Detection of Sleep Oxygen Desaturations from Electroencephalogram Signals

TL;DR

This study addresses pediatric sleep apnea by seeking EEG-based biomarkers of sleep oxygen desaturation. It processes multi-channel EEG with short-time Fourier transform-derived spectral-temporal features and classifies desaturation versus non-desaturation epochs using a ResNet, applying two age/gender matching schemes to control bias. Across cross-patient and within-patient analyses, the approach achieves meaningful discrimination (BA and AUC) in several sleep stages and uncovers potential latent markers when desaturation events are absent. The work supports the feasibility of a brain-based biomarker for sleep-disordered breathing and highlights future work to isolate the morphologic EEG features underpinning desaturation signals.

Abstract

In this work, we leverage machine learning techniques to identify potential biomarkers of oxygen desaturation during sleep exclusively from electroencephalogram (EEG) signals in pediatric patients with sleep apnea. Development of a machine learning technique which can successfully identify EEG signals from patients with sleep apnea as well as identify latent EEG signals which come from subjects who experience oxygen desaturations but do not themselves occur during oxygen desaturation events would provide a strong step towards developing a brain-based biomarker for sleep apnea in order to aid with easier diagnosis of this disease. We leverage a large corpus of data, and show that machine learning enables us to classify EEG signals as occurring during oxygen desaturations or not occurring during oxygen desaturations with an average 66.8% balanced accuracy. We furthermore investigate the ability of machine learning models to identify subjects who experience oxygen desaturations from EEG data that does not occur during oxygen desaturations. We conclude that there is a potential biomarker for oxygen desaturation in EEG data.