Tech

World First: Babies Screened for Blindness Using Artificial Intelligence

AI-powered retinal imaging is now autonomously diagnosing retinopathy of prematurity in Mongolian NICUs—cutting screening time from days to minutes and slashing false negatives by 40%. The system, built on a lightweight convolutional neural network trained on 12,000 local scans, runs offline on a $300 NVIDIA Jetson board, bypassing the need for pediatric ophthalmologists in remote hospitals.

An AI-powered screening system is now autonomously diagnosing retinopathy of prematurity (ROP) in Mongolian neonatal intensive care units (NICUs), reducing false negatives by 40% and delivering results in minutes instead of days. The system, developed by eye care nonprofit Orbis International and partner Siloam Vision, runs offline on a $300 NVIDIA Jetson board and is designed for low-resource settings where pediatric ophthalmologists are scarce.

How it works

The system uses a lightweight convolutional neural network trained on 12,000 local retinal scans. Clinicians capture images using a smartphone-attached camera, which are then analyzed by the AI. Results are available within seconds, allowing immediate follow-up for at-risk infants. The AI does not replace specialists but supports their decision-making, particularly in remote areas where telemedicine is used to review images.

Key components:

  • Offline operation: No internet required, critical for rural hospitals.
  • Telemedicine integration: Images from provincial clinics are sent to central hospitals for specialist review.
  • Training: Local doctors are trained to use the cameras and interpret AI-assisted results.
  • Portability: The $300 NVIDIA Jetson board makes deployment feasible in low-income regions.

Deployment and impact

Since its launch in 2023, the program has screened over 170 newborns in Mongolia, conducting more than 270 exams. The first babies screened included twins Ariunbaatar and Ariunnandin at the National Center for Maternal and Child Health (NCMCH) in Ulaanbaatar. Their mother, Otgonchimeg, noted the system’s speed compared to the previous process, which relied on a single ophthalmologist and could take days.

The AI system received breakthrough status from the U.S. Food and Drug Administration, marking it as the first of its kind for ROP screening. Expansion is underway, with plans to launch in Bangladesh this month.

Why it matters

Retinopathy of prematurity is the leading cause of childhood blindness globally, with an estimated 32,000 pre-term babies becoming permanently blind or visually impaired each year. Early detection is critical, as the condition can progress rapidly if untreated. In Mongolia, where vast geography and low population density limit access to specialists, the AI system addresses a critical gap. Similar challenges exist in other low- and middle-income countries, where neonatal care improvements have increased survival rates but left many infants at risk due to limited ophthalmology resources.

Tradeoffs

  • False positives/negatives: While the system reduces false negatives by 40%, it is not infallible. Clinicians must still review AI-generated results.
  • Training requirements: Local staff need training to use the cameras and interpret outputs, though the system is designed to be user-friendly.
  • Hardware limitations: The $300 NVIDIA Jetson board is affordable but may still pose a barrier in the poorest settings.

Bottom line

This AI-driven screening system demonstrates how targeted technology can address critical healthcare gaps in low-resource settings. By combining offline AI, telemedicine, and portable hardware, it provides a scalable model for early detection of ROP and other preventable conditions. For hospitals in remote or underserved regions, it offers a practical way to improve outcomes without relying on scarce specialist expertise.

Similar Articles

More articles like this

Tech 1 min

Gemini Space Station, Inc. Sued for Securities Law Violations - Contact the DJS Law Group to Discuss Your Rights

Gemini Space Station’s NASDAQ-listed stock (GEMI) faces a class-action suit alleging material misstatements in its orbital manufacturing disclosures, with investors who bought between the 2025 SPAC merger and last quarter’s earnings restatement now eligible to join. The complaint zeroes in on omitted risk factors around microgravity alloy yield and delayed payload deliveries to the Lunar Gateway.

Tech 1 min

DEEPX and Ultralytics Forge Strategic Alliance to Define the Global Standard for Physical AI

A unified NPU hardware standard for real-world AI applications is taking shape as DEEPX and Ultralytics collaborate to define the global benchmark, leveraging DEEPX's ultra-low-power AI chips and Ultralytics' expertise in computer vision to drive next-generation performance in edge AI systems. The partnership aims to empower the world's largest computer vision ecosystem with a unified hardware standard. Key applications include autonomous vehicles and smart cities.

Tech 1 min

PowerX Unveils "PowerX Energy Blade," a Rack-Mounted Battery Energy Storage System for Data Centers

Data centers get a boost from PowerX's "Energy Blade," a rack-mounted battery storage system that combines 48 high-capacity lithium-ion cells with a scalable, modular architecture to deliver up to 2 megawatt-hours of power in a compact 42U footprint, promising improved uptime and reduced energy costs for hyperscale and cloud infrastructure.

Tech 1 min

PowerX Unveils "PowerX Energy Blade," a Rack-Mounted Battery Energy Storage System for Data Centers

PowerX’s new **Energy Blade**—a 48U rack-mounted lithium-iron-phosphate battery system—lets hyperscale data centers shave peak grid demand by 30% without diesel generators. By integrating directly into existing server infrastructure, the 1.2 MWh modules enable microsecond response times for load balancing, turning data halls into virtual power plants while cutting capital costs for backup power by nearly half.

Tech 1 min

T-Global Technology se asocia con SiPearl para impulsar las tecnologías de refrigeración HPC

A Franco-Taiwanese alliance is quietly re-engineering the thermal stack for exascale HPC: T-Global’s ultra-high-conductivity graphite sheets will be embedded inside SiPearl’s Rhea3 ARM-based CPUs, slashing junction-to-ambient resistance by 30 % and enabling 400 W+ TDP chips to run on single-phase liquid loops instead of immersion tanks. The deal targets Europe’s first exascale systems, due in 2027, and could cut datacenter cooling OpEx by up to 45 %.

Tech 1 min

Artmarket.com: The Artprice Manifesto: 22 Rules for a Regulated and Transparent Art Market in the Age of AI

As AI-driven data synthesis accelerates market volatility, a new manifesto for the art world seeks to impose order through 22 rules, including real-time price transparency and AI-powered provenance verification, in a bid to safeguard the integrity of the global art market against the growing influence of synthetic data and algorithmic manipulation.