Assessing of Artificial Intelligence-based Software Platform for Diabetic Retinopathy Screening

The Filatov Institute of Eye Diseases and Tissue Therapy200 enrolled

Overview

To examine the potential for the detection of diabetic retinopathy (DR) using the artificial intelligence (AI)-based software platform Retina-AI.

Operator took fundus images with a non-mydriatic fundus camera as per the Retina-AI CheckEye imaging protocol (an optic disc centered image and a fovea centered image for each eye).Thereafter, operator uploaded fundus images in the AI system for processing by the neural network.

Study Type

OBSERVATIONAL

Enrollment

200

Conditions

Diabetic Retinopathy

Interventions

taking fundus photos using non-mydriatic fundus cameraDEVICE

using artificial intelligence to identify diabetic retinopathy in the early stages using fundus photography.

Eligibility

Sex: ALLMin age: 18 YearsMax age: 90 YearsHealthy volunteers:

Medical Language ↔ Plain English

Inclusion Criteria: 1. Documented diagnosis of diabetes mellitus by definition. 2. Understanding of the Study and willingness and ability to sign informed consent 3. Patient age 18 or above 4. Diagnostic for diabetes: 4a) Type 1 diabetes of a lest 5 years of evolution; or 4b) Type 2 diabetes Exclusion Criteria: -1. Patients under 18 years of age; 2. Failure to give informed consent; 3. Presence of retinal diseases - acquired disease: age-related macular degeneration (AMD), occlusion of retinal vessels (ORV), etc.; birth defects: coloboma of choroid or optic nerve disc, etc.; hereditary diseases: retinitis pigmentosa, angioid streaks of the retina, etc. 4\. A patient who has already undergone treatment (surgery, laser, etc.) for any disease of the retina: age-related macular degeneration (AMD), retinal vascular occlusion (ARV), etc. These patients should be excluded or allocated to a separate group.

Locations (1)

The Filatov Institute of Eye Diseases and Tissue Therapy

Odesa, Ukraine

RECRUITING

Outcomes

Primary Outcomes

The accuracy

The accuracy of detecting of DR

Time frame: Baseline

Secondary Outcomes

The percent of invalid images

The percent of invalid images for analysing by neural network

Time frame: Baseline

The percent of false positive detection of DR

The percent of false positive detection of DR in individuals without DR

Time frame: Baseline

Central Contacts

Andrii MD Korol, PhD

CONTACT

380936327266 andrii.r.korol@gmail.com

Olha MD Pohosian

CONTACT

380932084927 olha.a.pohosian@gmail.com

Data from ClinicalTrials.gov

This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.