针对焦虑的单次暴露疗法干预——大语言模型辅助效果研究

注册号:

Registration number:

ChiCTR2500101784 

最近更新日期:

Date of Last Refreshed on:

2025-04-29 16:43:26 

注册时间:

Date of Registration:

2025-04-29 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

针对焦虑的单次暴露疗法干预——大语言模型辅助效果研究

Public title:

Single-session Exposure Therapy for Anxiety: A Study on the Effectiveness of Large Language Model Assistance

注册题目简写:

English Acronym:

研究课题的正式科学名称:

针对焦虑的单次暴露疗法干预——大语言模型辅助效果研究

Scientific title:

Single-session Exposure Therapy for Anxiety: A Study on the Effectiveness of Large Language Model Assistance

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:

岳燕玲 

研究负责人:

牟文婷 

Applicant:

Yanling Yue 

Study leader:

Wenting Mu 

申请注册联系人电话:

Applicant telephone:

+86 152 8275 8537

研究负责人电话:

Study leader's
telephone:

+86 158 1038 9613

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:

yueyl23@mails.tsinghua.edu.cn

研究负责人电子邮件:

Study leader's E-mail:

yueyl23@mails.tsinghua.edu.cn

申请单位网址(自愿提供):

Applicant website(voluntary supply):

清华大学

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89号A座清华大学红杉公寓

研究负责人通讯地址:

北京市海淀区双清路30号清华大学明斋332

Applicant address:

Tsinghua University Redwood Apartments, Building A, 89 Shuangqing Road, Haidian District, Beijing

Study leader's address:

Room 332, Mingzhai, Tsinghua University, 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:

100084

申请人所在单位:

清华大学

Applicant's institution:

Tsinghua University

研究负责人所在单位:

清华大学

Affiliation of the Leader:

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-04-2025-038

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人文社会与工程委员会

Name of the ethic committee:

Tsinghua University Human, Social, and Engineering Subcommittee of the Science and Technology Ethics Committe

伦理委员会批准日期:

Date of approved by ethic committee:

2025-04-09 00:00:00

伦理委员会联系人:

杨老师

Contact Name of the ethic committee:

Mr. Yang

伦理委员会联系地址:

北京市海淀区清华园1号

Contact Address of the ethic committee:

1 Qinghua Yuan, Haidian District, Beijing, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 62785846

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:

30 Shuangqing Road, Haidian District, Beijing, 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):

北京市

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:

30 Shuangqing Road, Haidian District, Beijing, China

经费或物资来源:

国家自然科学基金,清华大学人才引进基金

Source(s) of funding:

National Natural Science Foundation of China, Tsinghua University Talent Introduction Fund

研究疾病:

焦虑  

Target disease:

Anxiety

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:

治疗新技术临床试验 

Study phase:

New Treatment Measure Clinical Study

研究设计:

随机平行对照 

Study design:

Parallel 

研究目的:

本研究的主要目的是探索和评估训练大语言模型辅助人类开展针对学业焦虑的单次暴露治疗的安全性、满意度和有效性。为了实现这个目标,本课题组将开发一款基于大语言模型的暴露治疗AI,辅助人类咨询师开展对学业焦虑的暴露治疗,通过随机对照试验,验证干预组和等待组被试在接受干预前后各关键指标上的差异以及被试报告的安全性和满意度指标。  

Objectives of Study:

The primary aim of this study is to explore and evaluate the safety, user satisfaction, and efficacy of a large language model (LLM)-assisted single-session exposure therapy for academic anxiety. To achieve this goal, the research team will develop an AI assistant based on a large language model to assist human counselors in delivering exposure-based interventions targeting academic anxiety. A randomized controlled trial will be conducted to examine differences between the intervention group and the waitlist control group on key outcome measures before and after the intervention, as well as to assess participant-reported safety and satisfaction.

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、存在自杀或自伤风险(PHQ-9自杀条目>=2);2、存在重度的抑郁情绪(PHQ-9总分>=20);3、存在酒精滥用风险(AUDIT总分>=10分);4、目前正在或近一个月内曾经接受过心理治疗或精神科药物治疗。

Exclusion criteria:

1. presence of suicide or self-harm risk (suicide item of PHQ-9 >= 2); 2. presence of severe depressive symptoms (total PHQ-9 score >=20); 3. risk of alcohol abuse (total AUDIT score >=10); 4. currently receiving, or having received within the past month, psychological therapy or psychiatric medication treatment.

研究实施时间:

Study execute time:

From 2025-05-08 00:00:00 To 2026-05-12 00:00:00  

征募观察对象时间:

Recruiting time:

From 2025-05-08 00:00:00 To 2025-05-11 00:00:00

干预措施:

Interventions:

组别:

干预组

样本量:

45

Group:

Intervention group and

Sample size:

干预措施:

暴露疗法

干预措施代码:

Intervention:

Exposure Therapy

Intervention code:

组别:

等待组

样本量:

45

Group:

Waitlist control group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

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):

清华大学 

单位级别:

大学 

Institution
hospital:

Tsinghua University

Level of the institution:

University

测量指标:

Outcomes:

指标中文名:

状态焦虑

指标类型:

主要指标

Outcome:

Anxiety

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

学业焦虑

指标类型:

主要指标

Outcome:

Academic anxiety

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

拖延

指标类型:

次要指标

Outcome:

Procrastinatio

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

心理治疗副作用

指标类型:

副作用指标

Outcome:

Psychotherapy Side Effects

Type:

Adverse events

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

大语言模型心理治疗安全性

指标类型:

副作用指标

Outcome:

Safety of LLM in psychotherapy

Type:

Adverse events

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

用户满意度

指标类型:

附加指标

Outcome:

User Satisfaction

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

自我效能感

指标类型:

附加指标

Outcome:

Self efficacy

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

痛苦耐受度

指标类型:

附加指标

Outcome:

Distress tolerance

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

抑郁

指标类型:

次要指标

Outcome:

Depression

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

人口学变量

指标类型:

附加指标

Outcome:

Demographic variables

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

人格

指标类型:

附加指标

Outcome:

Personality

Type:

Additional indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

广泛性焦虑

指标类型:

次要指标

Outcome:

Generalized Anxiety

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 60 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):

由不参与实验实施的人员通过计算机生成随机序列

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

A random sequence will be generated by a researcher not involved in the implementation of the intervention, using a computer-based randomization procedure.

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:

由于研究性质,无法对被试和干预实施者进行盲法。但数据分析将由不知分组信息的第三方在去标识的数据上进行,以降低偏倚风险。

Blinding:

Participants and intervention providers cannot be blinded due to the nature of the study. However, data analysts will remain blind to group allocation, and analysis will be conducted by a third party using de-identified data.

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

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):

由于本研究数据涉及大量被试的个人信息,仅可公开部分不涉及个人隐私的信息,公开时间在2026年5月12日之后,请联系yueyl23@mails.tsinghua.edu.cn

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

As the data in this study involve a large amount of personal information from participants, only information that does not involve personal privacy can be made publicly available. The data will be available after May 12, 2026. For access, please contact yueyl23@mails.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:

数据采集通过电子采集和管理系统进行采集,数据管理通过线下的本地RAID存储系统进行管理。

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

Data collection will be conducted through an electronic data capture and management system, and data management will be performed using an offline local RAID storage system.

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:

 2025-04-29 16:43:21