AI Summary
Sixteen-year-old Kavya Kopparapu developed Eyeagnosis, an AI-based system to detect diabetic retinopathy, after her grandfather in India was diagnosed with this vision-threatening complication of diabetes.
The system uses machine learning techniques and a 3D-printed lens attachment with a smartphone app to automatically screen for diabetic retinopathy.
Eyeagnosis transforms the diagnostic procedure from a 2-hour exam requiring a multi-thousand-dollar retinal imager to a quick photo snap with a phone.
Testing at Mumbai’s Aditya Jyot Eye Hospital showed the system delivered 100% accurate results in five patients.
Of 415 million diabetics worldwide, one-third will develop retinopathy, with 50% going undiagnosed and half of severe cases going blind in five years.
The lack of diagnosis is the biggest challenge in India, where programs send doctors to villages but there are many patients and few ophthalmologists. This affordable screening solution could dramatically improve access to eye care in underserved communities where trained specialists are scarce.