基于多模态AI模型的多囊卵巢综合征数字化营养诊疗与动态监控真实世界研究

注册号:

Registration number:

ChiCTR2600117107 

最近更新日期:

Date of Last Refreshed on:

2026-01-20 09:45:46 

注册时间:

Date of Registration:

2026-01-20 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于多模态AI模型的多囊卵巢综合征数字化营养诊疗与动态监控真实世界研究

Public title:

A Real-World Study of Digital Nutritional Diagnosis, Treatment, and Dynamic Monitoring for Polycystic Ovary Syndrome Based on Multimodal AI Models

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于多模态AI模型的多囊卵巢综合征数字化营养诊疗与动态监控真实世界研究

Scientific title:

A Real-World Study of Digital Nutritional Diagnosis, Treatment, and Dynamic Monitoring for Polycystic Ovary Syndrome Based on Multimodal AI Models

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:

张琚 

研究负责人:

张琚 

Applicant:

Zhang Ju 

Study leader:

Zhang Ju 

申请注册联系人电话:

Applicant telephone:

+86 18908098209

研究负责人电话:

Study leader's
telephone:

+86 28 6597 8146

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:

sunny123sha@qq.com

研究负责人电子邮件:

Study leader's E-mail:

36919151@qq.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:

四川省成都市武侯区沙堰西二街290号

研究负责人通讯地址:

成都市武侯区沙堰西二街290号

Applicant address:

No. 290, Shayan West 2nd Street, Wuhou District, Chengdu, Sichuan Province, China

Study leader's address:

No.290,Shayan West Second Street,Wuhou District,Chengdu

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:

四川省妇幼保健院/四川省妇女儿童医院

Applicant's institution:

Sichuan Provincial Maternity and Child Health Care Hospital/Sichuan Provincial Women’s and Children’

研究负责人所在单位:

四川省妇幼保健院

Affiliation of the Leader:

Sichuan Provincial Maternity and Child Health Care 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:

20260108-068

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:

四川省妇幼保健院医学伦理审查委员会

Name of the ethic committee:

The Medical Ethics Committee of Sichuan Provincial Maternity and Child Health Care Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2026-01-08 00:00:00

伦理委员会联系人:

吴选玲

Contact Name of the ethic committee:

Wu Xuanling

伦理委员会联系地址:

成都市武侯区沙堰西二街290号

Contact Address of the ethic committee:

No.290,Shayan West Second Street,Wuhou District,Chengdu

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 28 65978298

伦理委员会联系人邮箱:

Contact email of the ethic committee:

494483182@qq.com

研究实施负责(组长)单位:

四川省妇幼保健院

Primary sponsor:

Sichuan Provincial Maternity and Child Health Care Hospital

研究实施负责(组长)单位地址:

成都市武侯区沙堰西二街290号

Primary sponsor's address:

No.290,Shayan West Second Street,Wuhou District,Chengdu

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

四川省

市(区县):

Country:

China

Province:

Sichuan

City:

单位(医院):

四川省妇幼保健院

具体地址:

成都市武侯区沙堰西二街290号

Institution
hospital:

Sichuan Provincial Maternity and Child Health Care Hospital

Address:

No.290,Shayan West Second Street,Wuhou District,Chengdu

经费或物资来源:

2025年度成都医学院联合科研基金

Source(s) of funding:

2025 Chengdu Medical College Joint Research Fund

研究疾病:

多囊卵巢综合  

Target disease:

Polycystic Ovary Syndrome (PCOS)

研究疾病代码:

Target disease code:

研究类型:

干预性研究

Study type:

Interventional study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

以开源大模型(如Deepseek)为基础,构建面向PCOS人群的智能干预算法框架,通过融合多模态数据(如生物特征、饮食行为、生理监测、心理评估、药物使用等)实现对关键诊断和干预因素的立体识别与动态管理;借助可解释性AI模型,对不同干预路径的预测效果与机制进行可视化呈现,提升干预透明度与信任度;通过数字化人机交互优化患者体验,提升系统使用黏性与干预依从性;并在此基础上,联合临床医学、营养学、运动科学、运筹学与管理学等专业力量,形成跨学科协同的干预设计机制,推动AI系统在真实情境下的临床验证与长期跟踪,构建持续演化、数据闭环、适应个体差异的智能诊疗与干预新模式。为PCOS女性实现控制体重、优化体脂肌肉、降低代谢风险与改善妊娠结局提供智能化综合解决方案,推动以数据驱动、机制明确、干预智能为特征的精准健康管理模式发展。  

Objectives of Study:

Based on open-source large models (such as Deepseek), an intelligent intervention algorithm framework targeting the PCOS population is constructed. By integrating multimodal data (such as biological characteristics, dietary behaviors, physiological monitoring, psychological assessments, and medication use), it enables three-dimensional identification and dynamic management of key diagnostic and intervention factors. Using interpretable AI models, the predicted effects and mechanisms of different intervention pathways are visualized, enhancing transparency and trust in interventions. Digital human-computer interaction is leveraged to optimize patient experience, increasing system engagement and intervention adherence. On this basis, by combining expertise from clinical medicine, nutrition, exercise science, operations research, and management, a cross-disciplinary collaborative intervention design mechanism is formed. This facilitates clinical validation and long-term follow-up of the AI system in real-world settings, establishing a continuously evolving, data-closed-loop, and individually adaptive intelligent diagnosis and intervention model. The solution provides intelligent, comprehensive support for women with PCOS to manage weight, optimize body fat and muscle, reduce metabolic risk, and improve pregnancy outcomes, promoting the development of a precise health management model characterized by data-driven decision-making, clear mechanisms, and intelligent interventions.

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.有精神类疾病史、无生育意愿和体重管理意愿者,PCOS同时合并心、脑、肾等其他严重疾病的患者。

Exclusion criteria:

1.Individuals with a history of mental disorders, no desire for fertility or weight management, or those with PCOS concurrently complicated by other severe conditions affecting the heart, brain, kidneys, or other major organs.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-02-01 00:00:00 To 2027-12-31 00:00:00

干预措施:

Interventions:

组别:

试验组

样本量:

100

Group:

Experimental group

Sample size:

干预措施:

试验组进入体重管理营养与运动干预随访系统,能获得营养知识获取,互动交流,线上随访监测的全程管理等功能

干预措施代码:

Intervention:

The experimental group will use the Weight Management System for online nutrition education, interactive communication, and follow up monitoring.

Intervention code:

组别:

对照组

样本量:

100

Group:

Control group

Sample size:

干预措施:

对照组实施传统的线下营养与运动干预

干预措施代码:

Intervention:

Participants in the control group will undergo traditional offline nutrition and exercise interventions.

Intervention code:

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):

 

Country:

China

Province:

Sichuan

City:

单位(医院):

四川省妇幼保健院 

单位级别:

三级甲等 

Institution
hospital:

Sichuan Provincial Maternity and Child Health Care Hospital

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

受孕率

指标类型:

主要指标

Outcome:

pregnancy rate

Type:

Primary indicator

测量时间点:

不限制测量时间点

测量方法:

血hCG定量检测;超声检查

Measure time point of outcome:

No limit on the measurement time points

Measure method:

Serum hCG quantitative test; Ultrasonography

指标中文名:

体重管理成功率

指标类型:

主要指标

Outcome:

weight management success rate

Type:

Primary indicator

测量时间点:

分别在体重管理0.5、1、2、3个月

测量方法:

采用人体成分分析仪测量

Measure time point of outcome:

0.5, 1, 2, and 3 months after the intervention begins.

Measure method:

Measured using a body composition analyzer.

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

血液

组织:

Sample Name:

blood

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 49 years

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):

由 SPSS 25.0 生成随机数字表,按照随机数字表将患者分为试验组与对照组

Randomization Procedure (please state who generates the random number sequence and by what method):

A random number table was generated using SPSS 25.0, and patients were randomly allocated to either the experimental group or the control group based on this table.

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:

开放标签

Blinding:

Open-label study

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):

试验结束6个月内上传试验数据到ResMan平台 http://www.medresman.org.cn/login.aspx。

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

Upload the trial data to the ResMan platform within 6 months after the completion of the trial. http://www.medresman.org.cn/login.aspx.

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:

数据由量表及病例采集,由医院电子采集系统管理

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

The data is collected from scales and case reports, and managed through the hospital's electronic data capture system.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-01-20 09:45:30