Recent advances in AI have shown that AI can accurately detect diabetes through the analysis of retinal images that retinal experts would consider healthy. To better understand this feat, it’s worth taking a step back to understand the context and magnitude of the feat.
diabetes mellitus is a chronic health condition that affects the body’s ability to metabolize glucose, resulting in high sugars in the bloodstream. Over time, elevated blood sugar levels can lead to serious health problems, including heart disease, kidney failure, vision loss, and even death. In addition, the longer it takes patients to be diagnosed and treated, the more likely they are to develop such irreversible complications. Therefore, early diagnosis, even when a patient is asymptomatic, is critical to maintaining overall health and preventing adverse outcomes.
Despite the high prevalence of diabetes, 23%-27% of all diabetic adults in the United States remain undiagnosed. The underdiagnosis of diabetes can be attributed to several factors. First and foremost is the lack of regular health checks. Underserved populations with limited access to basic health care are much more likely to go undiagnosed simply because they lack basic access to screening and diagnostic services. Unfortunately, they are also at a higher risk of developing diabetes to begin with because of the increased prevalence of obesity. Another factor is the lack of public awareness of the symptoms of diabetes; those who are unaware of the symptoms are less likely to see a doctor when they appear.
Fasting glucose and glycosylated hemoglobin – also known as HbA1c – blood tests are the most established and accepted tools for diagnosing diabetes. Still, ophthalmologists are often the first to diagnose diabetes as a coincidental finding on visits for other reasons. The ophthalmologist usually detects signs of diabetic retinopathy – a common diabetes complication – and, as a result, suspects that the patient has diabetes and refers the patient to further investigations leading to a diabetes diagnosis. Nevertheless, this means that ophthalmologists who detect signs of diabetes are diagnosing a disease that has been present for a long time — long enough for diabetes complications to manifest. Additional examples where complications of diabetes can be detected and lead to diabetes diagnosis include periodontitis detected by dentists and foot and ankle disorders detected by podiatrists.
A groundbreaking artificial intelligence (AI) model recently developed by AEYE Health demonstrates the ability to accurately diagnose patients with diabetes based on retinal images otherwise considered free of diabetes-related complications. In other words, the AI can detect signs of diabetes in images that retina experts consider healthy. Retinal specialists can generally diagnose diabetes from retinal images if the complications associated with diabetes are visible on the images. However, the AI algorithm can diagnose diabetes from otherwise healthy retinas, which generally means an earlier stage of diabetes and the ability to get the right treatment and reduce complications before they occur.
Most AI models have been developed to perform the same tasks as doctors, ie try to replicate what doctors look for when analyzing images. But in the case of the AI developed by AEYE HealthAI is trained to perform tasks that are beyond the common domain of physicians’ capabilities.
This is revolutionary for a number of reasons, the most important of which is to enable early diagnosis of diabetes and reduce the number of undiagnosed diabetics. By deploying this AI in pharmacies and community clinics, people can test themselves quickly, cheaply and without drawing blood. No less important is the fact that AI is now able to extend the diagnostic capabilities currently available. Diabetes can be detected by pictures of the retina, even though retinal specialists cannot see the indicators of the disease.
About Dr. Zack Dvey-Aharon† PhD
dr. Zack Dvey-Aharon, Ph.D. is an international AI expert, serial entrepreneur, and co-founder and CEO of AEYE Health, a company with a mission to develop accurate, practical and accessible AI solutions to diagnose a wide variety of diseases based on retinal images. Earlier this year, AEYE Health published the results of its first pivotal clinical trial focused on the diagnosis of diabetic retinopathy.