When 16-year-old Kavya Kopparapu went back to school after the summer break in 2016, she wanted to put to use her newly acquired knowledge of computer science. And she thought, what better way to use it than for the good of her grandfather, who was suffering from diabetic retinopathy, a complication of diabetes that damages blood vessels in the retina and can lead to complete loss of vision.
What came off her efforts was Eyeagnosis, a smartphone app along with a 3D-printed lens that cuts the diagnostic procedure from a two-hour examination requiring a multi-thousand-dollar retinal image to a quick photo snapped with a phone, says a blog post on IEEE.
Kavya’s team, which includes her 15-year-old brother, Neeyanth, and her classmate Justin Zhang, worked on an artificial intelligence system to recognize signs of diabetic retinopathy in photos of eyes and offer a preliminary diagnosis. They presented the project at the O’Reilly Artificial Intelligence conference, in New York City, last month.
Her grandfather was cured of the problem before it could worsen, thanks to the timely intervention by the doctors. Kavya realised that time and diagnosis were of essence. She says,
The lack of diagnosis is the biggest challenge. In India, there are programmes that send doctors into villages and slums, but there are a lot of patients and only so many ophthalmologists. What if there were a cheap, easy way for local clinicians to find new cases and refer them to a hospital?
J. Fielding Hejtmancik, an expert in visual diseases at the National Institutes of Health (NIH), was elated about the discovery. He said,
The device is ideal for making screening much more efficient and available to a broader population. These kids have put things together in a very nice way; it’s a bit cheaper and simpler than most [systems designed by researchers]—who, by the way, all have advanced degrees!
A resident of Herndon, Virginia, US, Kavya started her project by googling about the existence of such a technology anywhere in the world. Eventually, she wrote to ophthalmologists, computational pathologists, biochemists, epidemiologists, neuroscientists, physicists, and experts in machine learning. She says,
I went home and taught myself Java, HTML, Python, C, my mom had to tear me away from the computer as I’d forget to eat most of the times.
Speaking about the implementation of the project, Hejtmancik says,
There’s a long road to clinical adoption. What she’s going to need is a lot of clinical data showing that Eyeagnosis is reliable under a variety of situations: in eye hospitals, in the countryside, in clinics out in the boonies of India. The only problem I see is that it’s so cheap that big companies might not see the potential for a profit margin. But that affordability is exactly what you want in medical care, in my opinion.