ChiCTR2500095999 版本V1.0 版本创建时间2025/01/16 09:10:14 中国临床试验注册中心

审核状态:

Project audit state:

通过审核

Successful

注册号:

Registration number:

ChiCTR2500095999 

最近更新日期:

Date of Last Refreshed on:

2025-01-16 09:10:06 

注册时间:

Date of Registration:

2025-01-16 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

人工智能(AI)辅助的膳食营养管理协同血糖控制的研究

Public title:

Artificial intelligence (AI) -assisted dietary nutrition management on the control of blood glucose

注册题目简写:

English Acronym:

研究课题的正式科学名称:

人工智能(AI)辅助的膳食营养管理软件协同临床开展血糖控制的转化研究

Scientific title:

Translational study of Artificial intelligence (AI) -assisted dietary nutrition management software on blood glucose control

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:

曾平 

研究负责人:

曾平 

Applicant:

Ping Zeng 

Study leader:

Ping Zeng 

申请注册联系人电话:

Applicant telephone:

+86 136 9301 3293

研究负责人电话:

Study leader's telephone:

+86 136 9301 3293

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:

pzeng2000@163.com

研究负责人电子邮件:

Study leader's E-mail:

pzeng2000@163.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:

北京市东城区东单大华路1号

研究负责人通讯地址:

北京市东城区东单大华路1号

Applicant address:

No. 1, Dongdan Dahua Road, Dongcheng District, Beijing

Study leader's address:

No. 1, Dongdan Dahua Road, Dongcheng District, Beijing

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:

北京医院

Applicant's institution:

Beijing Hospital

研究负责人所在单位:

北京医院

Affiliation of the Leader:

Beijing 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:

2024BJYYEC-KY153-02

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:

北京医院伦理委员会

Name of the ethic committee:

Ethics Committee of Beijing Hospital

伦理委员会批准日期:

Date of approved by ethic committee:

2024-10-21 00:00:00

伦理委员会联系人:

秦梓淋

Contact Name of the ethic committee:

Zilin Qin

伦理委员会联系地址:

北京市东城区东单大华路1号

Contact Address of the ethic committee:

No. 1, Dongdan Dahua Road, Dongcheng District, Beijing

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 10 8513 8105

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:

北京医院

Primary sponsor:

Beijing Hospital

研究实施负责(组长)单位地址:

北京市东城区东单大华路1号

Primary sponsor's address:

No. 1, Dongdan Dahua Road, Dongcheng District, Beijing

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

北京

市(区县):

Country:

China

Province:

Beijing

City:

单位(医院):

北京医院

具体地址:

北京市东城区东单大华路1号

Institution
hospital:

Beijing Hospital

Address:

No. 1, Dongdan Dahua Road, Dongcheng District, Beijing

经费或物资来源:

北京医院经费、合作单位匹配经费

Source(s) of funding:

Funds from Beijing Hospital and matching funds from cooperative units

Target disease:

Diabetes mellitus

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:

不健康膳食(过量、结构不合理等)是全球各地引发慢病特别是糖尿病负担的最大风险因素,诸多证据表明膳食干预可有效协助血糖控制,减少并发症发生。而临床营养实践中存在的技术力量薄弱、流程欠优化等问题,限制了膳食干预证据在糖尿病管理中的有效应用。人工智能技术(AI)为普及膳食知识,实施膳食营养管理,满足患者膳食个性化、多样化、结构合理的需求提供了方便和可能。 然而,目前临床医生和患者对膳食干预的重要性认识不足,研究证据多聚焦于某一个点,不能形成有针对性的干预措施。随着人工智能(artificial intelligence, AI)技术的快速发展和广泛应用,膳食干预证据协同临床治疗对慢病进行有效的干预和管理成为可能和必然。例如,通过调整膳食结构,使用人工智能进行个性化膳食推荐,可以协助预防和管理糖尿病、高血压等慢性疾病。此外,根据患者的个体化特征,利用人工智能可帮助医生为患者提供更为精确的膳食建议,从而改善治疗效果。 本研究拟将开发的人工智能辅助的膳食营养管理软件(简称AI)转化应用于临床,以新发生或血糖控制不佳、60岁及以上这一糖尿病高发群体为主要对象,通过24周的随机对照试验,研究“医护+AI”、“单独AI”、“自主管理”三种膳食管理模式对控制血糖、减少用药的协同作用;调查使用AI的满意度、依从性;分析健康膳食行为养成状况,回答AI辅助的膳食管理是否有效、如何更为有效地协助临床控制疾病等问题,为临床营养的筛、评、诊、治的流程优化以及跟踪服务提供AI技术支撑,也为推广应用提供证据。  

Objectives of Study:

Unhealthy diet (excessive, irrational structure, etc.) is the biggest risk factor for chronic diseases around the world, especially diabetes. Many evidences show that dietary intervention can effectively help control blood sugar and reduce complications. However, there are some problems in clinical nutrition practice, such as weak technical force and poor process optimization, which limit the effective application of dietary intervention evidence in diabetes management. Artificial intelligence technology (AI) provides convenience and possibility for popularizing dietary knowledge, implementing dietary nutrition management, and meeting the personalized, diversified, and structurally reasonable needs of patients' diets. However, currently clinical doctors and patients have insufficient understanding of the importance of dietary intervention, and research evidence mostly focuses on a single point, which cannot form targeted intervention measures. With the rapid development and widespread application of artificial intelligence (AI) technology, dietary intervention evidence combined with clinical treatment has become possible and inevitable for effective intervention and management of chronic diseases. For example, by adjusting the dietary structure and using artificial intelligence to make personalized dietary recommendations, we can help prevent and manage chronic diseases such as diabetes and hypertension. In addition, based on the individualized characteristics of patients, the use of artificial intelligence can help doctors provide more accurate dietary recommendations for patients, thereby improving treatment outcomes. This study plans to transform the developed AI assisted dietary nutrition management software (AI for short) into clinical applications. With the newly developed or poorly controlled population with high incidence of diabetes, 60 years old and over, as the main object, through a 24 week randomized controlled trial, this study will study the synergistic effect of the three dietary management modes of "medical care+AI", "individual AI" and "independent management" on blood glucose control and drug use reduction; Survey satisfaction and compliance with the use of AI; Analyze the status of healthy dietary behavior development, answer questions about whether AI assisted dietary management is effective and how to more effectively assist in clinical disease control, provide AI technology support for the optimization of clinical nutrition screening, evaluation, diagnosis, and treatment processes and tracking services, and also provide evidence for promotion and application.

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)年龄45~75岁; (2)经临床诊断为2型糖尿病,新发或既往血糖控制不佳,糖化血红蛋白水平>7.0%; (3)接受生活方式干预,能配合研究随访,且大部分时间在家就餐者; (4)能够自主选择餐食和独立进餐。

Inclusion criteria

(1) Age 45~75 years old; (2) Clinically diagnosed with type 2 diabetes mellitus, new onset or previous poor glycemic control, glycosylated hemoglobin level >7.0%; (3) Those who received lifestyle interventions, could cooperate with the study follow-up, and ate at home most of the time; (4) Be able to choose meals and eat independently.

排除标准:

(1)终末期肿瘤及生命周期小于1年; (2)经临床诊断为患有痴呆症或其他认知障碍疾病; (3)BMI大于30kg/m^2; (4)有胃肠道手术史或胃肠道功能受损病史; (5)不能配合研究实施,如存在吞咽功能障碍或进食困难等。

Exclusion criteria:

(1) End-stage tumors and life cycle less than 1 year; (2) Clinically diagnosed with dementia or other cognitive impairment diseases; (3) BMI greater than 30kg/m^2; (4) History of gastrointestinal surgery or impaired gastrointestinal function; (5) Unable to cooperate with the implementation of the study, such as swallowing dysfunction or difficulty eating.

研究实施时间:

Study execute time:

From 2025-02-10 00:00:00 To 2026-06-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-02-10 00:00:00 To 2026-02-09 00:00:00  

干预措施:

Interventions:

组别:

试验组1

样本量:

144

Group:

Test group 1

Sample size:

干预措施:

采用“医护+AI”管理模式,受试者自动接收膳食食谱,由医护人员负责监督管理膳食方案执行情况并提醒和协助录入信息

干预措施代码:

Intervention:

The "medical workers + AI" management model will be adopted. Subjects will automatically receive dietary recipes. Medical staff are responsible for supervising and managing the implementation of the dietary plan and reminding and assisting in entering information

Intervention code:

组别:

试验组2

样本量:

144

Group:

Test group 2

Sample size:

干预措施:

采用“单独AI”管理模式,受试者自动接收膳食食谱,由研究人员在后台进行监管、提醒和协助录入信息

干预措施代码:

Intervention:

The "single AI" management model will be adopted. Subjects will automatically receive dietary recipes. Researchers will supervise, remind, and assist in entering information in the computer background

Intervention code:

组别:

对照组

样本量:

144

Group:

Control group

Sample size:

干预措施:

接受健康宣教,对照组采用膳食“自主管理”模式

干预措施代码:

Intervention:

The control group will receive health education, and adopt a dietary "self-management" model

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

北京 

市(区县):

 

Country:

China 

Province:

Beijing 

City:

 

单位(医院):

北京医院 

单位级别:

三甲 

Institution
hospital:

Beijing Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

湖南 

市(区县):

 

Country:

China 

Province:

Hunan 

City:

 

单位(医院):

湘雅医院 

单位级别:

三甲 

Institution
hospital:

Xiangya Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

重庆 

市(区县):

 

Country:

China 

Province:

Chongqing 

City:

 

单位(医院):

重庆人民医院 

单位级别:

三甲 

Institution
hospital:

People's Hospital of Chongqing

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

糖化血红蛋白

指标类型:

主要指标

Outcome:

Glycated Hemoglobin

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

空腹血糖

指标类型:

次要指标

Outcome:

Fasting blood-glucose

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

餐后两小时血糖

指标类型:

次要指标

Outcome:

Postprandial Blood Glucose

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血脂

指标类型:

次要指标

Outcome:

Blood fat

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

血压

指标类型:

次要指标

Outcome:

Blood pressure

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

C肽

指标类型:

次要指标

Outcome:

C peptide

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

胰岛素

指标类型:

次要指标

Outcome:

Insulin

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

体重

指标类型:

次要指标

Outcome:

Weight

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

腰围

指标类型:

次要指标

Outcome:

Waist circumference

Type:

Secondary 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:

血液

组织:

Sample Name:

Blood

Tissue:

人体标本去向

使用后保存  

说明

Fate of sample:

Preservation 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 60 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):

按照年龄、体重、病程和患病状况进行分层,用SAS程序(proc plan,每block=9)产生分层随机序列。分层的方法为年龄< 75岁,或>=75岁;体重 BMI<27kg/m^2, 或BMI >=27kg/m^2;糖尿病新发或糖化>= 6.5%

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

SAS program (proc plan, block=9) will be used to generate a stratified random sequence. Stratification methods are defined as age<75 years old or >= 75 years old, BMI<27kg/m^2 or BMI>= 27kg/m^2, and diabetes new onset or HbA1C >= 6.5%

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:

人体指标测量人员以及统计分析人员设为被盲对象。干预持续时间为24周。

Blinding:

Physical and body measurement personnel and statistical analysts are designated as blind subjects.

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

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)用户自行在小程序上进行填写记录。(2)家人代为记录,通过绑定家人的形式,由家人代为在小程序上进行记录。(3)医护、营养指导员协助记录,营养指导员可在营养指导员端口协助用户进行记录。(4)后台补录,后台管理人员可在后台为指定人群进行记录的补录。

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

(1) Users can fill out records on the mini program themselves. (2) Family members are responsible for recording on the mini program by binding family members. (3) Medical workers and nutrition instructors assist in recording, and nutrition instructors can assist users in recording through the nutrition instructor port. (4) Backend supplementary recording, backend management personnel can record supplementary recording for designated groups in the backend.

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:

 2025-01-16 09:10:06