Nocturnal Oximetry–based Evaluation of Habitually Snoring Children

Abstract

Neural network-based automated analyses of nSp recordings provide accurate identification of OSA severity among habitually snoring children with a high pretest probability of OSA. Thus, nocturnal oximetry may enable a simple and effective diagnostic alternative to nocturnal polysomnography, leading to more timely interventions and potentially improved outcomes.

A graphical method for comparing nocturnal oxygen saturation profiles in individuals and populations: Application to healthy infants and preterm neonates

“…The current graphical implementation is designed for the direct clinical or scientific comparison of SpO 2 profiles. However, the information contained could also be used to develop automated classifiers using machine learning approaches …”

Nocturnal oximetry in pediatric respiratory disease: Urgent need for developing standardized interpretation rules

“…Depending on the depth of desaturations a McGill oximetry score of 1‐4 is assigned. Recently, a promising tool of automated oximetry analysis was developed . The tool is based on a neural network, signal‐processing technique, and provides a calculated apnea‐hypopnea index in high agreement with the index from conventional polysomnography in habitually snoring children with a high pretest probability of OSAS.…”

Pediatric pulmonology year in review 2017: Part 4 (Sleep medicine)

“…Participants with abnormal MOS ( N = 45) were 20 times more likely to undergo AT, but conclusions were limited due to the lack of comparison with standard PSG. Homero et al performed a study aimed at evaluating the role of neural network‐based automated analyses of nocturnal oximetry in the assessment of snoring children. These investigators analyzed the nocturnal oximetry recordings obtained as part of a clinical PSG of 4191 children aged 2‐18 years from 13 pediatric sleep laboratories around the world.…”