Doctors are testing a new machine learning algorithm at Aravind Eye Hospital in Madurai, India. With India’s doctor shortage and large diabetes problem, this new technology will aid in creating better diabetes care.
How does it work?
Technicians simply take an image of the patient’s eyes with a fundus camera (a special microscope with a camera attached that takes a picture of the retina), and the algorithm can detect if the patient needs to see an eye doctor for treatment. The algorithm uses artificial intelligence (AI), which is when computers are trained to do things usually done by human intelligence, such as making decisions and visual perception.
What is diabetic retinopathy?
Over time, diabetes can take its toll on the eyes and cause eye problems due to consistently high blood sugar which damages the blood vessels within the eyes. Diabetic retinopathy is a common side effect of diabetes and a leading cause of blindness. There are close to 415 million people at risk of diabetic retinopathy around the world. But if caught early enough, diabetic retinopathy can be treated.
Algorithms like this can be very beneficial, especially in undeveloped communities where there are not enough doctors. This machine learning software could screen thousand of people for diabetic eye disease in a short amount of time. This will save time and money for patients, doctors, and insurers alike.
“By integrating Verily and Google’s retinal diagnostic program into our screening process, we can improve our efficiency, giving physicians like myself more time to work closely with patients on treatment and management of their disease while increasing the volume of screenings we can perform,” said Dr. R. Usha Kim, Chief of Retina Services at Aravind Eye Hospital.
With rates of diabetes skyrocketing across the world, new technology like this from Google and Verily will help make treatment quicker and more efficient overall.