ChiCTR2500112977 版本V1.1 版本创建时间2025/12/23 15:48:00 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:

ChiCTR2500112977 

最近更新日期:

Date of Last Refreshed on:

2025-11-21 16:53:51 

注册时间:

Date of Registration:

2025-11-21 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

AI辅助决策对医疗质量与效率影响的随机对照试验

Public title:

A Randomized Controlled Trial on the Impact of AI-Assisted Decision-Making on Healthcare Quality and Efficiency

注册题目简写:

English Acronym:

研究课题的正式科学名称:

AI辅助决策对医疗质量与效率影响的随机对照试验

Scientific title:

A Randomized Controlled Trial on the Impact of AI-Assisted Decision-Making on Healthcare Quality and Efficiency

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:

黄琦 

研究负责人:

底骞 

Applicant:

Huang Qi 

Study leader:

Di Qian 

申请注册联系人电话:

Applicant telephone:

+86 134 1900 8583

研究负责人电话:

Study leader's
telephone:

+86 138 1191 1050

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:

hq23@mails.tsinghua.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

qiandi@tsinghua.edu.cn

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:

北京市海淀区双清路30号

研究负责人通讯地址:

北京市海淀区双清路30号

Applicant address:

No. 30 Shuangqing Road, Haidian District, Beijing

Study leader's address:

No. 30 Shuangqing Road, Haidian 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:

清华大学万科公共卫生与健康学院

Applicant's institution:

Vanke School of Public Health, Tsinghua University

研究负责人所在单位:

清华大学万科公共卫生与健康学院

Affiliation of the Leader:

Vanke School of Public Health, Tsinghua 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:

THU-01-2025-1037

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:

清华大学科技伦理委员会

Name of the ethic committee:

Tsinghua University Science and Technology Ethics Committee

伦理委员会批准日期:

Date of approved by ethic committee:

2025-09-17 00:00:00

伦理委员会联系人:

朱艳东

Contact Name of the ethic committee:

Zhu Yandong

伦理委员会联系地址:

清华大学 老环境楼 208

Contact Address of the ethic committee:

Room 208, Lao Huanjing Building, Tsinghua University

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 62781935

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:

清华大学

Primary sponsor:

Tsinghua University

研究实施负责(组长)单位地址:

北京市海淀区双清路30号

Primary sponsor's address:

No. 30 Shuangqing Road, Haidian 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):

清华大学

具体地址:

北京市海淀区双清路30号

Institution
hospital:

Tsinghua University

Address:

No. 30 Shuangqing Road, Haidian District, Beijing

经费或物资来源:

国家自然科学基金

Source(s) of funding:

NSFC

研究疾病:

慢性病  

Target disease:

chronic 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:

其它 

Study phase:

N/A

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

评估在大语言模型的辅助下,能否提高医生的工作效率和工作时间,能否改善医疗服务使用者的健康意识和健康行为  

Objectives of Study:

Evaluate whether the use of large language models can improve doctors' work efficiency and working hours, as well as enhance the health awareness and behavior of healthcare service users

药物成份或治疗方案详述:

 

Description for medicine or protocol of treatment in detail:

 

纳入标准:

医生(轨A) 1.执业医师/规培医师/住院医师/主治及以上; 2.熟练使用电脑/移动端; 3.签署知情同意,允许屏幕与操作日志记录(仅用于研究、脱敏存储)。 体检人群(轨B) 1.30–70岁; 2.近3个月未进行系统体检; 3.具备智能手机使用能力; 4.同意使用研究APP/小程序进行随访问卷; 5.签署知情同意。

Inclusion criteria

Doctor (Track A) 1. Practicing physician/trained physician/resident physician/attending physician or above; 2. Proficient in using computers/mobile devices; 3. Sign informed consent and allow screen and operation log recording (for research and desensitization storage only). Physical examination population (Track B) 1. 30-70 years old; 2. Has not undergone a systematic physical examination in the past three months; 3. Capable of using smartphones; 4. Agree to use the research app/mini program for follow-up questionnaire; 5. Sign informed consent.

排除标准:

医生(轨A) 1.过去3个月深度参与同类AI产品试点; 2.无法完成交叉试验全部任务者; 3.存在严重可能干扰试验的并发因素(如外部任务冲突等)。 体检人群(轨B) 1.既往重大疾病不稳定期; 2.明显认知障碍或无法完成随访; 3.参与可能干扰本研究的其他干预研究。

Exclusion criteria:

Doctor (Track A) 1. In the past three months, I have been deeply involved in piloting similar AI products; 2. Those who are unable to complete all tasks in the cross test; 3. There are serious concurrent factors that may interfere with the experiment, such as external task conflicts. Physical examination population (Track B) 1. Unstable period of major illness in the past; 2. Obvious cognitive impairment or inability to complete follow-up; 3. Participate in other intervention studies that may interfere with this study.

研究实施时间:

Study execute time:

From 2025-12-01 00:00:00 To 2026-12-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-12-01 00:00:00 To 2026-12-01 00:00:00

干预措施:

Interventions:

组别:

医生干预组

样本量:

108

Group:

Doctor intervention group

Sample size:

干预措施:

使用开发的大语言模型工具,在历史的体检报告中,根据体检结果,修订解读报告。不直接干预病人,仅使用既往的病例数据。

干预措施代码:

Intervention:

Using the developed language modeling tool, revise and interpret the medical examination report based on the examination results in the historical medical examination report. Do not directly intervene in patients, only use past case data.

Intervention code:

组别:

体检客户干预组

样本量:

120

Group:

Medical Examination Customer Intervention Group

Sample size:

干预措施:

在原有体检报告的基础上,增加一份由大语言模型辅助下医生审核通过的体检解读报告,后填写问卷。

干预措施代码:

Intervention:

On the basis of the original medical examination report, add a medical examination interpretation report approved by the doctor with the assistance of a big language model, and then fill out the questionnaire.

Intervention code:

组别:

医生对照组

样本量:

108

Group:

Doctor control group

Sample size:

干预措施:

不使用开发的大语言模型工具,利用传统的体检系统,在历史的体检报告中,根据体检结果,修订解读报告。不直接干预病人,仅使用既往的病例数据。

干预措施代码:

Intervention:

Without using developed language modeling tools, traditional medical examination systems are utilized to revise and interpret reports based on examination results in historical medical examination reports. Do not directly intervene in patients, only use past case data.

Intervention code:

组别:

体检客户对照组

样本量:

120

Group:

Medical examination customer control group

Sample size:

干预措施:

仅阅读体检报告,后填写问卷。

干预措施代码:

Intervention:

Read only the physical examination report and then fill out the questionnaire.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

新疆维吾尔自治区 

市(区县):

 

Country:

China

Province:

Xinjiang Uygur Autonomous Region

City:

单位(医院):

新疆维吾尔自治区人民医院 

单位级别:

三甲 

Institution
hospital:

Xinjiang Uygur Autonomous Region People's Hospital

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

江苏 

市(区县):

 

Country:

China

Province:

Jiangsu

City:

单位(医院):

苏州大学附属第一医院 

单位级别:

三甲 

Institution
hospital:

The First Affiliated Hospital of Soochow University

Level of the institution:

Tertiary A

国家:

中国

省(直辖市):

四川 

市(区县):

 

Country:

China

Province:

Sichuan

City:

单位(医院):

西南医科大学附属医院 

单位级别:

三甲 

Institution
hospital:

Affiliated Hospital of Southwest Medical University

Level of the institution:

Tertiary A

国家:

坦桑尼亚

省(直辖市):

Mwanza 

市(区县):

 

Country:

Tanzania

Province:

Mwanza

City:

单位(医院):

Bugando Hospital 

单位级别:

N/A 

Institution
hospital:

Bugando Hospital

Level of the institution:

N/A

国家:

加纳

省(直辖市):

Northern region 

市(区县):

 

Country:

Ghana

Province:

Northern region

City:

单位(医院):

Tamale Teaching Hospital 

单位级别:

N/A 

Institution
hospital:

Tamale Teaching Hospital

Level of the institution:

N/A

国家:

加纳

省(直辖市):

Northern region 

市(区县):

 

Country:

Ghana

Province:

Northern region

City:

单位(医院):

Upper east regional hospital Bolgatanga  

单位级别:

N/A 

Institution
hospital:

Upper east regional hospital Bolgatanga

Level of the institution:

N/A

国家:

坦桑尼亚

省(直辖市):

Dar es Salaam Region 

市(区县):

 

Country:

Tanzania

Province:

Dar es Salaam Region

City:

单位(医院):

Muhimbili Hospital  

单位级别:

N/A 

Institution
hospital:

Muhimbili Hospital

Level of the institution:

N/A

国家:

坦桑尼亚

省(直辖市):

Mjini Magharibi 

市(区县):

 

Country:

Tanzania

Province:

Mjini Magharibi

City:

单位(医院):

Mnazi Mmoja Hospital- Unguja 

单位级别:

N/A 

Institution
hospital:

Mnazi Mmoja Hospital- Unguja

Level of the institution:

N/A

测量指标:

Outcomes:

指标中文名:

医生端测量改每份体检报告的时间

指标类型:

主要指标

Outcome:

The doctor measures the time required to modify each physical examination report

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

医生端测改后的体检报告由高级专家评分

指标类型:

主要指标

Outcome:

The doctor's revised physical examination report will be evaluated by senior experts

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

体检客户端使用量表测量健康意识(HLS SF12)

指标类型:

主要指标

Outcome:

HLS SF12

Type:

Primary 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

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 70 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):

由实验设计人员,使用python软件,实行中心随机。

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

The experimental designers used Python software to implement central randomization.

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:

医生端施行盲法修改报告,高级专家盲法测评

Blinding:

Doctor's blind method modification report, senior expert blind method evaluation

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):

实验完成投稿后,公开相关实验数据,预计时间2026年12月31日,公开方式两种:①为实验室主页申请访问,网址:https://www.ai4healthcare.cn/;②向文章通讯作者发邮件申请数据,通讯作者邮箱:qiandi@tsinghua.edu.cn

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

Following the completion of the experiment and the submission of the manuscript, the associated experimental data will be released to the public on December 31, 2026. Access can be obtained through one of the following two channels: ① Apply for access via the laboratory homepage (https://www.ai4healthcare.cn/); ② Submit a data request via email to the corresponding author of the article: qiandi@tsinghua.edu.cn.

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:

使用数据为既往的电子病例数据,采集与管理由当地医院进行。脱敏后的数据,由清华大学训练模型与测评。

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

The data will be collected and managed by local hospitals based on past electronic medical records. The desensitized data was trained and evaluated by Tsinghua University.

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:

 2025-11-21 16:53:32