Verily is putting its new algorithm to real-world use. The company is undertaking a pilot at the Aravind Eye Hospital in Madurai, India. The process, Engadget reports, involves screening patients eyes, by taking images using a low-power fundus camera and microscope. The images are then scanned by the algorithm to assess eye disease. Fundus refers to the back of the eye.
Two diseases of the eye are screened for. The first is diabetic retinopathy. This is a medical condition in which damage occurs to the retina due to diabetes mellitus. It is one of the world’s leading cause of blindness. Through the use of the image analysis, microaneurysms (microscopic blood-filled bulges in the artery walls) can be seen.
The second eye disease examined is diabetic macular edema. This is the build-up of fluid in the macula, an area in the center of the retina. Fluid buildup causes the macula to swell and thicken, which distorts vision.
By detecting either of these eye diseases sufficiently early, medics can prevent the blindness that can arise from such conditions. The advantage of using the artificial intelligence is that it can catch eye diseases earlier, and it can detect signs of the diseases that might be missed by doctors.
Dr. R. Kim, chief medical officer and chief of retina services at the Aravind Eye Hospital, tells Google that by integrating the machine learning algorithm into their screening process: “physicians like me have more time to work closely with patients on treatment and management of their disease, while increasing the volume of screenings we can perform.”
Longer term Verily aims to make the algorithm available globally, to help medics assess these two common and damaging types of eye disease.