Trial Review

The safety and scientific validity of this study is the responsibility of the study sponsor and investigators. Listing a study does not mean it has been endorsed by the ANZCTR. Before participating in a study, talk to your health care provider and refer to this information for consumers
Trial registered on ANZCTR


Registration number
ACTRN12619001161112
Ethics application status
Approved
Date submitted
6/08/2019
Date registered
20/08/2019
Date last updated
25/05/2022
Date data sharing statement initially provided
20/08/2019
Type of registration
Prospectively registered

Titles & IDs
Public title
Seizure Detection and Classification Using Eyelid Movements
Scientific title
Identifying a Digital Biomarker for Seizure Detection and Classification Using Eyelid Movements: A Video-EEG Monitoring Study
Secondary ID [1] 298951 0
Nil known
Universal Trial Number (UTN)
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Seizures 313934 0
Condition category
Condition code
Neurological 312341 312341 0 0
Epilepsy

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
Participants admitted for inpatient video-EEG monitoring across the combined Comprehensive Epilepsy Program at The Alfred Hospital and The Royal Melbourne Hospital, and meeting eligibility criteria, will be invited to participate in the study. Enrolled participants will be asked to wear glasses that measure eyelid movements using infrared reflectance oculography. The glasses used are commercially available glasses from Optalert called the Eagle Wireless Glasses. They contain a sensor that measure the eyelid opening and transmit this information 500 times a second to a local data logger. The glasses have the option to fit prescription lenses where required. The local data logger transfers the data to a central storage server. Participants will wear the glasses during wakefulness throughout the monitoring period, which typically lasts five days. They will be monitored by hospital staff to ensure they are wearing the glasses when possible, the storage server can also be remotely monitored to ensure data is being collected and devices are sufficiently charged.
Intervention code [1] 315223 0
Diagnosis / Prognosis
Intervention code [2] 315224 0
Early detection / Screening
Comparator / control treatment
No control group
Control group
Uncontrolled

Outcomes
Primary outcome [1] 320969 0
To determine whether changes to eyelid movements immediately before, during and following epileptic seizures can be used for epileptic seizure detection, using the non-invasive wearable device (“Eagle Wireless Glasses”), which measures ocular parameters using infrared reflectance oculography and to quantify the sensitivity of this measurement.

Seizures are assessed by expert analysis of video EEG data concurrently recorded with the eyelid movement data.
Timepoint [1] 320969 0
Participants shall have their video EEG and eyelid movement data recorded during their hospital admission for 5 day video EEG monitoring. The video EEG is assessed towards the end of their admission, and a summary of annotated seizures shall be used to determine seizure times.
Eyelid movement data, which is collected concurrently, shall then be analysed for each patient with respect to these annotations. This will be done on an ongoing basis, and as a data set for classification using machine learning once all data has been collected.
Primary outcome [2] 320970 0
To examine whether changes to eyelid movements immediately before, during and following different epileptic seizure types will allow for classification by seizure type, using the non-invasive wearable device (“Eagle Wireless Glasses”), which measures ocular parameters using infrared reflectance oculography.
Seizures are assessed by expert analysis of video EEG data concurrently recorded with the eyelid movement data. This is an exploratory measure.
Timepoint [2] 320970 0
Participants shall have their video EEG and eyelid movement data recorded during their hospital admission for 5 day video EEG monitoring. The video EEG is assessed towards the end of their admission, and a summary of annotated seizures shall be used to determine seizure times.
Eyelid movement data, which is collected concurrently, shall then be analysed for each patient with respect to these annotations. This will be done on an ongoing basis, and as a data set for classification using machine learning once all data has been collected.
Primary outcome [3] 320971 0
To assess whether changes to eyelid movements preceding epileptic seizures will allow for seizure prediction, using the non-invasive wearable device (“Eagle Wireless Glasses”), which measures ocular parameters using infrared reflectance oculography. Seizures are assessed by expert analysis of video EEG data concurrently recorded with the eyelid movement data.
Timepoint [3] 320971 0
Participants shall have their video EEG and eyelid movement data recorded during their hospital admission for 5 day video EEG monitoring. The video EEG is assessed towards the end of their admission, and a summary of annotated seizures shall be used to determine seizure times.
Eyelid movement data, which is collected concurrently, shall then be analysed for each patient with respect to these annotations. This will be done on an ongoing basis, and as a data set for classification using machine learning once all data has been collected.
Secondary outcome [1] 373571 0
To investigate whether changes to eyelid movements immediately before, during and following epileptic seizures and non-epileptic events can be used to distinguish epileptic seizures from non-epileptic events, using the non-invasive wearable device (“Eagle Wireless Glasses”), which measures ocular parameters using infrared reflectance oculography. Seizures are assessed by expert analysis of video EEG data concurrently recorded with the eyelid movement data. The annotation not only includes the time and duration of a seizure but also whether the seizure is epileptic or non-epileptic in nature.
Timepoint [1] 373571 0
Participants shall have their video EEG and eyelid movement data recorded during their hospital admission for 5 day video EEG monitoring. The video EEG is assessed towards the end of their admission, and a summary of annotated seizures shall be used to determine seizure times.
Eyelid movement data, which is collected concurrently, shall then be analysed for each patient with respect to these annotations. This will be done on an ongoing basis, and as a data set for classification using machine learning once all data has been collected.

Eligibility
Key inclusion criteria
• Is able to provide personally signed and dated informed consent to participate in the study or will have a legally authorized representative sign the informed consent on his or her behalf before completing any study related procedures.
• Male or female (aged 18 years or older).
• Possible diagnosis of epilepsy or non-epileptic events and admitted for inpatient video-EEG monitoring.
• Participants with prescription glasses who can produce a valid lens prescription and can be filled using the standard set of prescription lenses available.
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Participants with prescription glasses who cannot produce a valid lens prescription or have a complex lens prescription that cannot be filled using the standard set of prescription lenses available.

Study design
Purpose of the study
Diagnosis
Allocation to intervention
Non-randomised trial
Procedure for enrolling a subject and allocating the treatment (allocation concealment procedures)
Methods used to generate the sequence in which subjects will be randomised (sequence generation)
Masking / blinding
Who is / are masked / blinded?



Intervention assignment
Single group
Other design features
Phase
Not Applicable
Type of endpoint/s
Statistical methods / analysis
As the primary outcome is sensitivity of seizure detection and great majority of the patients will have at least one epileptic seizure, independent sample size of 600 patients will provide 0.80 power to detect if there is a 3.4% or greater difference between the observed sensitivity and desired 90% sensitivity for simple classification models with significance level of 0.05..

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
16/09/2019
Actual
7/10/2019
Date of last participant enrolment
Anticipated
16/11/2022
Actual
Date of last data collection
Anticipated
22/11/2022
Actual
Sample size
Target
600
Accrual to date
215
Final
Recruitment in Australia
Recruitment state(s)
VIC
Recruitment hospital [1] 14439 0
The Alfred - Melbourne
Recruitment hospital [2] 14440 0
Royal Melbourne Hospital - Royal Park campus - Parkville
Recruitment hospital [3] 22436 0
Sir Charles Gairdner Hospital - Nedlands
Recruitment postcode(s) [1] 27453 0
3004 - Melbourne
Recruitment postcode(s) [2] 27454 0
3052 - Parkville
Recruitment postcode(s) [3] 37654 0
6009 - Nedlands

Funding & Sponsors
Funding source category [1] 303489 0
Commercial sector/Industry
Name [1] 303489 0
Optalert
Country [1] 303489 0
Australia
Funding source category [2] 303491 0
Hospital
Name [2] 303491 0
The Alfred
Country [2] 303491 0
Australia
Funding source category [3] 303492 0
Hospital
Name [3] 303492 0
Royal Melbourne Hospital
Country [3] 303492 0
Australia
Primary sponsor type
Commercial sector/Industry
Name
Otpalert
Address
112 Blamain St
Cremorne, 3121, VIC
Country
Australia
Secondary sponsor category [1] 303550 0
None
Name [1] 303550 0
Address [1] 303550 0
Country [1] 303550 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 304016 0
Alfred Hospital Ethics Committee, EC0031
Ethics committee address [1] 304016 0
The Alfred Hospital 55 Commercial
Road Melbourne, 3004, VIC
Ethics committee country [1] 304016 0
Australia
Date submitted for ethics approval [1] 304016 0
27/07/2019
Approval date [1] 304016 0
19/09/2019
Ethics approval number [1] 304016 0

Summary
Brief summary
In this study, we aim to use eyelid movement data collected from a commercial system from Optalert (Optalert Australia Pty Ltd, Melbourne, Australia) in patients with seizures in order to develop models to detect, predict and classify seizures. The device records eyelid and eye movements using an infrared light emitting diode located on a pair of light weight glasses frames.

Participants admitted for inpatient video-EEG monitoring across the combined Comprehensive Epilepsy Program at The Alfred Hospital and The Royal Melbourne Hospital will be invited to participate in the study. Participants will wear the glasses during wakefulness throughout the monitoring period, which typically lasts five days.

Once the seizure annotations and associated eyelid movements are collected, machine learning shall be used to determine if there is a digital biomarker that can be used to:
1. predict the onset of a seizure,
2. identify the occurrence of a seizure
3. classify the nature of the seizure.
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 95574 0
Prof Terence O'Brien
Address 95574 0
Department of Neurology Level 4 (Central Block) The Alfred Hospital 55 Commercial
Road Melbourne, 3004, VIC
Country 95574 0
Australia
Phone 95574 0
+61 3 9903 0304
Fax 95574 0
Email 95574 0
[email protected]
Contact person for public queries
Name 95575 0
Ms Shobi Sivathamboo
Address 95575 0
Department of Neurology Level 4 (Central Block) The Alfred Hospital 55 Commercial
Road Melbourne, 3004, VIC
Country 95575 0
Australia
Phone 95575 0
+61 3 9903 0304
Fax 95575 0
Email 95575 0
[email protected]
Contact person for scientific queries
Name 95576 0
Ms Shobi Sivathamboo
Address 95576 0
Department of Neurology Level 4 (Central Block) The Alfred Hospital 55 Commercial
Road Melbourne, 3004, VIC
Country 95576 0
Australia
Phone 95576 0
+61 3 9903 0304
Fax 95576 0
Email 95576 0
[email protected]

Data sharing statement
Will individual participant data (IPD) for this trial be available (including data dictionaries)?
No
No/undecided IPD sharing reason/comment
The results of this study will be kept confidential.
The results of this study may be published.


What supporting documents are/will be available?

No Supporting Document Provided



Results publications and other study-related documents

Documents added manually
No documents have been uploaded by study researchers.

Documents added automatically
No additional documents have been identified.