多模态AI情绪识别系统在青少年学⽣危机⾏为评估和预警中的应⽤研究

注册号:

Registration number:

ChiCTR2600120691 

最近更新日期:

Date of Last Refreshed on:

2026-03-18 14:34:15 

注册时间:

Date of Registration:

2026-03-18 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

多模态AI情绪识别系统在青少年学⽣危机⾏为评估和预警中的应⽤研究

Public title:

Multimodal AI Emotion Recognition: A Comprehensive Approach to Assessing and Predicting Crisis Behaviour in Adolescents

注册题目简写:

English Acronym:

研究课题的正式科学名称:

多模态AI情绪识别系统在青少年学⽣危机⾏为评估和预警中的应⽤研究

Scientific title:

Multimodal AI Emotion Recognition: A Comprehensive Approach to Assessing and Predicting Crisis Behaviour in Adolescents

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:

杨雨晴 

研究负责人:

杨雨晴 

Applicant:

Yang Yuqing 

Study leader:

Yuqing Yang 

申请注册联系人电话:

Applicant telephone:

+86 571 89972179

研究负责人电话:

Study leader's
telephone:

+86 571 8997 2179

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:

1473469320@qq.com

研究负责人电子邮件:

Study leader's E-mail:

1473469320@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:

浙江省杭州市西湖区古翠路234号

研究负责人通讯地址:

浙江省杭州市西湖区古翠路234号

Applicant address:

No. 234 Gucui Road, Xihu District, Hangzhou City, Zhejiang Province

Study leader's address:

No. 234 Gucui Road, Xihu District, Hangzhou City, Zhejiang Province

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:

浙江省立同德医院

Applicant's institution:

Tongde Hospital of Zhejiang Province

研究负责人所在单位:

浙江省立同德医院

Affiliation of the Leader:

Tongde Hospital of Zhejiang Province

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:

浙同德伦审2026研第024号—JY

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:

浙江省立同德医院医学伦理委员会

Name of the ethic committee:

Medical Ethics Committee of Tongde Hospital of Zhejiang Province

伦理委员会批准日期:

Date of approved by ethic committee:

2026-01-27 00:00:00

伦理委员会联系人:

朱于青

Contact Name of the ethic committee:

Zhu YuQing

伦理委员会联系地址:

浙江省杭州市西湖区古翠路234号

Contact Address of the ethic committee:

No. 234 Gucui Road, Xihu District, Hangzhou City, Zhejiang Province

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 571 89975971

伦理委员会联系人邮箱:

Contact email of the ethic committee:

zhuyuqingnb@163.com

研究实施负责(组长)单位:

浙江省立同德医院

Primary sponsor:

Tongde Hospital of Zhejiang Province

研究实施负责(组长)单位地址:

浙江省杭州市西湖区古翠路234号

Primary sponsor's address:

No. 234 Gucui Road, Xihu District, Hangzhou City, Zhejiang Province

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

中国

省(直辖市):

浙江省

市(区县):

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江省立同德医院

具体地址:

浙江省杭州市西湖区古翠路234号

Institution
hospital:

Tongde Hospital of Zhejiang Province

Address:

No. 234 Gucui Road, Xihu District, Hangzhou City, Zhejiang Province

经费或物资来源:

浙江省卫生健康行业科技计划项目

Source(s) of funding:

The ‌Zhejiang Provincial Medical and Health Science and Technology Plan

研究疾病:

自伤;自杀;消极想法;消极冲动;危机行为;抑郁情绪和抑郁障碍  

Target disease:

self-harm; suicide; suicidal idea; suicidal impulse; crisis behaviours; depressive emotions and depression

研究疾病代码:

Target disease code:

研究类型:

观察性研究

Study type:

Observational study

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

本研究应用多模态AI情绪识别系统对青少年抑郁症学生危机行为进行风险性评估,验证该系统的有效性和准确性,有助于建立更高效的危机行为筛查、预警和风险性分级评估系统。此外通过AI学习构建青少年学生危机行为的情绪模型,探索青少年学生危机行为的客观性预警标准。  

Objectives of Study:

This study utilizes a multimodal AI emotion recognition system to perform risk assessment for crisis behaviors among depression adolescent students. It intends to verify the effectiveness and accuracy of the system while contributing to the development of a more efficient approach for screening crisis behaviours, issuing early warnings, and assessing risk levels. Additionally, an emotional model of adolescents' crisis behaviours is created through AI learning to explore objective early warning criteria for these behaviours.

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.脑器质性疾病、躯体器质性疾病、神经系统器质性疾病、广泛性发育障碍、学习困难、品行障碍、精神发育迟滞、自闭症谱系障碍、注意力缺陷障碍及精神障碍,听视觉异常等疾病,以及其他精神心理障碍。

Exclusion criteria:

1.Organic brain diseases, somatic diseases, organic nervous system disorders, pervasive developmental disorders, learning difficulties, conduct disorders, intellectual disabilities, autism spectrum disorders, attention deficit disorders, mental health disorders, auditory or visual abnormalities and so on,and other mental health problems.

研究实施时间:

Study execute time:

From 2026-01-01 00:00:00 To 2028-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2026-09-01 00:00:00 To 2028-06-30 00:00:00

干预措施:

Interventions:

组别:

抑郁存在危机行为组

样本量:

32

Group:

Depression with Crisis Behaviour Group

Sample size:

干预措施:

干预措施代码:

Intervention:

None

Intervention code:

组别:

抑郁不存在危机行为组

样本量:

32

Group:

Depression without Crisis Behaviour 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):

浙江省 

市(区县):

 

Country:

China

Province:

Zhejiang

City:

单位(医院):

浙江省立同德医院 

单位级别:

三级甲等 

Institution
hospital:

Tongde Hospital of Zhejiang Province

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

心率变异HRV相关数据

指标类型:

主要指标

Outcome:

Heart Rate Variability (HRV)-related data

Type:

Primary indicator

测量时间点:

研究开始时,每隔一个月评估一次;出现危机行为时

测量方法:

非接触式心率呼吸频率监测仪使用光纤传感技术评估HRV相关数据。

Measure time point of outcome:

At the beginning of the study, and assess every other month. Crisis behaviour appears.

Measure method:

Non-contact heart rate and respiratory rate monitors use optical fiber sensing technology to evaluate data related to Heart Rate Variability (HRV).

指标中文名:

消极状态和危机行为记录

指标类型:

主要指标

Outcome:

Record of negative state and crisis behaviours

Type:

Primary indicator

测量时间点:

一直从入组持续到研究结束,持续半年

测量方法:

受试者记录

Measure time point of outcome:

It lasts continuously for 6 months, from enrollment in the group until the end of the study

Measure method:

Record by participants

指标中文名:

临床诊断

指标类型:

主要指标

Outcome:

Diagnose

Type:

Primary indicator

测量时间点:

研究开始时

测量方法:

使用标准化临床访谈——简明国际神经精神访谈(Mini International Neuropsychiatirc Interview, MINI)中文版问卷

Measure time point of outcome:

At the beginning of the study

Measure method:

Standardized clinical interview——Mini International Neuropsychiatirc Interview, MINI

指标中文名:

脑神经活动强度

指标类型:

主要指标

Outcome:

Neural activity intensity

Type:

Primary indicator

测量时间点:

研究开始时;出现危机行为时

测量方法:

脑功能成像系统使用近红外技术评估脑神经活动强度。

Measure time point of outcome:

At the beginning of the study;Crisis behaviour appears.

Measure method:

Brain function imaging systems use near-infrared technology to evaluate the intensity of cerebral neural activity.

指标中文名:

危机行为相关影响因素

指标类型:

次要指标

Outcome:

influencing factors related to crisis behaviour

Type:

Secondary indicator

测量时间点:

研究开始时

测量方法:

使用自评心理量表,包括中家庭环境量表、父母养育方式量表。

Measure time point of outcome:

At the beginning of the study

Measure method:

Using self-rating psychological questionnaire, including Family Environment Scale - Chinese Version(FES-CV) and Egna Minnen av Barndoms Uppfostran(EMBU).

指标中文名:

临床症状

指标类型:

主要指标

Outcome:

Clinical Symptoms

Type:

Primary indicator

测量时间点:

研究开始时,每隔一个月评估一次;出现危机行为时

测量方法:

使用自评心理量表,包括中学生心理健康问卷、宗氏抑郁自评量表和病人健康问卷。

Measure time point of outcome:

At the beginning of the study, and assess every other month. Crisis behaviour appears.

Measure method:

Using self-rating psychological questionnaire, including Mental Health Inventory of Middle School, Zong's Self-rating Scale for Depression (SDS) and Patient Health Questionnaire (PHQ9).

采集人体标本:

Collecting sample(s)
from participants:

标本中文名:

组织:

Sample Name:

NA

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 12 years
最大 Max age 18 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):

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

None

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:

Blinding:

None

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):

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:

数据采集使用标准化病例记录表,实验中收集的数据采用电子采集和管理系统。在研究过程中收集到的所有受试者信息与数据,将严格保密。知情同意书与研究记录将分开存放。受试者的研究记录会被赋予唯一编码,该编码可关联至其知情同意书,且研究记录仅通过此唯一编码进行标识。研究结束后,知情同意书将被销毁。仅研究负责人有权访问上述信息与研究记录。

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

Data collection and management using a standard data collection and management system include a CRF and an electronic data capture. All the information and data collected about participants during the research will be kept strictly confidential. The consent form and research records will be stored separately. Participants’ research records will be given a unique code that links them to their consent form. Their records will only be identified by this unique code. The consent forms will be destroyed at the end of the study. Only the principal investigator will have access to these information and research records.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2026-03-18 14:34:05