Centre For Clinical Research And Biostatistics (CCRB)

Back

1 Unique Trial Number (assigned by CCRB)

CUHK_CCRB00582

2 Trial Registration Date

2018-02-07

i Registration Status

Prospective

3 Secondary IDs

CREC Ref No. 2017.554

Protocol No. 2017-HL-001

4 Source(s) of Funding

This is no a funded project

5 Primary Sponsor

N/A

6 Secondary Sponsor

N/A

Function

Not Applicable

Please specify

7 Responsible Contact Person (public contact person for patients interested in participating)

i Name

Ka Lai Yip

ii Address

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

iii Phone

3505 3856

iv Email

Hannahykl@cuhk.edu.hk

v Affiliation

Division of Neurology, The Chinese University of Hong Kong

vi Country

Hong Kong

8 Research Contact Person (person to contact for scientific inquiries)

i Name

Ho Wan Leung

ii Address

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

iii Phone

3505 3856

iv Email

Howanleung@cuhk.edu.hk

v Affiliation

Division of Neurology, The Chinese University of Hong Kong

vi Country

Hong Kong

9 Official Scientific Title of the Study

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

10 Public Title

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

i Public Title in Chinese 研究名稱

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

11 Short Title (Optional)

12 Countries of Recruitment

Hong Kong

13 Research Ethic Review

i Has the study received appropriate ethics approval?

Yes

ii When is the approval date?

2017-11-20

iii Full Name of IRB/IEC

Joint CUHK-NTEC Clinical Research Ethics Committee

Please specify

iv IRB/IEC approval reference number

CREC Ref. No: 2017.554

14 Medical Condition Being Studied

Epilepsy

15 Intervention

i Types of intervention

Other

Please specify

A artificial intelligent program

ii Description/ name of Intervention/article

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.

iii Dosage form of the intervention

Not drug trial

iv Dosage of the intervention

Not drug trial

v Duration of the intervention

Not drug trial

vi Frequency of the intervention

One epileptic seizure episode per subject

16 Comparative Treatments

i Description/ name of comparative treatments

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.

ii Dosage form of the comparative treatments

Not drug trial

iii Dosage of the comparative treatments

Not drug trial

iv Duration of the comparative treatments

Not drug trial

v Frequency of the comparative treatments

One normal body movement per subject

17 Key Inclusion and Exclusion Criteria

i Inclusion Criteria

Subjects are aged or above 18 years old

Subjects are diagnosed with epilepsy

Subjects who completed a video recording

Subjects are able to give an informed consent

ii Exclusion Criteria

No captured event has been found in the video recording

iii Age Minimum

18

iv Age Maximum

999

v Gender

Both Male and Female

18 Study Type

Observational

19 Study Design

i Randomization

Not Applicable

Please specify

ii Nature of control

Not Applicable

iii Degree of masking

Not Applicable

If Single-blind, who will be masked?

iv Group Assignment

Not Applicable

v Study Phase

Other

Please specify

N/A

vi Study Objectives (Optional)

20 Anticipated trial start date

2018-03-01

21 Target Sample Size

40

22 Recruitment Status

Recruiting

23 Primary Outcome

i The Name of the outcome

Model validation

ii The metric or method of measurement used

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

iii The timepoint(s) of primary interest

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

24 Secondary Outcome

i The Name of the outcome

Detection latency

ii The metric or method of measurement used

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.

iii The timepoint(s) of primary interest

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

25 Study Information/Publication

i Study Information/Publication Available?

No

ii Link to Study Information/Publication

26 Last Update Date

2020-12-07

27 Primary Registry and Trial Identifying Number

28 Date of Registration in Primary Registry

Back

Trial History Detail on 2018-02-22