Big Tech uses AI to arrest blindness among India's burgeoning diabetics

Diabetic retinopathy is a leading cause of blindness and vision loss in adults and tech giants such as Intel and Google are building AI-based innovations to address such problems

India has one of the largest diabetic populations of any country in the world, approaching 98 million cases by 2030. Research shows that diabetic retinopathy (DR) is a leading cause of blindness and vision loss in adults, and early detection and treatment is critical to stopping the damage. However, the lack of trained retinal specialists in India — especially in remote, rural regions — limits effective screening of asymptomatic patients. Many such patients do not receive proper and timely medical attention and develop advanced diabetic eye disease as a result. Tech giants such as Intel, Google and Microsoft are building artificial intelligence-based innovations to address such problems. 

Using Intel’s technology, Sankara Eye Foundation and Singapore-based Leben Care are deploying a comprehensive retina risk assessment software-as-a-service (SaaS) platform in India. The innovation, called Netra.AI, is a cloud-based artificial intelligence (AI) solution powered by Intel. It uses deep learning to identify retinal conditions in a short span of time with the accuracy level of human doctors. Netra.AI can accurately identify diabetic retinopathy (DR), greatly reducing the screening burden on vitreoretinal surgeons.

“India has one of the largest diabetic populations in the world and diabetic retinopathy is the major cause for vision loss and blindness in persons of working age,” says Prakash Mallya, vice president and managing director of sales, marketing and communications group, Intel India. “The use of AI to improve disease detection and prevention is a critical step for the healthcare industry and a giant leap for humankind.”

With Netra.AI, Sankara Eye Foundation and Leben Care have leveraged the power of Intel Xeon scalable processors and built-in Intel deep learning (DL) boost to accurately detect DR. This enables timely treatment to effectively combat avoidable vision impairment and blindness in diabetic patients.

Netra.AI analyses images from portable, technician-operated fundus camera devices, for immediate results of referable DR grading via a cloud-based web portal. The solution uses cutting-edge AI algorithms, developed in collaboration with leading retina experts, with a four-step deep convolutional neural network (DCNN). This neural network helps in detecting DR stage and annotating lesions based on pixel density in the fundus images. The solution can be expanded to other retinal conditions and glaucoma. This helps to reduce the screening burden on healthcare specialists and focus key resources on patients who need immediate care and intervention.

“Technology and AI are democratising healthcare access, especially in screening for ailments,” says Dr Kaushik Murali, president of medical administration, quality and education, Sankara Eye Foundation India.

Sankara played a key role in the design and development of Netra.AI along with Leben Care. “It is an example of how like-minded collaborators can create meaningful and impactful solutions for various challenges that face humanity," says Murali.

So far, Netra.AI has screened 3,093 patients in India and identified 742 at-risk patients. The solution generates detailed reports within two minutes of uploading images. It offers immediate and highly accurate diagnosis to help doctors provide instant counsel for patients needing a referral to the hospital. It is a powerful tool for screening retinal illnesses in large populations with limited infrastructure, resources and an overburdened healthcare system. The solution also delivers sensitivity and accuracy while detecting any DR, that is, 99.7 per cent and 98.5 per cent respectively.

Diabetic retinopathy is a leading cause of blindness across the world and 463 million people are currently at risk. Countries such as India, China and the US, have the most cases.

The biggest challenge with diagnosing DR, is the sheer number of cases. Diabetes is at an all-time high around the world, and the number of people living with the disease is only increasing. Many complications can arise from diabetes, including diabetic retinopathy (DR) and diabetic macular edema (DME)—two of the leading causes of preventable blindness in adults. In India, a shortage of more than 100,000 eye doctors—and the fact that only six million of 72 million people with diabetes are screened for diabetic eye disease, meaning that many individuals go undiagnosed and untreated, according to Google.

Google is building on its efforts to apply AI in screening for  DR, working with partners like Aravind Eye Hospital and Sankara Nethralaya.

Google and Verily—Alphabet’s life sciences and healthcare arm—had developed a machine-learning algorithm to make it easier to screen for disease, as well as expand access to screening for DR and DME. As part of this effort, it conducted a global clinical research program with a focus on India. One of the real-world clinical use of the algorithm was done at the Aravind Eye Hospital in Madurai.

Thousands of patients come through the doors of Aravind Eye Hospital and vision centres every day. By integrating machine learning algorithm into the screening process, physicians have more time to work closely with patients on treatment and management of their disease, while increasing the volume of screenings they can perform.

Google believes its machine learning algorithm could be helpful in many other areas of the world where there aren’t enough eye doctors to screen a growing population with diabetes. 

Last January, Microsoft Corp, also announced AI for Health, a new $40 million, five-year programme. It is part of Microsoft’s $165 million AI for Good initiative, that will leverage AI technology to empower researchers and organizations to address some of the world’s toughest challenges in health. It includes detecting diabetic retinopathy to prevent blindness. Last year Intelligent Retinal Imaging Systems (IRIS),  which provides telemedicine solutions for diabetic retinal evaluation, was announced as a grantee for the Microsoft AI for Health Initiative.

Early detection and effective treatment of DR can reduce the risk of blindness up to 95 per cent. Microsoft's collaboration with research and the development of an AI solution is empowering IRIS to bring retinal evaluations to underserved populations across the globe in an effort to end preventable blindness. Microsoft had also partnered with Forus Health, a Bengaluru-based start-up focused on retinal imaging devices. The firm is leveraging AI for the early detection of eye diseases such as diabetic retinopathy, glaucoma, and macular degeneration to help reduce avoidable blindness.