Trial Review

Technical difficulties have been reported by some users of the search function and is being investigated by technical staff. Thank you for your patience and apologies for any inconvenience caused.

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
ACTRN12623001174673
Ethics application status
Approved
Date submitted
27/09/2023
Date registered
14/11/2023
Date last updated
14/11/2023
Date data sharing statement initially provided
14/11/2023
Type of registration
Retrospectively registered

Titles & IDs
Public title
Assessing cardiovascular disease risk from retinal images using artificial intelligence at primary care settings
Scientific title
Assessing cardiovascular risk by integrating retinal photography and artificial intelligence at primary care settings
Secondary ID [1] 310695 0
Nil known
Universal Trial Number (UTN)
Trial acronym
Linked study record

Health condition
Health condition(s) or problem(s) studied:
Cardiovascular disease risk assessment 331603 0
Retinal assessment 331888 0
Condition category
Condition code
Cardiovascular 328340 328340 0 0
Other cardiovascular diseases
Eye 328618 328618 0 0
Normal eye development and function

Intervention/exposure
Study type
Interventional
Description of intervention(s) / exposure
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. Retinal images taken will then be transferred to an artificial intelligence system that we are testing and a retina-predicted cardiovascular disease (CVD) risk score will be generated. Image quality will be assessed by the artificial intelligence system before generating the retina-predicted CVD risk score. If the image quality is ungradable, the retina-predicted CVD risk score will be shown as not applicable. Besides retinal photography, participants will be asked to complete a health survey, and a satisfaction survey about their experiences of using the artificial intelligence system. Information used for well-established CVD risk score calculation, including blood pressure and lipid results is collected. If lipids are not available, research assistants will measure the weight and height of the participants. The whole session requires a once-off visit of 40 minutes to one hour. The trial is carried out at general practitioner clinics. Adherence will be determined by the completion status on the RedCap platform which is recorded by the research assistants.
Intervention code [1] 327098 0
Early detection / Screening
Intervention code [2] 327269 0
Prevention
Comparator / control treatment
No control group
Control group
Uncontrolled

Outcomes
Primary outcome [1] 336192 0
The diagnostic accuracy of retina-predicted cardiovascular disease (rpCVD) risk score for detecting moderate/high CVD risk
Timepoint [1] 336192 0
Assessed at the conclusion of the study.
Primary outcome [2] 336193 0
The reliability of retina-predicted cardiovascular disease (rpCVD) risk score by comparing with well-established risk-factor-based cardiovascular disease risk calculators
Timepoint [2] 336193 0
Assessed at the conclusion of the study.
Secondary outcome [1] 427275 0
The satisfaction of patients using the retina-predicted cardiovascular disease (rpCVD) screening model.
Timepoint [1] 427275 0
Assessed immediately after the patient uses the artificial intelligence system and receives the report during the once-off visit.
Secondary outcome [2] 427276 0
The proportion of moderate/high risk participants detected by the retina-predicted cardiovascular disease (rpCVD) screening model
Timepoint [2] 427276 0
Assessed at the conclusion of the study.
Secondary outcome [3] 428308 0
The feasibility of the retinal-predicted cardiovascular disease risk score screening system in primary care clinics.
Timepoint [3] 428308 0
Assessed at the conclusion of the study.
Secondary outcome [4] 428792 0
The satisfaction of support staff and health-care providers using the retina-predicted cardiovascular disease (rpCVD) screening model.
Timepoint [4] 428792 0
Assessed at the conclusion of the study at specific study sites.

Eligibility
Key inclusion criteria
Patients who have completed all or parts of a cardiovascular disease risk assessment in the past six months and are aged between 45 and 70 years old, will be identified by the research team as eligible to participate.
Minimum age
45 Years
Maximum age
70 Years
Sex
Both males and females
Can healthy volunteers participate?
No
Key exclusion criteria
Participants with medical conditions necessitating immediate or urgent medical interventions.

Study design
Purpose of the study
Prevention
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
Efficacy
Statistical methods / analysis
All rpCVD will be compared with well-established risk-factor-based CVD risk scores. The well-established risk score will be considered as the reference standard for the accuracy of the rpCVD. The indicators for accuracy include sensitivity, specificity, accuracy, positive and negative predictive value, and area under curve (AUC). The indicators for reliability include limits of agreement between rpCVD and well-established risk factors, mean absolute error for continuous risk values, and kappa statistic for categorical risk levels.

Assessment of end-user acceptability will be determined by the positive response rate/screening rate. The responses to the 5-point Likert scale question will be analysed using the “document variable statistics” function in MAXQDA software. Data from the open-ended questionnaire will be analysed thematically. All themed information will be shared for review by the project steering committee.

Recruitment
Recruitment status
Recruiting
Date of first participant enrolment
Anticipated
Actual
19/06/2023
Date of last participant enrolment
Anticipated
30/06/2024
Actual
Date of last data collection
Anticipated
30/06/2024
Actual
Sample size
Target
600
Accrual to date
227
Final
Recruitment in Australia
Recruitment state(s)
VIC

Funding & Sponsors
Funding source category [1] 314912 0
Government body
Name [1] 314912 0
National Health and Medical Research Council (NHMRC) Medical Research Future Fund
Country [1] 314912 0
Australia
Funding source category [2] 315109 0
Commercial sector/Industry
Name [2] 315109 0
Eyetelligence Pty Ltd
Country [2] 315109 0
Australia
Primary sponsor type
Other
Name
Centre for Eye Research Australia
Address
Level 7/32 Gisborne St, East Melbourne VIC 3002
Country
Australia
Secondary sponsor category [1] 316919 0
None
Name [1] 316919 0
Address [1] 316919 0
Country [1] 316919 0

Ethics approval
Ethics application status
Approved
Ethics committee name [1] 313904 0
St Vincent’s Hospital (Melbourne) Human Research Ethics Committee
Ethics committee address [1] 313904 0
41 Victoria Parade Fitzroy VIC 3065
Ethics committee country [1] 313904 0
Australia
Date submitted for ethics approval [1] 313904 0
17/01/2023
Approval date [1] 313904 0
23/02/2023
Ethics approval number [1] 313904 0

Summary
Brief summary
Researchers at the Centre for Eye Research Australia (CERA) in collaboration with industry partner Eyetelligence Pty Ltd have developed a system integrating retinal photography and artificial intelligence (AI) to predict the risk of heart diseases. The retina is located at the back of the eye and has the important ability to sense vision. When the retina is photographed, it shows small vessels that can indicate the health of your heart. The cardiovascular disease (CVD) risk score refers to the probability of developing CVD events in the future. This project aims to assess the real-world impact, accuracy, and feasibility of the rpCVD screening system in primary care settings in Australia.
Trial website
Trial related presentations / publications
Public notes

Contacts
Principal investigator
Name 129738 0
Prof Mingguang He
Address 129738 0
Level 7/32 Gisborne St, East Melbourne VIC 3002, Centre for Eye Research Australia
Country 129738 0
Australia
Phone 129738 0
+610399298361
Fax 129738 0
Email 129738 0
mingguang.he@unimelb.edu.au
Contact person for public queries
Name 129739 0
Prof Mingguang He
Address 129739 0
Level 7/32 Gisborne St, East Melbourne VIC 3002, Centre for Eye Research Australia
Country 129739 0
Australia
Phone 129739 0
+610399298361
Fax 129739 0
Email 129739 0
mingguang.he@unimelb.edu.au
Contact person for scientific queries
Name 129740 0
Prof Mingguang He
Address 129740 0
Level 7/32 Gisborne St, East Melbourne VIC 3002, Centre for Eye Research Australia
Country 129740 0
Australia
Phone 129740 0
+610399298361
Fax 129740 0
Email 129740 0
mingguang.he@unimelb.edu.au

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.