HealthDay News — Neural network-based automated analyses of nocturnal oximetry (nSpO2) recordings provide accurate identification of obstructive sleep apnea-hypopnea syndrome (OSA) severity among habitually snoring children, according to a study published online in the American Journal of Respiratory and Critical Care Medicine.
Roberto Hornero, PhD, from the University of Valladolid in Spain, and colleagues developed and validated an automated neural network algorithm using an initial set of single-channel nSpO2 recordings from 589 patients referred for suspected OSA. Then, nSpO2 recordings from a total of 4191 children originating from 13 pediatric sleep laboratories around the world were prospectively evaluated using the algorithm.
The researchers found that the automatically estimated apnea-hypopnea index (AHI) showed high agreement with AHI from conventional nocturnal polysomnography (intra-class correlation coefficient, 0.785) when tested in 3602 additional subjects. Further assessment on the widely-used AHI cut-off points 1, 5, and 10 events/hour revealed an incremental diagnostic ability (75.2%, 81.7%, and 90.2% accuracy, respectively; 0.788, 0.854, and 0.913 area under the receiver-operating characteristics curve, respectively).
“An automated neural network algorithm based on overnight oximetry recordings provides accurate identification of OSA severity among habitually snoring children with a high pre-test probability of OSA,” the authors write.
Hornero R, Kheirandish-Gozal L, Gutierrez-Tobal G, et al. Nocturnal oximetry-based evaluation of habitually snoring children [published online July 31, 2017]. Am J Resp Crit care Med. doi:10.1164/rccm.201705-0930OC