Actively Recruiting
Prediction of Incident Atherosclerotic Cardiovascular Disease From Retinal Photographs Via Deep Learning
Led by Yonsei University · Updated on 2021-02-11
2400
Participants Needed
1
Research Sites
N/A
Total Duration
On this page
AI-Summary
What this Trial Is About
Researchers are studying how deep learning algorithms can predict body measurements and cardiovascular disease risk using retinal (fundus) photographs. This observational study focuses on people with various cardiovascular conditions such as heart attack, heart failure, hypertension with organ damage, high-risk dyslipidemia, and diabetes. It aims to validate the ability of these algorithms to predict cardiovascular events over time. Participants will have fundus photographs taken twice during the first year and again two years later. The study will follow major cardiovascular events for five years to assess the prediction accuracy of the deep learning model. This study does not involve drug or device treatments but focuses on image analysis and risk prediction. During the study, participants will undergo retinal photography and clinical evaluations related to their cardiovascular health. The main outcome measured is the occurrence of major adverse cardiovascular disease events within four years. Researchers will monitor participants' health data over several years to verify the algorithm's predictive ability and collect follow-up information to support long-term analysis.
CONDITIONS
Brief Title
Deep Learning of Retinal Photographs and Atherosclerotic Cardiovascular Disease
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Adults aged 20 to 79 years
- Diagnosed with myocardial infarction within 5 years confirmed by cardiovascular angiography
- Heart failure with reduced ejection fraction (less than 40%) detected by echocardiography or MRI
- Heart failure with preserved ejection fraction (40% or more) with specific heart function markers
- High risk subclinical atherosclerosis with defined artery stenosis or plaques on imaging
- Hypertension with target organ damage as defined by proteinuria, heart changes, arterial stiffness, kidney function, or brain MRI findings
- High risk dyslipidemia with LDL cholesterol above set thresholds despite statin use
- Type 2 diabetes diagnosed more than 5 years ago or type 1 diabetes diagnosed more than 10 years ago
- Low risk hypertension or dyslipidemia controlled under specified medication or cholesterol levels
You will not qualify if you...
- Serious eye diseases preventing good quality fundus photography
- Inability to read and sign the consent form in person
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
Duration - Initial assessment period
Participants undergo retinal photography and cardiovascular assessments to collect data for deep learning analysis.
1 visit (in-person)
Duration - Up to 4 years
Participants are monitored for up to 4 years to observe the incidence of major adverse cardiovascular disease.
Periodic visits depending on study protocol
Trial Site Locations
Total: 1 location
1
Yonsei University College of Medicine
Seoul, South Korea, 03722
Actively Recruiting
Research Team
S
Sungha Park
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
0
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here