A new screening program in India uses machine learning to reduce the risk of preventable blindness from retinopathy in premature babies.
ROP is a condition that occurs when blood vessels develop abnormally in the retina.
WHAT IT’S ABOUT
CleaVision, a social venture supported by enterprise software provider SAP, has developed a solution that automates the identification of retinal and vascular features and provides disease recommendations. plus, is associated with severe ROP in premature infants. It does this by integrating image data processing with SAP Business Technology Platform, SAP AI Platform, and SAP Analytics Cloud.
The automated deep learning screening technology has been trialled at Narayana Nethralaya Eye Institute (NNEI) in Bangalore, one of the leading eye hospitals in India that has performed over 2,000 newborn ROP screening sessions. Now, it has created a huge database of retinal images from infants in different stages of the disease.
Following this pilot, CleaVision sought to expand the implementation of its solution through Karnataka’s Internet-enabled Telemedicine Network.
WHY IT IMPORTANT
About 20% of the world’s 15 million premature babies were born in India. There, about 200,000 babies are thought to be at risk of developing the severe stage of ROP, where abnormally developing blood vessels in the baby’s eyes can cause bleeding, scarring and detachment of the retina, eventually leading to blindness. irreversible blindness. According to CleaVision, early diagnosis is essential to help infants receive timely treatment to completely recover from this disease.
“Given that India has the highest number of preterm pregnancies and the fact that there are relatively few qualified ROP doctors, the more we can digitize and automate prescreening, the more those practitioners will more time for actual treatment,” CleaVision co-founder Chirag told Gupta.
Narayan VK, co-founder of CleaVision added: “Using the power of machine learning and data analysis, we can help doctors focus on treating infants at risk for disease. .
Dr Anand Vinekar, chief of pediatric retinal detachment at NNEI, said the CleaVision screening solution has the potential to assist ROP technicians and specialists in making more accurate diagnoses. He added: “That would help in timely treatment of these children, providing better outcomes, preventing blindness from ROP.
With this technology, the screening program can also be extended to achieve low resource settings.
SNAPSHOT . MARKET
An analogy Automated deep learning system for advanced ROP detection in premature infants is being developed in the United States through support from the National Eye Institute. In 2020, the device was awarded breakthrough status by the Food and Drug Administration.
Meanwhile, in Australia, researchers from the University of South Australia also use AI to develop computer vision system Remotely monitor the vital signs of premature babies and detect the baby’s face while lying on the hospital bed.