Study: AI Could Help NHS Clinicians Diagnose Pediatric Sleep Apnea

Artificial intelligence (AI)-based software designed to help diagnose pediatric sleep apnea has achieved high accuracy rates in a National Health Service (NHS) trial, with the findings independently reviewed by clinical specialists. 

Glasgow company Seluna tested its autoscoring and sleep staging software on 500 retrospective sleep studies from NHS Greater Glasgow and Clyde’s Royal Hospital for Children. The technology, which hosts a pipeline of machine learning algorithms for automated data analytics, processed each study in less than five minutes to identify severe cases with complete (100%) accuracy based on Apnea-Hypopnea Index severity classification, while mild cases achieved 86% and moderate cases 92% accuracy. Overall, the algorithms performed within the bounds of human inter-scorer variability.

Pediatric sleep apnea affects up to 4% of children globally yet remains widely underdiagnosed. The condition can cause serious developmental and behavioral problems if left untreated. Sleep studies produce vast amounts of complex physiological data that doctors and physiologists must interpret manually but the process can take up to four hours per patient and requires specialist staff who are in short supply. 

Seluna’s cloud-based autoscoring software helps doctors and physiologists interpret pediatric sleep studies more efficiently, thus reducing strain on health services and delivering faster results to families.

“I’ve heard doctors describe their sleep departments as ‘drowning in data,’ with no ability to scale to meet growing demand,” Seluna CEO Dr. Scott Black said. “What this study proves is that our software works on real NHS data, with all the missing sensors and messy signals that pediatric sleep medicine involves. Our goal now is to replicate this study with hospitals across the U.K. and get our solution into the hands of clinicians.”

The study’s findings, supported by the West of Scotland Innovation Hub, have been independently reviewed by pediatric sleep specialists at Sheffield Children’s NHS Foundation Trust and University Hospital Southampton NHS Foundation Trust.

Pediatric obstructive sleep apnea is characterized by repeated episodes of partial or complete airway obstruction during sleep. In children, the condition disrupts neurocognitive development, causing behavioral problems including ADHD-like symptoms, poor concentration, stunted growth, and long-term increased risk of cardiovascular disease and metabolic disorders. The primary cause of pediatric obstructive sleep apnea is enlarged tonsils and adenoids. While adenotonsillectomy successfully treats most cases, current diagnostic pathways cannot reliably predict which children will benefit from surgery, resulting in both unnecessary operations and missed cases.

Unlike adult sleep apnea, children rarely show daytime sleepiness. Instead, they exhibit hyperactivity, bedwetting, restless sleep with loud snoring, mouth breathing, and poor school performance—symptoms often misattributed to ADHD or behavioral issues.

“Adenotonsillectomy is the most common procedure we perform in children, and sleep apnea is the most common reason for it. Seluna’s technology has the potential to reduce delays, improve consistency in reporting, and allow us to prioritize care for the children who most urgently need intervention,” commented Dr. Haytham Kubba, a pediatric ENT surgeon at the Royal Hospital for Children.

A multi-site, U.K.-wide study has received ethical approval and is being led by chief investigator, Dr. Heather Elphick at Sheffield Children’s NHS Foundation Trust. Th trial will involve six pediatric hospitals including Glasgow, Southampton, Sheffield, Alder Hey, Evelina, and Great Ormond Street. Seluna is also conducting a further multi-site algorithm optimization study in the United States—pending ethics approval—led by chief investigator, Dr. Cristina Baldassari at Children’s Hospital of the King’s Daughters. 

Seluna is a Glasgow-based medtech company developing AI-powered diagnostic software for childhood sleep disorders. The company’s Software as a Medical Device (SaMD) automatically interprets pediatric sleep studies, providing clinicians with rapid, standardized analysis and clinical decision support. Founded by Drs. Black and Yola Jones, the company is backed by Gabriel Investment Syndicate, Scottish Enterprise, University of Strathclyde, and STAC Invest.