Electroencephalography Theta/Beta Ratio Decreases in Patients with Severe Obstructive Sleep Apnea

Machine-learning-based classification of obstructive sleep apnea using 19-channel sleep EEG data

OBJECTIVE

This study aimed to investigate the neurophysiological effects of obstructive sleep apnea (OSA) using multi-channel sleep electroencephalography (EEG) through machine learning methods encompassing various analysis methodologies including power spectral analysis, network analysis, and microstate analysis.

METHODS

Twenty participants with apnea-hypopnea index (AHI) ≥ 15 and 18 participants with AHI <15 were recruited. Overnight polysomnography was conducted concurrently with 19-channel EEG. Preprocessed EEG data underwent computation of relative spectral power. A weighted network based on graph theory was generated; and indices of strength, path length, eigenvector centrality, and clustering coefficient were calculated. Microstate analysis was conducted to derive four topographic maps. Machine learning techniques were employed to assess EEG features capable of differentiating two groups.

RESULTS

Among 71 features that showed significant differences between the two groups, seven exhibited good classification performance, achieving 88.3 % accuracy, 92 % sensitivity, and 84 % specificity. These features were power at C4 theta, P3 theta, P4 theta, and F8 gamma during NREM1 sleep and at Pz gamma during REM sleep from power spectral analysis; eigenvector centrality at F7 gamma during REM sleep from network analysis; and duration of microstate 4 during NREM2 sleep from microstate analysis. These seven EEG features were significantly correlated with polysomnographic parameters reflecting the severity of OSA.

CONCLUSIONS

The application of machine learning techniques and various EEG analytical methods resulted in a model that showed good performance in classifying moderate to severe OSA and highlights the potential of EEG to serve as a biomarker of functional changes in OSA.

Characteristics of ADHD Symptoms and EEG Theta/Beta Ratio in Children With Sleep Disordered Breathing

Objectives. This study aimed to explore parent-reported symptoms of attention deficit-hyperactivity disorder (ADHD) and sleep electroencephalogram (EEG) theta/beta ratio (TBR) characteristics in children with sleep disordered breathing (SDB). Methods. The parents of children (aged 6-11 years) with SDB (n = 103) and healthy controls (n = 28) completed the SNAP-IV questionnaire, and children underwent overnight polysomnography. Children with SDB were grouped according to obstructive apnea/hypopnea index: primary snoring, mild, and moderate-severe obstructive sleep apnea (OSA) groups. The TBR in non-rapid eye movement (NREM) periods in three sleep cycles was analyzed. Results. Children with SDB showed worse ADHD symptoms compared with the healthy control. There was no intergroup difference in TBR. The time-related decline in TBR observed in the control, primary snoring and mild OSA groups, which was not observed in the moderate-severe OSA group. Overnight transcutaneous oxygen saturation was negatively associated with the hyperactivity/impulsivity score of ADHD symptom. The global TBR during the NREM period in the first sleep cycle was positively correlated with inattention score. Conclusion. Children with SDB showed more ADHD inattention symptoms than the healthy control. Although we found no difference in TBR among groups, we found significant main effect for NREM period. There existed a relationship between hypoxia, TBR, and scores of ADHD symptoms. Hence, it was speculated that TBR can reflect the nocturnal electrophysiological manifestations in children with SDB, which may be related to daytime ADHD symptoms.