India approves world’s first regulatory-approved AI for ROP screening, developed by Remidio and KIDROP 

0
72

Remidio Innovative Solutions has received approval from India’s Central Drugs Standard Control Organisation (CDSCO) for MediosHI ROP AI. For the first time in the world, a regulator has approved an artificial intelligence (AI) to support screening for retinopathy of prematurity (ROP), a leading cause of preventable childhood blindness.

Remidio’s offline MediosHI ROP AI screens premature babies for ROP and plus disease at the bedside, flagging those who need a specialist’s attention, so no baby goes blind for the lack of timely screening.

For a premature baby, time is short. ROP can become sight-threatening within weeks of birth, and a baby who misses timely treatment can lose their sight for life.

The AI works offline at the bedside and is device agnostic, reading images from Remidio’s Insta Neubo 130 and from other ROP cameras. A trained nurse or technician images the baby’s retina and gets an immediate AI read. An ophthalmologist then reviews the images remotely and decides the next step. Screening can now reach units that specialists rarely visit.

The most premature births in the world, fewer than 200 specialists

India has more premature births than any other country, an estimated 3.02 million in 2020 [2]. At-risk babies need repeated eye examinations over several weeks [1], which adds up to millions of examinations every year. India has fewer than 300 ROP specialists [1], roughly one for every 15,000 premature babies born each year, and most are in large cities. In a 2017 study of four district newborn units, only 18% of eligible babies were screened even once [3].

Every missed baby is a child who goes blind

ROP can move from mild to sight-threatening in a matter of weeks, and in its most aggressive form, within days. If the retina detaches, the child’s sight usually cannot be restored. Every year, an estimated 2,900 children in India are left visually impaired by ROP [4]. With each specialist responsible for thousands of babies, there is no room for a single miss.

MediosHI ROP AI is built for this problem. It screens every baby for signs of ROP and plus disease and flags those who need a specialist, so the doctor’s time goes to them first. In clinical testing, it did not miss a single baby with type 1 ROP, the severe form that needs urgent treatment. In units with no specialist on site, its consistent read also helps nurses and technicians learn to recognise risk.

“ROP is not a problem of science; treatment works. It is a problem of reach: too few babies are examined in time. By putting a camera and offline AI, designed and made in India for hard-to-reach units, in the hands of trained nurses and technicians, we move from screening when a specialist can visit to screening as standard in every neonatal unit,” said Dr. Anand Sivaraman, Chief Executive Officer, Remidio.

A record of every examination

Much ROP screening is still done by indirect ophthalmoscopy, where the doctor examines the retina directly and the only record is a note or a hand drawing. AI screening works from retinal images, so every examination is documented. The images can be compared over time, reviewed by a specialist and shown to parents. They also protect clinicians. In the United States, payouts in ROP malpractice cases have been about three times the average for ophthalmology claims, and photographs are recognised as more reliable evidence than drawings [5].

Screening at the bedside, specialists in the loop

The AI fits into tele-ROP, the telemedicine model that Narayana Nethralaya’s KIDROP programme has used since 2008.

  1. Image. A trained nurse or technician photographs the baby’s retina with a wide-field ROP camera.
  2. Screen. The AI analyses the images on the spot, with no internet connection, and flags findings suggestive of ROP and plus disease.
  3. Decide. The images and findings reach an ROP specialist, who prioritises flagged cases and decides on follow-up, referral or treatment. The AI does not clear babies or replace specialist review.

This lets one specialist support many more neonatal units and spend their time on the babies who need examination and treatment.

“India cannot train enough ROP specialists in time for the babies being born today. What we can change is who does the screening and where the specialist’s time goes. The AI prioritises; the ophthalmologist decides,” said Dr. Divya Rao, Chief Medical Officer and Medical Director, Remidio.

Built on 18 years of KIDROP screening

Remidio and Narayana Nethralaya Eye Institute’s KIDROP program jointly developed MediosHI ROP AI with funding from the Biotechnology Industry Research Assistance Council (BIRAC), using KIDROP’s extensive bank of labelled retinal images. KIDROP is India’s first tele-ROP programme and one of the largest in the world. Since 2008, it has grown from three centres in Karnataka to 177, screened more than 115,000 premature babies and provided more than 6,500 treatments.

In a recently concluded study of 600 infants imaged on multiple ROP cameras, the AI detected every case of type 1 ROP. Against a diagnosis agreed by a panel of ROP specialists, it correctly flagged 91% of babies with any stage of ROP (sensitivity) and correctly identified 87% of babies without it (specificity).

“KIDROP has shown that trained nurses and technicians, equipped with imaging systems, can screen babies far from a specialist. Standardised wide-field imaging and AI within our tele-ROP network take that further: every screener gets the same consistent first triage, in any unit. That is how we intend to expand ROP screening to every baby who needs it, so that no baby is missed simply because of where they were born,” said Dr. Anand Vinekar, Founder and Program Director, KIDROP, and Head, Department of Pediatric Retina, Narayana Nethralaya Eye Institute, Bengaluru.

“As regulatory frameworks for AI in medical devices evolve, clearly defining the software’s intended purpose and scope is key to responsible innovation. MediosHI ROP AI supports a specific role in the ROP triage workflow, with all clinical decisions firmly in the hands of clinicians. This approval marks an important milestone in advancing responsible AI adoption in healthcare,” said Sundeep Agarwal, Senior Vice President, Quality Assurance and Regulatory Affairs, Remidio.

What parents can do

Every premature baby born less than 2000 grams, should have an eye screening within 30 days of birth. Parents of babies born early should ask their doctor or neonatal unit for an ROP screening before the baby goes home.