Automated detection of diabetic retinopathy lesions in fundus photos
Official title: Validation of the Artificial Intelligence Subsystem of the DDART Medical Device for the Automated Detection of Lesions Compatible With Diabetic Retinopathy in a Random Sample of Retinal Fundus Photographs
Run by Democritus University of Thrace · NCT07758582 · Data updated 2026-11-12
This study tests a smart imaging system within the DDART device to see if it can reliably spot diabetic retinopathy lesions in color fundus photographs.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 2000 (estimated) |
| Sponsor | Democritus University of Thrace Academic / other |
| Locations | 1 site (Alexandroupoli) |
| Status | Recruiting |
| Started | May 21, 2026 |
| Main results expected | April 19, 2027 |
| Study ends | April 19, 2027 |
| Registry record updated | August 11, 2026 |
| Trial ID | NCT07758582 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults (18+) who have a high-resolution color fundus photograph and a confirmed ophthalmology diagnosis, with images suitable for analysis.
✕Probably not a fit
Patients whose images are of poor quality or have other eye diseases that affect interpretation may not benefit from the AI assessment.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational study validates the AI subsystem of the DDART medical device for automated detection of diabetic retinopathy lesions in retinal fundus images. It uses a random sample of high-quality color fundus photographs to measure how often the AI correctly identifies diabetic retinopathy and how well it distinguishes disease severity. The study compares the algorithm’s performance with assessments by experienced ophthalmologists and reports diagnostic accuracy, sensitivity, specificity, and ROC-AUC. No interventional treatment is administered; the focus is on diagnostic performance of the AI tool. Eligible participants are adults with available high-resolution fundus images, while images of poor quality or with interfering ocular diseases are excluded.
Why it matters
Potential benefit: If successful, this AI subsystem could help clinicians quickly and consistently screen for diabetic retinopathy using retinal images.
How similar studies have gone: Prior work in automated retinal image analysis has shown promise in detecting diabetic retinopathy, but this study evaluates a specific DDART AI subsystem against expert readers.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria Age ≥18 years Availability of a high-resolution color fundus photograph Confirmed diagnosis established by an ophthalmology specialist Exclusion Criteria Poor-quality retinal images Concomitant ocular diseases that interfere with image interpretation
Where it's running
-
University Hospital of Alexandroupolis
Alexandroupoli, Greece Recruiting
Study contacts
- Study coordinator: Georgios Labiris
- Email: glampiri@med.duth.gr
- Phone: +302551030990
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Corticosteroid for Diabetic Macular Edema (DME) in Adults with Diabetic Retinopathy
This trial tests whether intravitreal corticosteroid injections can influence inflammatory biomarkers and improve DME in adults with type 2 diabetes.
-
Retinal microvascular changes in diabetic retinopathy measured with OCTA
This observational study tests how retinal blood vessel patterns seen on OCTA relate to vision and blood sugar control in adults with diabetic retinopathy.
-
MK-8748 vs. aflibercept for diabetic macular edema
This trial tests whether the investigational medicine MK-8748 can treat diabetic macular edema as well as the standard treatment aflibercept in adults with diabetes.
-
MK-8748 vs aflibercept for diabetic macular edema
This trial tests whether MK-8748 can treat diabetic macular edema as well as the standard treatment aflibercept in people with diabetes.
-
Surabgene Lomparvovec in the Suprachoroidal Space for Diabetic Retinopathy
This study tests a one-time gene therapy called surabgene lomparvovec to see if it can help adults with non-proliferative diabetic retinopathy avoid vision-threatening events.
-
RO7663498 eye injection safety in diabetic retinopathy
This study tests the safety, tolerability, and how the drug behaves in the body after an intravitreal injection for people with diabetic retinopathy.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.