基于面部表情的深度学习模型用于精准评估产妇分娩期疼痛及治疗

注册号:

Registration number:

ChiCTR1800018753 

最近更新日期:

Date of Last Refreshed on:

2018-12-16 19:33:43 

注册时间:

Date of Registration:

2018-10-08 00:00:00 

注册号状态:

预注册

Registration Status:

Prospective registration

注册题目:

基于面部表情的深度学习模型用于精准评估产妇分娩期疼痛及治疗

Public title:

Assess Intrapartum Pain Relief after Epidural Analgesia With Facial Expressions Information Using Artificial Neural Networks

注册题目简写:

English Acronym:

研究课题的正式科学名称:

基于面部表情的深度学习模型用于精准评估产妇分娩期疼痛及治疗

Scientific title:

Assess Intrapartum Pain Relief after Epidural Analgesia With Facial Expressions Information Using Artificial Neural Networks

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:

程丹 

研究负责人:

张卫 

Applicant:

Dan Cheng 

Study leader:

Wei Zhang 

申请注册联系人电话:

Applicant telephone:

+86 15938718201

研究负责人电话:

Study leader's
telephone:

+86 13673996966

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:

chengdan0607@163.com

研究负责人电子邮件:

Study leader's E-mail:

zhangw571012@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:

河南省郑州市二七区建设东路1号

研究负责人通讯地址:

河南省郑州市二七区建设东路1号

Applicant address:

1 Jianshe Road East, Zhengzhou, He'nan, China

Study leader's address:

1 Jianshe Road East, Zhengzhou, He'nan, 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:

郑州大学第一附属医院麻醉科

Applicant's institution:

The First Affiliated Hospital of Zhengzhou University, Henan, PR China

研究负责人所在单位:

郑州大学第一附属医院麻醉科

Affiliation of the Leader:

The First Affiliated Hospital of Zhengzhou University, Henan, PR China

是否获伦理委员会批准:

Approved by ethic committee:

No

伦理委员会批件文号:

Approved No. of ethic committee:

伦理委员会批件附件:

Approved file of Ethical Committee:

批准本研究的伦理委员会名称:

Name of the ethic committee:

伦理委员会批准日期:

Date of approved by ethic committee:

2013-08-26 00:00:00

伦理委员会联系人:

Contact Name of the ethic committee:

伦理委员会联系地址:

Contact Address of the ethic committee:

伦理委员会联系人电话:

Contact phone of the ethic committee:

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:

郑州大学第一附属医院

Primary sponsor:

The First Affiliated Hospital of Zhengzhou University

研究实施负责(组长)单位地址:

河南省郑州市二七区建设东路1号

Primary sponsor's address:

1 Jianshe Road East, Zhengzhou, He'nan, China

试验主办单位(项目批准或申办者):

Secondary sponsor:

国家:

美国

省(直辖市):

马萨诸塞州

市(区县):

波士顿

Country:

USA

Province:

Massachusetts

City:

Boston

单位(医院):

麻省总医院

具体地址:

55 Fruit St, Boston, MA

Institution
hospital:

Massachusetts General Hospital

Address:

55 Fruit St, Boston, MA

国家:

中国

省(直辖市):

河南

市(区县):

郑州

Country:

China

Province:

He'nan

City:

Zhengzhou

单位(医院):

郑州大学第一附属医院

具体地址:

河南省郑州市二七区建设东路1号

Institution
hospital:

The First Affiliated Hospital of Zhengzhou University

Address:

1 Jianshe Road East, Zhengzhou, He'nan, China

经费或物资来源:

医院部门资金

Source(s) of funding:

Hospital Departmental Funding

研究疾病:

分娩期疼痛  

Target disease:

Intrapartum Pain

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:

诊断试验新技术临床试验 

Study phase:

Diagnostic New Technique Clincal Study

研究设计:

队列研究 

Study design:

Cohort study 

研究目的:

评估基于面部表情的个性化深度学习计算机模型(面部表情模型)用于临床分娩期疼痛及镇痛治疗效果评价的临床应用效能,并探索其与标准自我报告疼痛评分的相关性。即是否面部表情模型可用于患者疼痛定量评价,并可与视觉疼痛评分类似,通过面部表情而非患者自我汇报,定量捕捉到镇痛治疗后疼痛的变化。  

Objectives of Study:

A personalized deep learning computer model based on facial expressions (facial expression model) was evaluated for clinical application efficacy in clinical delivery pain and analgesic treatment evaluation, and its correlation with standard self-reported pain scores was explored. That is, whether the facial expression model can be used for quantitative evaluation of patient pain, and similar to the Visual Analogue Scale, quantitatively captures the change in pain after analgesia treatment through facial expression rather than self-reporting of the patient.

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)面部有明显烧伤、烫伤、瘢痕挛缩、外伤等影响面部识别的情况;
(2)产妇存在硬膜外麻醉禁忌症:中枢系统疾病(如脑膜炎、结核、肿瘤等),脊柱畸形,穿刺部位感染、败血症,心血管功能不全(如严重贫血、休克、心力衰竭、冠心病等),凝血功能障碍(血小板低于80*109/L,PT超过正常值3秒,TT超过正常值5秒,APTT超过正常值10秒);
(3)产妇无法配合摆体位行硬膜外麻醉;
(4)当前正参与另一项可能会干扰本研究结果的研究;
(5)经研究者判定不适合入组的其它情况。

Exclusion criteria:

(1) The face has obvious burns, scar contractures or trauma affecting facial recognition;
(2) Maternal epidural anesthesia contraindications: central system diseases (e.g. meningitis, tuberculosis and tumors), spinal deformity, puncture site infection, sepsis, cardiovascular insufficiency (e.g. severe anemia, shock, heart failure, crown Heart disease), coagulopathy (platelets below 80*109/L, PT exceeds normal value for 3 seconds, TT exceeds normal value for 5 seconds, APTT exceeds normal value for 10 seconds);
(3) The maternal woman cannot perform epidural anesthesia with the pendulum position;
(4) Currently participating in another study that may interfere with the results of this study;
(5) Other circumstances that the investigator determines are not suitable for enrollment.

研究实施时间:

Study execute time:

From 2018-11-15 00:00:00 To 2019-02-01 00:00:00  

征募观察对象时间:

Recruiting time:

From 2018-11-15 00:00:00 To 2019-02-01 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):

标准自我报告疼痛评分

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):

standard self-reported pain scores

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):

个性化深度学习计算机模型(面部表情模型)

Index test:

personalized deep learning computer model based on facial expressions (facial expression model)

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)

拟行经阴道分娩并行硬膜外麻醉分娩镇痛的产妇

例数:

Sample size:

50

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):

Vaginal delivery and epidural anesthesia for labor analgesia maternal women

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):

例数:

Sample size:

0

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

研究实施地点:

Countries of recruitment and research settings:

国家:

中国

省(直辖市):

河南 

市(区县):

郑州 

Country:

China

Province:

He'nan

City:

Zhenghou

单位(医院):

郑州大学第一附属医院 

单位级别:

三级甲等 

Institution
hospital:

The First Affiliated Hospital of Zhengzhou University

Level of the institution:

Tertiary A Hospital

测量指标:

Outcomes:

指标中文名:

视觉模拟疼痛评分

指标类型:

主要指标

Outcome:

Visual Analogue Scale

Type:

Primary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

面部表情

指标类型:

次要指标

Outcome:

Facial Expressions

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

焦虑自评量表

指标类型:

次要指标

Outcome:

Self-rating Anxiety Scale

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

疼痛灾难化量表

指标类型:

次要指标

Outcome:

Pain Catastrophizing Scale

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

抑郁自评量表

指标类型:

次要指标

Outcome:

Self-rating Depression Scale

Type:

Secondary indicator

测量时间点:

测量方法:

Measure time point of outcome:

Measure method:

指标中文名:

SPE, SEN, ACC, ROC

指标类型:

主要指标

Outcome:

SPE, SEN, ACC, ROC

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:

面部表情

组织:

面部

Sample Name:

Facial expressions

Tissue:

human face

人体标本去向

使用后保存  

说明

视频保存

Fate of sample:

Preservation after use  

Note:

video recording and stored as digital file

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 40 years

性别:

女性

Gender:

Female

随机方法(请说明由何人用什么方法产生随机序列):

无随机

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

No 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:

观察性研究,无盲法

Blinding:

None

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):

因牵涉到患者面部影像,获取方式需联系主要研究者并获得试验患者同意

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

Contact Primary Investigator and consent from patients needed.

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:

数据收集使用病例记录表(CRF)及相机录像, 数据将被储存在密码保护的本地硬盘内(不上传至网络)以严格保护患者面部影像隐私。

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

Data collection: paper-based Case Report Form (CRF) and camera recording; Data will be entered into excel sheets and facial videos will be stored in a password protected local drive to protect patients' facial data information.

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:

 2018-10-08 13:34:06