ChiCTR2500102985 版本V1.0 版本创建时间2025/05/22 15:20:23 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:

ChiCTR2500102985 

最近更新日期:

Date of Last Refreshed on:

2025-05-22 15:20:03 

注册时间:

Date of Registration:

2025-05-22 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

115(审核员标注请勿删除:1.请上传伦理通过版本且有版本号标注的研究方案(201911);2.研究方案中未提及纳排标准、样本量、指标,请注册者核对,如有修改请联系伦理委员会;≥≤这类格式统一改为>=?<=;3.检查修改研究实施地点的名称填写格式;4.指标的中英文不要缩写;)基于AI Agent的数智化工作流促进基层医生COPD的筛查和随访管理

Public title:

AI Agent-Driven Digital Workflow for Enhancing COPD Screening and Follow-Up Management in Primary Care

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于AI Agent的数智化工作流促进基层医生COPD的筛查和随访管理

Scientific title:

AI Agent-Driven Digital Workflow for Enhancing COPD Screening and Follow-Up Management in Primary Care

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:

曾美怡 

研究负责人:

徐东 

Applicant:

Meiyi Zeng 

Study leader:

Dong Xu 

申请注册联系人电话:

Applicant telephone:

+86 136 9232 2071

研究负责人电话:

Study leader's
telephone:

+86 139 1098 8979

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:

2901294775@qq.com

研究负责人电子邮件:

Study leader's E-mail:

roman.xu@gmail.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:

中国广东省广州市沙太南路1023号

研究负责人通讯地址:

中国广东省广州市沙太南路1023号

Applicant address:

1023 Shatai Road South, Baiyun District, Guangzhou, Guangdong, China

Study leader's address:

1023 Shatai Road South, 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

Applicant's institution:

Southern Medical University

研究负责人所在单位:

南方医科大学

Affiliation of the Leader:

Southern 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:

南医伦审[2025]第29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:

南方医科大学生物医学伦理委员会

Name of the ethic committee:

Biomedical Ethics Committee of Southern Medical University

伦理委员会批准日期:

Date of approved by ethic committee:

2025-04-30 00:00:00

伦理委员会联系人:

马俊

Contact Name of the ethic committee:

Jun Ma

伦理委员会联系地址:

广东省广州市沙太南路1023-1063号南方医科大学行政楼215

Contact Address of the ethic committee:

Room 215, Administration Building, Southern Medical University, No. 1023-1063, Shatai South Road, Guangzhou City, Guangdong Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 20 6164 7452

伦理委员会联系人邮箱:

Contact email of the ethic committee:

majun11@smu.edu.cn

研究实施负责(组长)单位:

南方医科大学

Primary sponsor:

Southern Medical University

研究实施负责(组长)单位地址:

中国广东省广州市沙太南路1023号

Primary sponsor's address:

1023 Shatai Road South, Baiyun District, Guangzhou, Guangdong, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

广东

市(区县):

广州

Country:

China

Province:

Guangdong

City:

Guangzhou

单位(医院):

南方医科大学

具体地址:

中国广东省广州市沙太南路1023号

Institution
hospital:

Southern Medical University

Address:

1023 Shatai Road South, Baiyun District, Guangzhou, Guangdong, China

经费或物资来源:

瑞士发展与合作署

Source(s) of funding:

Swiss Agency for Development and Cooperation

研究疾病:

慢性阻塞性肺疾病  

Target disease:

Chronic Obstructive Pulmonary Disease

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:

探索性研究/预试验 

Study phase:

0

研究设计:

整群随机分组 

Study design:

Cluster randomization 

研究目的:

本研究旨在通过构建基于AI Agent的数智化工作流,整合远程筛查、智能决策支持和动态随访管理,解决中国基层COPD筛查率低、诊疗不规范及随访缺失等核心问题。采用“设计马拉松”多方共建模式优化工具适配性,并通过整群随机对照试验验证其降低急性加重率、提升筛查覆盖率及改善患者生活质量的效果,同时评估卫生经济学效益,为基层慢病管理数字化转型及政策推广提供循证依据。  

Objectives of Study:

This study aims to solve the core problems of low COPD screening rate, unstandardized diagnosis and treatment, and lack of follow-up at the grassroots level in China by constructing an AI agent-based digital workflow that integrates remote screening, intelligent decision support, and dynamic follow-up management. A "design marathon" model was adopted to optimize the adaptability of the tool, and a cluster randomized controlled trial was conducted to validate its effectiveness in reducing acute exacerbation rate, increasing screening coverage, and improving patients' quality of life, as well as evaluating the health economic benefits, which will provide evidence-based evidence for the digital transformation of grassroots chronic disease management and the promotion of the policy.

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. 对于基层医疗机构,纳入标准为:(1)机构类型,经卫生健康行政部门认证的社区卫生服务中心或乡镇卫生院;(2)服务资质,具备COPD慢性病规范化管理资质,并纳入国家基本公共卫生服务项目考核体系;(3)数据基础:具备电子健康档案系统,且近3年慢性病管理数据完整率≥70%; 2. 对于基层医生,纳入标准为:(1)执业资质,持有全科医生、公卫医师或护士执业证书,且在岗从事慢性病管理工作≥1年;(2)服务范围,直接参与COPD患者的随访、评估或健康指导;(3)语言能力:能够使用普通话跟研究者沟通,并且能用当地方言于当地人进行有效沟通; 3. 对于患者,纳入标准为:(1)诊断明确:符合《中国慢性阻塞性肺疾病基层诊疗与管理指南(2024年)》诊断标准。(2)管理连续性:在样本机构接受规范管理≥6个月,并纳入国家基本公卫服务系统;(3)沟通能力:具备基本交流能力。

Inclusion criteria

1. For primary health care institutions, the inclusion criteria are: (1) type of institution, community health service center or township health center certified by the health and wellness administrative department; (2) service qualification, qualified for standardized management of chronic diseases in COPD and included in the assessment system of the national basic public health service program; (3) data base: with an electronic health record system and the completeness of chronic disease management data in the past three years ≥70%; 2. For primary care physicians, the inclusion criteria were: (1) practice qualification, holding a license to practice as a general practitioner, public health physician, or nurse, and having been on the job for ≥1 year in the management of chronic diseases; (2) scope of service, directly involved in the follow-up, assessment, or health guidance of COPD patients; (3) language ability: able to communicate with the researcher in Putonghua, and able to communicate effectively with the local people in their local dialect; 3. For patients, the inclusion criteria were: (1) clear diagnosis: meeting the diagnostic criteria of the Chinese Guidelines for Primary Diagnosis, Treatment and Management of Chronic Obstructive Pulmonary Disease (2024). (2) Management continuity: receiving standardized management in the sample institution for ≥6 months and being included in the national basic public health service system; (3) Communication skills: having basic communication skills.

排除标准:

1. 对于基层医疗机构,排除标准为:(1)近6个月内参与过类似数智化干预研究;(2)正在实施其他慢性病管理模式改革试点; 2. 对于基层医生,排除标准为:(1)同时参与其他可能干扰研究结果的培训或项目;(2)近3年因慢性病管理质量问题被行政部门通报批评。(3)计划在未来6个月内离职或长期休假(>3个月); 3. 对于患者,排除标准为:(1)认知障碍:确诊阿尔茨海默病、血管性痴呆或其他影响沟通的神经系统疾病;(2) 参与冲突:同期加入其他慢性病干预研究项目。(3) 迁移计划:未来12个月内可能迁出本管理辖区。

Exclusion criteria:

1. For primary care providers, the exclusion criteria were: (1) participation in a similar Numerical Intelligence Intervention Study in the last 6 months; (2) ongoing implementation of other chronic disease management model reform pilots; 2. For primary care physicians, the exclusion criteria are: (1) concurrently participating in other training or programs that may interfere with the study results; (2) having been criticized by the administration in the past 3 years for quality of chronic disease management. (3) planning to leave their jobs or go on long-term leave (>3 months) within the next 6 months; 3. For patients, the exclusion criteria were: (1) Cognitive impairment: confirmed diagnosis of Alzheimer's disease, vascular dementia, or other neurological disorders affecting communication; (2) Participation in conflict: enrollment in other chronic disease intervention research programs during the same period. (3) Migration plan: potential to move out of this administrative jurisdiction within the next 12 months.

研究实施时间:

Study execute time:

From 2025-06-01 00:00:00 To 2027-07-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-06-01 00:00:00 To 2026-04-30 00:00:00

干预措施:

Interventions:

组别:

干预组

样本量:

840

Group:

Intervention Group

Sample size:

干预措施:

慢性阻塞性肺疾病(COPD)患者接受新开发的AI赋能工作流管理

干预措施代码:

Intervention:

Chronic Obstructive Pulmonary Disease (COPD) Patients Managed with Newly Developed AI-Enabled Workflow

Intervention code:

组别:

对照组

样本量:

840

Group:

Control Group

Sample size:

干预措施:

慢性阻塞性肺疾病(COPD)患者接受常规方法管理

干预措施代码:

Intervention:

Chronic Obstructive Pulmonary Disease (COPD) Patients Managed with Conventional Methods

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

广东 

市(区县):

深圳 

Country:

China

Province:

Guangdong

City:

Shenzhen

单位(医院):

龙岗中心医院龙西社区健康服务中心 

单位级别:

社区卫生服务中心 

Institution
hospital:

Longgang Central Hospital Longxi Community Health Service Center

Level of the institution:

Community Health Service Center

国家:

中国

省(直辖市):

云南 

市(区县):

兴义 

Country:

China

Province:

Yunnan

City:

Xingyi

单位(医院):

保山市基层医疗卫生机构 

单位级别:

社区卫生服务中心 

Institution
hospital:

Basic medical and health institutions in Baoshan City

Level of the institution:

Community Health Service Center

国家:

中国

省(直辖市):

四川 

市(区县):

龙泉驿 

Country:

China

Province:

Sichuan

City:

Longquanyi

单位(医院):

龙泉驿区基层医疗卫生机构 

单位级别:

社区卫生服务中心 

Institution
hospital:

Primary health care institutions in Longquanyi District

Level of the institution:

Community Health Service Center

测量指标:

Outcomes:

指标中文名:

慢阻肺病患者规范健康服务率

指标类型:

主要指标

Outcome:

Standardized health service rate for patients with chronic lung disease

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

急性加重率

指标类型:

主要指标

Outcome:

Acute Exacerbation Rate

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

30岁及以上人群COPD知晓率

指标类型:

次要指标

Outcome:

Awareness Rate of COPD in Population Aged 30 and Above

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

COPD患者规范治疗率

指标类型:

次要指标

Outcome:

Standardized Treatment Rate of COPD Patients

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

COPD药物治疗率

指标类型:

次要指标

Outcome:

Medication Treatment Rate of COPD

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

COPD患者健康管理率

指标类型:

次要指标

Outcome:

Health Management Rate of COPD Patients

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

COPD治疗干预率

指标类型:

次要指标

Outcome:

Therapeutic Intervention Rate of COPD

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:

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 100 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):

本研究采用分层区组随机化方法,由统计团队通过SAS 9.4软件的PROC PLAN模块生成随机序列(种子数=20241101)。根据城市资源水平(深圳、兴义、保山)和机构服务负荷(年慢病管理量≥500例为高负荷,<500例为低负荷)将24家基层医疗机构划分为6个层级,每层内4家机构通过区组随机法分配至4个干预批次(每批6家),形成阶梯推进模式(基线期3个月+4个干预期,每期3个月)。

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

This study employed a stratified block randomization method, with statisticians generating random sequences using the PROC PLAN module in SAS 9.4 software (seed number=20241101). Based on urban resource levels (Shenzhen, Xingyi, Baoshan) and institutional service load (annual chronic disease management volume ≥500 cases classified as high-load, <500 as low-load), 24 primary healthcare institutions were stratified into 6 tiers. Within each tier, 4 institutions were allocated to 4 intervention batches (6 institutions per batch) through block randomization, forming a stepwise implementation model (3-month baseline period + 4 intervention phases, each lasting 3 months).

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:

由于阶梯楔形设计的动态性,参与机构及医护人员无法设盲,但通过标准化数据录入和同步指标采集减少实施偏倚。主要结局(如COPD早期检出率)由中央数据团队匿名处理,隐藏机构ID和时间标记,确保结果评估者盲态分析;统计团队在初步分析完成后揭盲,避免分析偏倚。

Blinding:

Due to the dynamic nature of the stepped-wedge design, blinding of participating institutions and healthcare professionals was not feasible. However, implementation bias was minimized through standardized data entry and synchronous indicator collection. Primary outcomes (e.g., Early Detection Rate) underwent anonymized processing by a central data team, with institution IDs and timestamps concealed to ensure blinded analysis by outcome assessors.

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):

研究数据采集结束后,经过一年的数据保护期,相关研究人员可根据合理需求向通讯作者索取原始数据。

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

After a one-year data protection period at the end of the study data collection, the researchers concerned may request the original data from the corresponding authors according to their reasonable needs.

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:

本试验采用电子采集和管理系统(EDC),所有数据通过项目开发的工作流系统及红帽系统(REDCap)采集和管理。REDCap是免费且功能强大的数据采集、储存和管理的云工具。

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

This trial utilized an electronic data capture and management system (EDC). All data were collected and managed through the workflow system developed for the project and the Research Electronic Data Capture (REDCap) system. REDCap is a free yet powerful cloud-based tool for data collection, storage, and management.

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:

 2025-05-22 15:20:03