |
Shi Yuhua |
|
申请注册联系人电话: Applicant telephone: |
+86 13570532321 |
研究负责人电话: Study leader's telephone: |
+86 20 62786842 |
|
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: |
liuyd9@163.com |
研究负责人电子邮件: Study leader's E-mail: |
shiyuhua2003@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: |
中国广东省广州市白云区广州大道北1838号 |
研究负责人通讯地址: |
中国广东省广州市白云区广州大道北1838号 |
|
Applicant address: |
No. 1838, Guangzhou Avenue North, Baiyun District, Guangzhou, Guangdong, China |
Study leader's address: |
No. 1838, Guangzhou Avenue North, Baiyun District, Guangzhou, Guangdong, China |
|
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: |
南方医科大学南方医院 |
||
|
Applicant's institution: |
Nanfang Hospital, Southern Medical University |
||
|
研究负责人所在单位: |
南方医科大学南方医院 |
||
|
Affiliation of the Leader: |
Southern Medical University Southern Hospital |
||
|
是否获伦理委员会批准: |
是/Yes |
||
|
Approved by ethic committee: |
Yes |
||
|
伦理委员会批件文号: Approved No. of ethic committee: |
NFEC-2025-062 |
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: |
南方医科大学南方医院医学伦理委员会 |
||
|
Name of the ethic committee: |
Medical Ethics Committee of Nanfang Hospital |
||
|
伦理委员会批准日期: Date of approved by ethic committee: |
2025-02-19 00:00:00 |
||
|
伦理委员会联系人: |
胡兴媛 |
||
|
Contact Name of the ethic committee: |
Hu Xingyuan |
||
|
伦理委员会联系地址: |
中国广东省广州市白云区广州大道北1838号 |
||
|
Contact Address of the ethic committee: |
No. 1838, Guangzhou Avenue North, Baiyun District, Guangzhou, Guangdong, China |
||
|
伦理委员会联系人电话: Contact phone of the ethic committee: |
+86 20 62787238 |
伦理委员会联系人邮箱: Contact email of the ethic committee: |
nfyyec@163.com |
|
研究实施负责(组长)单位: |
南方医科大学南方医院 |
||||||||||||||||||||||
|
Primary sponsor: |
Southern Medical University Southern Hospital |
||||||||||||||||||||||
|
研究实施负责(组长)单位地址: |
中国广东省广州市白云区广州大道北1838号 |
||||||||||||||||||||||
|
Primary sponsor's address: |
No. 1838, Guangzhou Avenue North, Baiyun District, Guangzhou, Guangdong, China |
||||||||||||||||||||||
|
试验主办单位(项目批准或申办者): Secondary sponsor: |
|
||||||||||||||||||||||
|
经费或物资来源: |
生殖健康及重大出生缺陷防控研究 |
||||||||||||||||||||||
|
Source(s) of funding: |
National Key Research and Development Program |
||||||||||||||||||||||
|
Target disease: |
Uterine structural injuries |
||||||||||||||||||||||
|
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: |
队列研究 |
||||||||||||||||||||||
|
Study design: |
Cohort study |
||||||||||||||||||||||
|
研究目的: |
主要目的:基于人工智能算法,融合临床、影像等多区域、多中心多模态数据,针对不同子宫结构损伤建立双向队列,运用 XGBoost 集成学习和多模态深度学习算法,围绕自然妊娠和辅助生殖构建覆盖孕前、孕期及围产期的不良妊娠结局多阶段 AI 预测模型。 次要目的:开发GPT大模型,将成为基于多中心多模态数据的不良妊娠结局预测的重要突破,具有很大的科学和临床价值。 |
||||||||||||||||||||||
|
Objectives of Study: |
Primary Objective:To establish bidirectional cohorts based on different uterine structural injuries by integrating multi-regional, multi-center multimodal data (including clinical and imaging data) using artificial intelligence algorithms. Leveraging XGBoost ensemble learning and multimodal deep learning algorithms, the aim is to develop a multi?stage AI prediction model for adverse pregnancy outcomes, covering the pre?pregnancy, pregnancy, and perinatal periods, with applicability to both natural conception and assisted reproductive technology.Secondary Objective:To develop GPT?based large language models, which will represent a significant breakthrough in predicting adverse pregnancy outcomes based on multi?center multimodal data, offering substantial scientific and clinical value. |
||||||||||||||||||||||
|
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.自愿签署知情同意书; |
||||||||||||||||||||||
|
Inclusion criteria |
1.Voluntarily sign the informed consent form. 2.Age>=18; 3.Gender: Female; 4.Diagnosis via medical history: scarred uterus (post-cesarean section, post-myomectomy or adenomyomectomy, or post-uterine rupture repair), post-cervical conization, or post-induced abortion. Or diagnosis via hysteroscopy: intrauterine adhesions. 5.Planning pregnancy or currently pregnant. |
||||||||||||||||||||||
|
排除标准: |
1.患有精神疾病,无法配合随访; |
||||||||||||||||||||||
|
Exclusion criteria: |
1.Diagnosed with a psychiatric disorder and unable to comply with follow-up. |
||||||||||||||||||||||
|
研究实施时间: Study execute time: |
从 From 2024-12-01 00:00:00至 To 2027-11-30 00:00:00 |
征募观察对象时间: Recruiting time: |
从From 2026-01-13 00:00:00 至 To 2026-12-31 00:00:00 |
|
干预措施: Interventions: |
|
|
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: |
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): |
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 |
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): |
无 |
|
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: |
通过提取入组受试者常规临床诊疗记录、孕前以及孕期血清学指标、超声影像学、遗传学、辅助生殖治疗(如有)数据获取研究数据。要求研究者在整个监测期间根据患者病历信息填写研究的电子病例报告表(eCRF)。 数据管理 1数据管理 1) 研究者必需保证数据真实、完整、准确; 2) 研究记录做任何更正时只能划线,旁注改后的数据,说明理由,由研究者签名并注明日期,不得擦涂、覆盖原记录; 3) 实验室检查项目齐全。 2. 数据记录与文件保存 病例报告表上有关受试者数据应以受试者编码方式记录,受试者只能通过受试者编码或其姓名首字母缩写识别。 本研究采用专业的数据管理系统进行数据管理。数据录入采用双人双机录入方式,录入完成后进行一致性比对,确保数据录入准确。源数据核查由专门的核查人员定期进行,对数据的完整性、准确性和逻辑性进行检查。对于质控数据的质疑,由数据管理员及时与研究者沟通,解答疑问并记录处理过程。数据锁定需经过项目负责人、数据管理员和统计人员共同确认,签署数据库锁定申请表后,由数据管理员对数据库进行锁定。数据库锁定后,由数据管理员导出分析数据库,交统计人员进行统计分析。锁定后的数据不可再编辑,数据库锁定之后发现的问题,经确认后可在统计分析程序中修正。再编辑,数据库锁定之后发现的问题,经确认后可在统计分析程序中修正。 |
|
Data collection and Management (A standard data collection and management system include a CRF and an electronic data capture: |
1. Principles of Data ManagementInvestigators must ensure the authenticity, completeness, and accuracy of the data.Any corrections to research records must be made by drawing a single line through the original entry, annotating the corrected data nearby, stating the reason for the change, and signing and dating the correction by the investigator. Erasures or overwriting of original records are prohibited.Laboratory test items must be complete.2. Data Recording and Document PreservationSubject data on the Case Report Form (CRF) shall be recorded using a subject identification code. Subjects can only be identified by this code or their initials.This study will employ a professional data management system. Data entry will be performed using a dual independent entry method by two personnel using separate devices, followed by consistency checks to ensure accuracy. Source Data Verification (SDV) will be conducted regularly by dedicated monitors to check for data completeness, accuracy, and logical consistency. Any data queries identified during quality control will be promptly communicated by the data manager to the investigator for resolution, with the entire process documented.Database locking requires joint confirmation from the project lead, data manager, and statistician. Following the signing of a Database Lock Request Form, the data manager will execute the database lock. After locking, the data manager will export the analysis dataset for statistical analysis by the statistician. Once locked, the database cannot be edited. Any issues discovered post-lock, upon confirmation, may be addressed through corrections within the statistical analysis program. |
|
数据与安全监察委员会: Data and Safety Monitoring Committee: |
有/Yes |