Smartphone App Used to Detect Diabetes-Related Vision Disorder

Indian medical technology company Remidio Innovative Solutions has developed a smartphone app that uses AI to detect diabetic retinopathy (DR), an eye condition that can cause blindness in people with diabetes.

The app, Remidio Medios DR AI, can be downloaded onto a smartphone, which is then connected to the company’s handheld retinal camera. The setup allows for DR screening in remote locations without access to graphics processing unit-based servers or even the internet, the company said, adding that it is currently being used in Himachal Pradesh, rural West Bengal and other areas with limited access to screening. It also has the benefit of not requiring the patient’s pupils to be dilated.

DR is caused by high blood-sugar levels, which can damage blood vessels in the retina. These in turn can swell, leak or become blocked. The damaged vessels can then cause the eye to grow new vessels that do not work well and can leak or bleed easily, according to the National Institutes of Health. Early detection of DR can prevent diabetes-related blindness.

Remidio Medios DR was just approved by India’s Central Drugs Standard Control Organisation (CDSCO). It has also been given the green light by the European Commission and Singapore’s Health Sciences Authority. It is currently not available in the United States, however.

Related:Eyesight-Restoring Device From Musk Company Earns FDA Breakthrough Designation

"The CDSCO's approval helps us bring care closer to patients, but we are particularly excited to see India become a global leader in leveraging AI to eliminate preventable blindness caused by DR," Remidio Chief Medical Officer Divya Rao said.

The AI uses a deep learning algorithm that runs on two convolutional neural networks based on Google’s Inception-V3, which is used for image analysis and detection in computer vision. The algorithm was trained on a set of more than 50,000 images of retinas, some with DR and some without, according to a study by the Indian Journal of Ophthalmology, which found the program to be highly effective in detecting DR.

"A science-first, public-health approach has helped Remidio not only assess the performance of its AI in real world settings, but also for the AI research ecosystem to learn from clinical outcomes associated with primary care-led DR screening programs, care-gap closure pathways and the cost-benefit analysis of bringing screening closer to the patient," said Rajiv Raman, a senior vitreo-retinal consultant with Sankara Nethralaya, a specialty eye-care hospital in India.