Validation of an Automatic Analysis Algorithm of the Referable Diabetic Retinopathy From Fundus Images
Study Details
Study Description
Brief Summary
Diabetic retinopathy (DR) is a leading cause of vision loss globally. Of an estimated 285 million people with diabetes mellitus worldwide, approximately one-third have signs of DR and of these, a further one-third of DR is vision-threatening DR, including diabetic macular edema (DME). Diabetic retinopathy is a retinal disease that can often be stopped with early diagnosis, but if neglected, it can lead to severe vision loss, including permanent blindness. Diabetes has high morbidity and there are millions of people who should be screened for diabetic retinopathy (DR). Annual eye screening is recommended for all diabetic patients since vision loss can be prevented if DR is diagnosed in its early stages. Currently, the number of clinical personnel trained for DR screening is less than that needed to screen a growing diabetic population. Therefore, the automatic DR screening system will be able to screen more diabetic patients and diagnose them early.
Condition or Disease | Intervention/Treatment | Phase |
---|---|---|
|
Detailed Description
Diabetic Retinopathy (DR) is the leading cause of vision loss in adults aged 20-74 years [1]. Diabetic retinopathy (DR) is the most common cause of blindness in the working population of the United States [2].
Diabetic retinopathy (DR) is responsible for causing up to 24,000 Americans to go blind annually, according to the U.S. Centers for Disease Control and Prevention (CDC). Yet this is a preventable problem. Early detection and treatment can prevent or delay blindness due to DR in 90 percent of people with diabetes, but 50 percent or more don't get their eyes examined or are diagnosed too late for effective treatment, the CDC reports. [3] From 1990-2010, DR ranked as the fifth most common cause of preventable blindness and the fifth most common cause of moderate to severe visual impairment [4]. In 2010, of an estimated 285 million people worldwide with diabetes, over one-third have signs of DR, and a third of these are afflicted with vision-threatening diabetic retinopathy (vtDR), defined as severe non-proliferative DR or proliferative DR (PDR) or the presence of diabetic macular edema (DME) [5]. These estimates are expected to rise further due to the increasing prevalence of diabetes, aging of the population, and increasing life expectancy of those with diabetes. While recent improvement in diabetes treatment has decreased macrovascular mortality, more patients with diabetes live long enough for DR and vision-threatening diabetic retinopathy (vtDR) to develop.[6] Key research related to eye screening rates for people with diabetes concluded that screening rates remain poor. A 1990 program launched by the American Academy of Ophthalmology (AAO), known as Diabetes 2000, was designed to increase nationwide DR screening rates. However, after 20 years of implementation, screening rates continue to stagnate, with only 50-60% of diabetic patients properly evaluated [7].
An automated screening device would allow for immediate screening results at the point of care, standardization of results, and elimination of most overhead costs associated with telemedicine. Leaders in the ophthalmic community report that an automated diabetic retinopathy screening device in the hands of front-line providers would increase screening rates and detect more treatable vision-threatening retinopathy [8].
Study Design
Outcome Measures
Primary Outcome Measures
- To determine the sensitivity and specificity of EyeCheckup to detect more than mild diabetic retinopathy in the primary care setting [1 visit (1 day)]
The performance of EyeCheckup will be evaluated using sensitivity and specificity measures.
- To determine the sensitivity and specificity of EyeCheckup to detect vision-threatening diabetic retinopathy in the primary care setting [1 visit (1 day)]
The performance of EyeCheckup will be evaluated using sensitivity and specificity measures.
Secondary Outcome Measures
- Accuracy of diagnosis with artificial intelligence algorithm and comparison of this result with ETDRS certified graders. [1 visit (1 day)]
Eligibility Criteria
Criteria
Inclusion Criteria:
-
A diagnosis of diabetes mellitus
-
Understanding of study and provision of written informed consent
-
22 years of age or older
-
No history of any other retinal vascular disease, glaucoma, or another disease that may affect the appearance of the retina or optic disc (refractive error and ocular surface disease are allowed)
-
Other than cataract surgery, no history of intraocular surgery, ocular laser treatments for any retinal disease, or ocular injections for diabetic macular edema or proliferative disease -No media opacity precluding good retinal photography
Exclusion Criteria:
-
No diagnosis of diabetes mellitus
-
Potential subject cannot understand study or informed consent
-
A history of retinal vascular disease other than due to diabetic retinopathy, glaucoma, or other disease that may affect the appearance of the retina or optic disc
-
Previous intraocular surgery other than cataract; previous laser to the retina; or previous intraocular injections for the treatment of diabetic retinopathy
-
Pregnant women or women with gestational diabetes mellitus
-
A media opacity in either eye that is severe enough to preclude good retinal photography
-
Permanent vision impairment in one or both eyes
-
The participant is contraindicated for imaging with fundus imaging systems used in the study:
-
Participant is hypersensitive to light
-
Participant recently received photodynamic therapy (PDT)
-
Participant uses drugs that cause photosensitivity
Contacts and Locations
Locations
No locations specified.Sponsors and Collaborators
- URAL Telekomunikasyon San. Trade Inc.
Investigators
None specified.Study Documents (Full-Text)
None provided.More Information
Publications
None provided.- EC-2023DR