Diabetic Retinopathy (DR) is a complication of diabetes that results in blindness. This type of blindness is the leading cause of preventable blindness in the world, but nearly 50% of all cases go undiagnosed. Sixteen-year-old Kavya Kopparapu was personally affected by DR when her grandfather was diagnosed. Kavya was quoted stating that diagnosis of DR is the biggest challenge for this disease. Kavya put her skills in computer science to work and has invented a simple, yet inexpensive tool to diagnose DR: Eyeagnosis.
The standard diagnosis for DR involves an advanced retinal imaging machine that takes photos of the back of the eye. The cost of equipment and availability of trained staff members creates an inaccessible procedure for many affected individuals. In response to the inaccessibility of this technology, Kavya developed a smartphone app that can screen for the disease with the help of a specially trained artificial intelligence program and 3D printed lens attachment. Kavya trained the neural network to recognize pictures of what DR looks like, and created a database of 34,000 retinal scans from the National Institute of Health (NIH).
Eyeagnosis still requires a scan to diagnose, but does so without a large, costly machine. The scan is completed through an app that uses a simple 3D printed lens that concentrates light from the smartphone camera flash on the back of the eye. Kavya has begun testing Eyeagnosis on human patients. While the data is still limited, the future is bright for Eyeagnosis.
Once this product has been made available for wide spread use, it could be the step toward bringing the 50% undiagnosed cases of DR down to 0%.