探索脑-心电生理联动MLP模型如何精确诊断抑郁症的机制

注册号:

Registration number:

ChiCTR2500099887 

最近更新日期:

Date of Last Refreshed on:

2025-03-31 16:23:30 

注册时间:

Date of Registration:

2025-03-31 00:00:00 

注册号状态:

补注册

Registration Status:

Retrospective registration

注册题目:

探索脑-心电生理联动MLP模型如何精确诊断抑郁症的机制

Public title:

Exploring the Mechanism of How the Brain-Heart Electrophysiological Linkage Multilayer perceptron(MLP) Model Achieves Precise Diagnosis of Depression.

注册题目简写:

English Acronym:

研究课题的正式科学名称:

脑-心电生理联动MLP模型在抑郁症精准诊断中的作用机制研究

Scientific title:

Mechanistic Study of the Brain-Heart Electrophysiological Coupling Multilayer perceptron(MLP) Model in Precise Diagnosis of Depression.

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:

李梦倩 

研究负责人:

李梦倩 

Applicant:

Mengqian Li 

Study leader:

Mengqian Li 

申请注册联系人电话:

Applicant telephone:

+86 15879098200

研究负责人电话:

Study leader's
telephone:

+86 791 88692280

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:

limengqian@126.com

研究负责人电子邮件:

Study leader's E-mail:

limengqian@126.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:

南昌大学第一附属医院象湖院区

研究负责人通讯地址:

南昌市东湖区永外正街17号

Applicant address:

The First Affiliated Hospital of Nanchang University, Xianghu Campus

Study leader's address:

17# Yongwai Zhengjie, Nanchang City, Jiangxi Province, 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:

南昌大学

Applicant's institution:

Nanchang University

研究负责人所在单位:

南昌大学第一附属医院

Affiliation of the Leader:

The First Affiliated Hospital of Nanchang 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:

IIT[2024]临伦审第071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:

南昌大学第一附属医院IIT项目伦理审查委员会

Name of the ethic committee:

Medical Ethics Committee of the First Affiliated Hospital of Nanchang University

伦理委员会批准日期:

Date of approved by ethic committee:

2024-02-21 00:00:00

伦理委员会联系人:

舒展

Contact Name of the ethic committee:

Zhan Shu

伦理委员会联系地址:

南昌市东湖区永外正街17号

Contact Address of the ethic committee:

17# Yongwai Zhengjie, Nanchang City, Jiangxi Province, China

伦理委员会联系人电话:

Contact phone of the ethic committee:

+86 791 88692201

伦理委员会联系人邮箱:

Contact email of the ethic committee:

493831410@qq.com

研究实施负责(组长)单位:

南昌大学第一附属医院

Primary sponsor:

The First Affiliated Hospital of Nanchang University

研究实施负责(组长)单位地址:

南昌市东湖区永外正街17号

Primary sponsor's address:

17# Yongwai Zhengjie, Nanchang City, Jiangxi Province, 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):

江西

市(区县):

Country:

China

Province:

Jiangxi

City:

单位(医院):

南昌大学第一附属医院

具体地址:

南昌市东湖区永外正街17号

Institution
hospital:

The First Affiliated Hospital of Nanchang University

Address:

17# Yongwai Zhengjie, Nanchang City, Jiangxi Province, China

经费或物资来源:

国家自然科学基金

Source(s) of funding:

The National Natural Science Foundation of China (NSFC)

研究疾病:

抑郁障碍  

Target disease:

Depressive Disorder

研究疾病代码:

Target disease code:

研究类型:

诊断试验

Study type:

Diagnostic test

研究所处阶段:

其它 

Study phase:

N/A

研究设计:

诊断试验诊断准确性 

Study design:

Diagnostic test for accuracy 

研究目的:

总体目标:建立脑-心电生理联动MLP抑郁症精准诊断模型,探究诊断机制。 1.构建:脑-心电生理联动MLP抑郁症分类(性别)、分级诊断模型; 2.评价:脑-心电生理联动FCN协同MLP模型在抑郁症精准诊断中的临床价值; 3.回答:探究EEG微状态因素(因子)、心率变异性因素(因子)、抑郁诊断量表因素(因子)的影响权重,回答MLP模型的诊断机制; 4.探讨:脑-心电生理联动MLP抑郁症精准诊断模型的临床价值。  

Objectives of Study:

Overall Objective: To establish a precise diagnosis model for depression based on brain-heart electrophysiological linkage based on multilayer perceptron (MLP), and to explore the diagnostic mechanism. 1. Construction: Brain-heart Electrophysiological Linkage MLP Model for Depression Classification (Gender) and Grading Diagnosis; 2. Evaluation: Clinical Value of the Brain-Cardiac Electrophysiological Linkage a fully convolutional neural network (FCN) Collaborative MLP Model in Precise Diagnosis of Depression; 3. Answer: Investigate the influence weights of EEG microstate factors (factors), heart rate variability factors (factors), and depression diagnosis scale factors (factors), and explain the diagnostic mechanism of the MLP model; 4. Exploration: Clinical Value of the Brain-heart Electrophysiological Linkage MLP Model for Precise Diagnosis of Depression;

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:

抑郁组 1.根据 DSM-5 诊断标准,受试者当前/既往有精神分裂症谱系或其他精神 病、 双相或相关障碍、强迫及相关障碍、创伤及应激相关障碍、分离障碍、神经性厌食或贪食、人格障碍等; 2.既往存在癫痫发作病史(儿童高热惊厥引起的抽搐除外); 3.既往有过其他躯体疾病,尤其是神经疾病史、颅脑外伤史; 4.既往有严重过敏史; 5.近 1 年内存在酒精或药物依赖/药物滥用史(包括苯二氮卓类药物,除外 尼古丁或咖啡因),或筛选时尿液药物检测呈阳性; 6.经研究者评估任何其他可能妨碍依从性、损害受试者健康或干扰研究结局的情况; 对照组 1.在匹配的年龄范围内,有抑郁症状的报告; 2.HAM-D17 总评分≥22 分; 3.既往存在其他严重精神疾病的诊断; 4.既往有过其他躯体疾病,尤其是神经疾病史、颅脑外伤史; 5.既往有严重的认知功能障碍或神经系统疾病; 6.既往有药物滥用或酗酒的历史.

Exclusion criteria:

depression group 1. According to DSM-5 diagnostic criteria, subjects currently or previously have schizophrenia spectrum or other psychotic disorders, bipolar or related disorders, obsessive-compulsive and related disorders, trauma- and stressor-related disorders, dissociative disorders, anorexia nervosa or bulimia nervosa, personality disorders, etc; 2. A history of epileptic seizures (excluding convulsions caused by febrile seizures in childhood); 3. A history of other somatic diseases, particularly neurological disorders and history of traumatic brain injury; 4. A history of severe allergies; 5. A history of alcohol or drug dependence/abuse within the past year (including benzodiazepines, excluding nicotine or caffeine), or a positive urine drug test at screening; 6. Any other condition, as assessed by the investigator, that may interfere with compliance, compromise the subject's health, or interfere with the study outcomes. control group 1. The following criteria were met within the matched age range: Reports of depressive symptoms; 2. A total score of >=22 on the 17-item Hamilton Depression Rating Scale (HAMD-17); 3. Past diagnosis of other severe psychiatric disorders; 4. History of other somatic diseases, especially neurological diseases or history of traumatic brain injury; 5. History of severe cognitive impairment or neurological diseases; 6. History of drug abuse or alcoholism.

研究实施时间:

Study execute time:

From 2024-01-01 00:00:00 To 2027-12-31 00:00:00  

征募观察对象时间:

Recruiting time:

From 2024-12-23 00:00:00 To 2027-12-31 00:00:00

诊断试验:

Diagnostic Tests:

金标准或参考标准(即可准确诊断某疾病的单项方法或多项联合方法,在本研究中用于诊断是否有该病的临床参考标准):

抑郁症的金标准是《精神障碍诊断与统计手册(DSM - 5)》和《国际疾病分类(ICD - 10)》。

Gold Standard or Reference Standard (The clinical reference standards required to establish the presence or absence of the target condition in the tested population in present study):

The gold standard for diagnosing depression is the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), and the International Classification of Diseases, Tenth Revision (ICD-10).

指标试验(即本研究的待评估诊断试验,无论为方法、生物标志物或设备,均请列出名称):

汉密尔顿量表、脑电微状态和心率采集、5-羟色胺再摄取抑制剂抗药物、建立脑-心电生理联动 多层感知器(MLP )抑郁症精准诊断模型。

Index test:

The Hamilton Depression Rating Scale (HAMD), EEG microstates , heart rate acquisition, selective serotonin reuptake inhibitors (SSRIs) as antidepressants, and the establishment of a brain-cardiac electrophysiological linkage Multilayer Perceptron (MLP) modle for precise diagnosis of depression.

目标人群(可以是某种疾病患者或正常人群,详细描述其疾病特征,注意应纳入符合分布特点的全序列病例,具有良好的代表性)

抑郁症患者

例数:

Sample size:

180

Target condition (The target condition is a particular disease or disease stage that the index test will be intended to identify. Please specify the characteristics in detail; the population should has a complete spectrum and good representative):

Patient with major depressive disorder.

容易混淆的疾病人群(即与目标疾病不易区分的一种或多种不同疾病,应避免采用正常人群对照的病例-对照设计):

双相情感障碍患者

例数:

Sample size:

120

Population with condition difficult to distinguish from the target condition, the normal population in a case-control study design should be avoid:

Patient with bipolar disorder.

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

江西 

市(区县):

 

Country:

China

Province:

Jiangxi

City:

单位(医院):

南昌大学第一附属医院 

单位级别:

三级甲等 

Institution
hospital:

The First Affiliated Hospital of Nanchang University

Level of the institution:

Tertiary A

测量指标:

Outcomes:

指标中文名:

汉密尔顿抑郁量表

指标类型:

主要指标

Outcome:

Hamilton Depression Scale (HAMD)

Type:

Primary indicator

测量时间点:

入组前及治疗后

测量方法:

Measure time point of outcome:

Pre-treatment and Post-treatment

Measure method:

指标中文名:

微状态

指标类型:

主要指标

Outcome:

Microstate

Type:

Primary indicator

测量时间点:

入组前及治疗后

测量方法:

EEG 数据中微状态 A(语音加工)、微状态 B(视觉想象)、微状态 C(主观感受)和微状态 D(注意力)的数据,通过医院脑电设备收集。

Measure time point of outcome:

Pre-enrollment and Post-treatment

Measure method:

EEG Data on Microstates A (Voice Processing), B (Visual Imagery), C (Subjective Experience), and D (Attention) Collected Using Hospital EEG Equipment.

指标中文名:

心率变异性数据

指标类型:

主要指标

Outcome:

Heart Rate Variability (HRV) Data

Type:

Primary indicator

测量时间点:

入组前及治疗后

测量方法:

包括自主神经系统活性、自主神经系统稳定性、抗压能力、疲劳指数等指标,通过医院心率变异性仪器收集。

Measure time point of outcome:

Pre-enrollment and Post-treatment

Measure method:

Heart Rate Variability (HRV) Metrics Including Autonomic Nervous System (ANS) Activity, ANS Stability, Stress Resilience, and Fatigue Index Collected Using Hospital HRV Equipment.

指标中文名:

EEG微状态特征权重

指标类型:

次要指标

Outcome:

EEG microstate features

Type:

Secondary indicator

测量时间点:

测量方法:

通过全卷积神经网络(FCN)提取的脑电微状态(如微状态A、B、C、D)在诊断模型中的贡献度,通过主成分分析(PCA)来确定;

Measure time point of outcome:

Measure method:

The contributions of EEG microstates (such as microstates A, B, C, and D) extracted by the Fully Convolutional Network (FCN) in the diagnostic model are determined through Principal Component Analysis (PCA).

指标中文名:

MLP模型诊断准确性

指标类型:

主要指标

Outcome:

Diagnostic accuracy of MLP model

Type:

Primary indicator

测量时间点:

测量方法:

通过ROC曲线评估

Measure time point of outcome:

Measure method:

Assess using the ROC curve

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:

正在进行

Recruiting

年龄范围:

Participant age:

最小 Min age 18 years
最大 Max age 65 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):

2027年12月以公开发表论文方式公开原始数据

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

Raw data to be made publicly available in December 2027 in the form of an open access paper

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:

纸质/电子表格、数据库建立及录入、电子化数据采集;数据库清洗及锁定,数据存档等。

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

Paper forms / Electronic spreadsheets;Database establishment and data entry;Electronic data capture (EDC);Database cleaning and locking; Data archiving etc.

数据与安全监察委员会:

Data and Safety Monitoring Committee:

无/No

注册人:

Name of Registration:

 2025-03-31 16:23:13