Today is 2020-01-26

Epileptic seizure detection by neural network architecture based on semiology of video recording
download

注册号:

Registration number:

ChiCTR1800014891 

最近更新日期:

Date of Last Refreshed on:

2018-03-03 

注册时间:

Date of Registration:

2018-02-07 

注册号状态:

预注册  

Registration Status:

Prospective registration  

注册题目:

利用(Spatial-Temporal GRU Convolutional Neural Network)深度學習的方法開發新型的智能電腦軟件以分析腦癎發作 

Public title:

Epileptic seizure detection by neural network architecture based on semiology of video recording 

注册题目简写:

 

English Acronym:

 

研究课题的正式科学名称:

利用(Spatial-Temporal GRU Convolutional Neural Network)深度學習的方法開發新型的智能電腦軟件以分析腦癎發作 

Scientific title:

Epileptic seizure detection by neural network architecture based on semiology of video recording 

研究课题代号(代码):

Study subject ID:

2017-HL-001 

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:

CUHK_CCRB00582 

申请注册联系人:

Ka Lai Yip 

研究负责人:

Ho Wan Leung 

Applicant:

Ka Lai Yip 

Study leader:

Ho Wan Leung 

申请注册联系人电话:

Applicant telephone:

+852 3505 3856 

研究负责人电话:

Study leader's telephone:

+852 3505 3856 

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:

Hannahykl@cuhk.edu.hk 

研究负责人电子邮件:

Study leader's E-mail:

Howanleung@cuhk.edu.hk 

申请单位网址(自愿提供):

Applicant website(voluntary supply):

https://www2.ccrb.cuhk.edu.hk/registry/public/520 

研究负责人网址(自愿提供):

Study leader's website(voluntary supply):

https://www2.ccrb.cuhk.edu.hk/registry/public/520 

申请注册联系人通讯地址:

Room 124010, 10/F, Lui Che Woo Clinical Sciences Building, Price of Wales Hospital, 30-32 Ngan Shing Street, Shatin, New Territories, Hong Kong, China 

研究负责人通讯地址:

Division of Neurology, Department of Medicine & Therapeutics, Price of Wales Hospital, Shatin, Hong Kong, China 

Applicant address:

Room 124010, 10/F, Lui Che Woo Clinical Sciences Building, Price of Wales Hospital, 30-32 Ngan Shing Street, Shatin, New Territories, Hong Kong, China 

Study leader's address:

Division of Neurology, Department of Medicine & Therapeutics, Price of Wales Hospital, Shatin, Hong Kong, 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:

Division of Neurology, The Chinese University of Hong Kong 

Applicant's institution:

Division of Neurology, The Chinese University of Hong Kong 

是否获伦理委员会批准:

是 

Approved by ethic committee:

Yes 

伦理委员会批件文号:

Approved No. of ethic committee:

2017.554 

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:

Joint CUHK-NTEC Clinical Research Ethics Committee 

Name of the ethic committee:

Joint CUHK-NTEC Clinical Research Ethics Committee 

伦理委员会批准日期:

Date of approved by ethic committee:

2017-11-20 

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:

The Chinese University Of Hong Kong 

Primary sponsor:

The Chinese University of Hong Kong 

研究实施负责(组长)单位地址:

The Chinese University of Hong Kong 

Primary sponsor's address:

The Chinese University of Hong Kong 

试验主办单位(项目批准或申办者):

Secondary sponsor:

经费或物资来源:

N/A 

Source(s) of funding:

N/A 

研究疾病:

癲癇 

Target disease:

Epilepsy 

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 

研究目的:

利用(Spatial-Temporal GRU Convolutional Neural Network)深度學習的方法開發新型的智能電腦軟件以分析腦癎發作 

Objectives of Study:

Epileptic seizure detection by neural network architecture based on semiology of video recording 

药物成份或治疗方案详述:

Experimental group: This research is an observational study using video recording to construct an artificial intelligent program for the recognition of epileptic seizures. In the present study, a novel marker-free analytical tool is used as a vision-based monitoring to the epileptic episodes. The video of seizure onsets will be confirmed by specialist or delegated research staffs and processed to the computing analysis. Control group: The 40 videos recording for the control will be obtained from the open database in the internet. The control is defined as that without seizure in that video recording. 

Description for medicine or protocol of treatment in detail:

Experimental group: This research is an observational study using video recording to construct an artificial intelligent program for the recognition of epileptic seizures. In the present study, a novel marker-free analytical tool is used as a vision-based monitoring to the epileptic episodes. The video of seizure onsets will be confirmed by specialist or delegated research staffs and processed to the computing analysis. Control group: The 40 videos recording for the control will be obtained from the open database in the internet. The control is defined as that without seizure in that video recording. 

研究设计:

随机平行对照 

Study design:

Parallel 

纳入标准:

1. Subjects are aged or above 18 years old; 2. Subjects are diagnosed with epilepsy; 3. Subjects who completed a video recording; 4. Subjects are able to give an informed consent. 

Inclusion criteria

1. Subjects are aged or above 18 years old; 2. Subjects are diagnosed with epilepsy; 3. Subjects who completed a video recording; 4. Subjects are able to give an informed consent. 

排除标准:

No captured event has been found in the video recording 

Exclusion criteria:

No captured event has been found in the video recording 

研究实施时间:

Study execute time:

FromTo  

干预措施:

Interventions:

组别:

Two groups

样本量:

40

Group:

Two groups

Sample size:

干预措施:

using video recording to construct an artificial intelligent program for the recognition of epileptic seizures, One epileptic seizure episode per subject, versus 40 video recording without seizure.

干预措施代码:

Intervention:

using video recording to construct an artificial intelligent program for the recognition of epileptic seizures, One epileptic seizure episode per subject, versus 40 video recording without seizure.

Intervention code:

研究实施地点:

Countries of recruitment and research settings:

国家:

中國 

省(直辖市):

香港特別行政區 

市(区县):

 

Country:

China 

Province:

Hong Kong SAR 

City:

 

单位(医院):

香港中文大學 

单位级别:

香港中文大學 

Institution
hospital:

Chinese University of Hong Kong  

Level of the institution:

Chinese University of Hong Kong 

测量指标:

Outcomes:

指标中文名:

Model validation

指标类型:

主要指标 

Outcome:

Model validation

Type:

Primary indicator 

测量时间点:

The efficacy of distinguishing the epilepsy behavior and normal motion will be scored.

测量方法:

The currently used detection model (Spatial-Temporal GRU Convolutional Neural Network) will be validated by the study of video from epilepsy patients.

Measure time point of outcome:

The efficacy of distinguishing the epilepsy behavior and normal motion will be scored.

Measure method:

The currently used detection model (Spatial-Temporal GRU Convolutional Neural Network) will be validated by the study of video from epilepsy patients.

指标中文名:

Detection latency

指标类型:

次要指标 

Outcome:

Detection latency

Type:

Secondary indicator 

测量时间点:

The existing of false positive will be eliminated by Two Stream Segmented ConvNets

测量方法:

A loss function for the calculation of the detection latency is created based on (1) the seizures and normal behavior required separately and (2) the uniformly increasing loss function.

Measure time point of outcome:

The existing of false positive will be eliminated by Two Stream Segmented ConvNets

Measure method:

A loss function for the calculation of the detection latency is created based on (1) the seizures and normal behavior required separately and (2) the uniformly increasing loss function.

采集人体标本:

Collecting sample(s)
from participants:

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 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):

N/A

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

N/A

盲法:

N/A

Blinding:

N/A

试验完成后的统计结果(上传文件):

Calculated Results ater
the Study Completed(upload file):

原始数据公开时间:

The time of sharing IPD:

Real time access

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):

Not stated

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

Not stated

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:

Not stated

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

Not stated

数据管理委员会:

Data Managemen Committee:

有/Yes

注册人:

Name of Registration:

 2018-02-07
return list