A Glasgow-based medtech startup is could transform the way childhood sleep apnoea is diagnosed and treated.
Seluna’s machine learning platform aims to improve the diagnosis and management of childhood sleep disorders following the launch of a major clinical validation study with the Royal Hospital for Children in Glasgow.
The study, involving 500 anonymised patients under 18 years old, will run from now until the end of 2025. It aims to validate Seluna’s diagnostic software as a medical device (SaMD), which is designed to automatically interpret sleep studies via a pipeline of machine-learning algorithms. This will support Registered Polysomnographic Technologists (RPSGTs) and doctors in diagnosing and managing paediatric sleep apnoea.
Seluna is addressing a critical gap in paediatric sleep medicine, aiming to be the first SaMD developed specifically for diagnostics in this underserved market. Currently, the gold-standard pathway relies on manual interpretation of complex sleep study data – a slow and labour-intensive approach that creates significant bottlenecks in an already strained healthcare system.
The validation study follows Seluna’s recent success in securing nearly £650,000 funding via continued support from existing backers Gabriel Investment Syndicate, Scottish Enterprise and the University of Strathclyde, as well as a new investor STAC Invest.
Dr Scott Black, co-founder and CEO of Seluna, said: “Paediatric sleep diagnostics has been underserved for too long. It’s a complex challenge, which is why existing tools weren’t built for children – until now. This validation study will demonstrate clinical impact and make a clear statement: we’re here to set a new standard. We’re here to innovate, drive change, and compete internationally, with backing from investors who recognise the potential of the paediatric healthcare market.”
Seluna’s machine learning pipeline automatically scores paediatric sleep studies by identifying and classifying digital biomarkers of sleep-disordered breathing. Designed to reduce clinical workload and support objective, data-driven decisions, the system streamlines and standardises the diagnostic pathway. The algorithms are designed to be interpretable and transparent, and to support, not replace, clinical judgement.
Dr Ruth Hamilton, consultant clinical scientist at Royal Hospital for Sick Children, Glasgow, and principal investigator, added: “What makes Seluna’s approach so compelling is its focus on explainable AI. As clinicians, we need to understand why the technology is making certain recommendations. Seluna’s focus on interpretability builds the trust we need to confidently use this technology in clinical practice. It will help take pressure off busy departments and allow us to stop firefighting wait lists.”