Trial Review

Registering a new trial?

To achieve prospective registration, we recommend submitting your trial for registration at the same time as ethics submission.

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
ACTRN12624000982516
Ethics application status
Approved
Date submitted
6/07/2024
Date registered
13/08/2024
Date last updated
13/08/2024
Date data sharing statement initially provided
13/08/2024
Type of registration
Prospectively registered

Titles & IDs
Public title
Retinal red flag screening for headache in the emergency department
Scientific title
Artificial Intelligence Powered Smart Camera to Screen “Red Flags” for Life-Threatening Headache at the Point-of-Care in the Emergency Department Patients
Secondary ID [1] 312463 0
Nil known
Universal Trial Number (UTN)
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
headache 334298 0
optic disc edema 334299 0
retinal assessment 334300 0
Condition category
Condition code
Emergency medicine 330952 330952 0 0
Other emergency care
Neurological 330953 330953 0 0
Other neurological disorders
Eye 330954 330954 0 0
Diseases / disorders of the eye

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure

The smart camera is a portable and fully automated non-mydriatic retinal camera that will be integrated with an AI model to detect retinal red flags. It guides patients through the retinal imaging process with voice prompts. The associate investigator will provide three hours of face-to-face training two weeks before the first participant enrollment.
Upon consent, participants will undergo non-mydriatic retinal photography for both eyes. Participants will not be dilated and images will be taken for both eyes. A trained clinical trial research assistant of the research team will take the retinal images for the participants, which takes around 5-10 minutes. If the image quality is insufficient (graded as "ungradable" by the artificial intelligence system), research assistants will try up to three attempts to get good-quality images. The session will be delivered in a one-on-one and face-to-face mode. The fundus images obtained will be uploaded and reviewed by an ophthalmologist within 96 hours. The ophthalmologist will assess the quality of images captured by the Smart Camera, and provide grading notes for the images and follow-up recommendations. If the ophthalmologist finds any issues that need further follow-up by eye care practitioners, the participant will be informed via email or through postal mail. By the end of this trial, all fundus images will be run through the AI algorithm and AI grading results will be generated. Besides retinal photography, participants will be asked to complete a socio-demographic/headache survey during the visit, and a satisfaction survey about their experiences of using the screening system during the visit or through email if not completed on site. Adherence will be determined by the completion status on the RedCap platform which is recorded by the research assistants.
The focus group interviews aim to gain a deeper understanding of perceptions regarding the Smart Camera screening service, including the facilitators and barriers to using this system in real-world practice. By the end of this trial, participants and clinicians or support staff will be randomly selected to participate in focus groups and/or in-depth interviews. The size of each group will not exceed 10 people. The maximum number of participants will be determined when the thematic saturation is reached. The focus groups interviews will be conducted by qualitative research experts from our research group.
Intervention code [1] 328971 0
Early detection / Screening
Comparator / control treatment
No control group
Control group
Uncontrolled

Outcomes
Primary outcome [1] 338723 0
Assessment of feasibility of the retinal screening in the ED
Timepoint [1] 338723 0
Upon conclusion of the study
Primary outcome [2] 338724 0
Assessment of the diagnostic accuracy of the AI algorithm
Timepoint [2] 338724 0
Upon conclusion of the study
Primary outcome [3] 338965 0
Assessment of end-user acceptability and satisfaction of the retinal screening in the ED
Timepoint [3] 338965 0
Upon conclusion of the study
Secondary outcome [1] 437126 0
Assessment of the impact of the Smart Camera screening system
Timepoint [1] 437126 0
Upon conclusion of the study

Eligibility
Key inclusion criteria
Patients in the Emergency Department who meet the following criteria are considered eligible for the study.
(1) are 18 years or older;
(2) are able to give informed consent and adhere to study procedures;
(3) have English language capacity;
(4) have a chief complaint of headaches;
(5) have been triaged as level 3 to 5 on the Australasian Triage Scale, an index of clinical urgency from 1 that requires immediate assessment and treatment to 5 that can be assessed and treated within 2 hours.
Minimum age
18 Years
Maximum age
No limit
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Patients who meet any of the following criteria will not be included in the study:
(1) have unstable vital signs;
(2) have a change in consciousness level;
(3) are unable to comply with the requirements of informed consent or the screening protocol.

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
Open (masking not used)
Who is / are masked / blinded?



Intervention assignment
Single group
Other design features
Phase
Not Applicable
Type of endpoint/s
Statistical methods / analysis
1) Descriptive statistics (mean and standard deviation, median and interquartile range, or frequency and percent) will be provided for participant characteristics and presented according to study site.
2) Descriptive statistics (e.g. numbers and percentages) will be used to summarise user-experience survey responses.
3) Diagnostic accuracy parameters (overall accuracy, sensitivity, specificity, positive predictive value, negative predictive value) will be presented with 95% confidence intervals to assess the ability of the Smart Camera algorithm to detect optic disc oedema.
4) Regression-based methods (such as logistic and log-binomial regression) will be used to identify the influential factors for the positive response rate and satisfaction rate, and to explore the differences in detection of life-threatening conditions and in diagnostic testing patterns between participants with and without optic disc oedema detected.
All statistical analyses will be performed using Stata (StataCorp, Texas, USA) or equivalent specialised statistical software program.

Recruitment
Recruitment status
Not yet recruiting
Date of first participant enrolment
Anticipated
1/09/2024
Actual
Date of last participant enrolment
Anticipated
Actual
Date of last data collection
Anticipated
Actual
Sample size
Target
200
Accrual to date
Final
Recruitment in Australia
Recruitment state(s)
VIC

Funding & Sponsors
Funding source category [1] 316877 0
Charities/Societies/Foundations
Name [1] 316877 0
Ramaciotti Health Investment Grant
Country [1] 316877 0
Australia
Primary sponsor type
Charities/Societies/Foundations
Name
Centre for Eye Research Australia
Address
Country
Australia
Secondary sponsor category [1] 319123 0
None
Name [1] 319123 0
Address [1] 319123 0
Country [1] 319123 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 315638 0
Western Health Ethics Committee
Ethics committee address [1] 315638 0
Office for Research Level 3 Western Centre for Health, Research & Education (CHRE) Building Sunshine Hospital, 176 Furlong Road, St Albans VIC 3021
Ethics committee country [1] 315638 0
Australia
Date submitted for ethics approval [1] 315638 0
Approval date [1] 315638 0
11/07/2024
Ethics approval number [1] 315638 0

Summary
Brief summary
Headache is the fourth most common chief complaint in the ED. Optic disc oedema, characterized by optic nerve swelling from intracranial hypertension, is one of the most important red flags that prompts timely further evaluation of life-threatening headache.
However, examination of the optic nerve is infrequently and poorly performed by ED physicians. While artificial intelligence has enabled the automated detection of optic disc oedema from retinal images, these AI systems have not been clinically validated in real-world settings. A group of researchers from the Centre for Eye Research Australia, Monash and Melbourne university have worked with Eyetelligence Ltd to develop the world’s first hardware-software integrated system (i.e. AI-powered Smart Camera) to screen the retinal red flag of headache automatically.
We hypothesize that the Smart Camera system will demonstrate reasonably good feasibility, accuracy and end-user acceptance in screening for red flags of life-threatening headache in the Emergency Department.
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 135342 0
A/Prof Zhuoting Zhu
Address 135342 0
Centre for Eye Research Australia, Level 7, 32 Gisborne St, East Melbourne VIC 3002
Country 135342 0
Australia
Phone 135342 0
+61 469747024
Fax 135342 0
Email 135342 0
[email protected]
Contact person for public queries
Name 135343 0
Zhuoting Zhu
Address 135343 0
Centre for Eye Research Australia, Level 7, 32 Gisborne St, East Melbourne VIC 3002
Country 135343 0
Australia
Phone 135343 0
+61 469747024
Fax 135343 0
Email 135343 0
[email protected]
Contact person for scientific queries
Name 135344 0
Zhuoting Zhu
Address 135344 0
Centre for Eye Research Australia, Level 7, 32 Gisborne St, East Melbourne VIC 3002
Country 135344 0
Australia
Phone 135344 0
+61 469747024
Fax 135344 0
Email 135344 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


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.