AI studies in children's airway disorders largely focused on sleep apnea diagnosis
A systematic review found promising diagnostic results, but no studies addressing treatment or monitoring and unresolved questions about practical use.
Based on the published abstract. The full paper may contain additional methods, results and limitations.
The 30-second takeaway
Most included studies used artificial intelligence to identify obstructive sleep apnea or classify its severity, often from overnight physiological signals. Some models reported high diagnostic performance, but results varied with the data and study design. The review found no treatment or monitoring studies, so it does not show that these tools improve children's care or health outcomes.
Small samples, differing patient populations and a strong focus on sleep apnea limited generalizability. Validation, data diversity and feasibility remained unresolved, preventing the reported performance from establishing readiness for routine use.
What the models analyzed
Overnight blood oxygen saturation was the most common input, followed by clinical information and other physiological recordings. The review therefore mainly describes tools that interpret collected signals, rather than a tested pathway for managing airway disorders.
Accuracy is only part of evaluation
The abstract lists performance results from different approaches, but also says performance depended on input data and study design. Those figures do not provide a common comparison showing which tool works best across children or clinical settings.
The original publication
Current role of artificial intelligence and machine learning: is their application feasible in pediatric upper airway obstructive disorders?
Dallari V, Reale M, Fermi M et al.
Eur Arch Otorhinolaryngol · 2026
- PubMed ID
- 40775390
- Record checked
AI-assisted research and writing. This explains one selected publication; it is not a complete review of everything known. Our approach.
One more question, understood.
Keep track of the research you’ve explored.