The seventh leading cause of death in the world is diabetes and the number of people affected from it is increasing rapidly. Out of 415 million diabetes patients in world, 78.3 million people are from South-East Asia. These people are always at a risk of getting diabetic retinopathy, a complication which arises from diabetes and can eventually lead to blindness if left untreated.

The condition is severe in India and makes it susceptible to the extreme effects of this disease is the lack of availability of eye specialists, resulting in nearly 45 per cent patients suffering vision loss before diagnosis. Google, using AI, is hopeful to help Indian doctors detect diabetic retinopathy in early stages.

Google has developed an artificial intelligence model that can detect diabetic retinopathy by evaluating the scans of the retinas - the region at the back of the eye - using special cameras. This image is then analyzed by Googles machine learning algorithm, grading those scans on a five-point scale ranging between no diabetic retinopathy or DR, which can be managed using a combination of diet and medication, to the most severe case, which might need a surgery.

Google product manager Lily Peng said at the companys Solve with AI Conference in Tokyo on July 10 that, in 2016, they published a paper in the Journal of American Medical Association which has shown that this AI system was performing the level of the Generalists and since then they have made improvements to the algorithm, and now it is on par with the specialists.

Google has already directed this program in two South-East Asian countries -- Thailand and India. And in India, Google partnered with Aravind Eye Hospital in Madurai and Sankara Eye Hospital in Chennai.

Remarkably, Aravind Eye Hospital also has 70 satellite clinics located across south India that provide to the people who cannot come to the hospital for routine scans. At these satellite clinics, nurses capture the image of the patients retinas. These images are then uploaded on to the cloud where Googles ML algorithm works in combination with the specialists to detect and diagnose the disease, which can be treated, based on the severity.After the success of this pilot project, the company is now hopeful to team up with other hospitals across the country as well.