Sleep Instabilities Assessed by Cardiopulmonary Coupling Analysis Increase During Childhood and Adolescence

A Survey on Recent Advances in Machine Learning Based Sleep Apnea Detection Systems

Sleep apnea is a sleep disorder that affects a large population. This disorder can cause or augment the exposure to cardiovascular dysfunction, stroke, diabetes, and poor productivity. The polysomnography (PSG) test, which is the gold standard for sleep apnea detection, is expensive, inconvenient, and unavailable to the population at large. This calls for more friendly and accessible solutions for diagnosing sleep apnea. In this paper, we examine how sleep apnea is detected clinically, and how a combination of advances in embedded systems and machine learning can help make its diagnosis easier, more affordable, and accessible. We present the relevance of machine learning in sleep apnea detection, and a study of the recent advances in the aforementioned area. The review covers research based on machine learning, deep learning, and sensor fusion, and focuses on the following facets of sleep apnea detection: (i) type of sensors used for data collection, (ii) feature engineering approaches applied on the data (iii) classifiers used for sleep apnea detection/classification. We also analyze the challenges in the design of sleep apnea detection systems, based on the literature survey.

Multicomponent Analysis of Sleep Using Electrocortical, Respiratory, Autonomic and Hemodynamic Signals Reveals Distinct Features of Stable and Unstable NREM and REM Sleep

A new concept of non-rapid eye movement (NREM) and rapid eye movement (REM) sleep is proposed, that of multi-component integrative states that define stable and unstable sleep, respectively, NREM_S, NREM_US REM_S, and REM_US. Three complementary data sets are used: obstructive sleep apnea (20), healthy subjects (11), and high loop gain sleep apnea (50). We use polysomnography (PSG) with beat-to-beat blood pressure monitoring, and electrocardiogram (ECG)-derived cardiopulmonary coupling (CPC) analysis to demonstrate a bimodal, rather than graded, characteristic of NREM sleep. Stable NREM (NREM_S) is characterized by high probability of occurrence of the <1 Hz slow oscillation, high delta power, stable breathing, blood pressure dipping, strong sinus arrhythmia and vagal dominance, and high frequency CPC. Conversely, unstable NREM (NREM_US) has the opposite features: a fragmented and discontinuous <1 Hz slow oscillation, non-dipping of blood pressure, unstable respiration, cyclic variation in heart rate, and low frequency CPC. The dimension of NREM stability raises the possibility of a comprehensive integrated multicomponent network model of NREM sleep which captures sleep onset (e.g., ventrolateral preoptic area-based sleep switch) processes, synaptic homeostatic delta power kinetics, and the interaction of global and local sleep processes as reflected in the spatiotemporal evolution of cortical “UP” and “DOWN” states, while incorporating the complex dynamics of autonomic-respiratory-hemodynamic systems during sleep. Bimodality of REM sleep is harder to discern in health. However, individuals with combined obstructive and central sleep apnea allows ready recognition of REM_S and REM_US (stable and unstable REM sleep, respectively), especially when there is a discordance of respiratory patterns in relation to conventional stage of sleep.

Effects of sound environment on the sleep of college students in China

Chinese college students reside primarily in four-person bedrooms and even six-person bedrooms, where the sound from roommates may affect their sleep. Therefore, the purpose of the present study is to investigate the effects of different sound sources and sound levels on sleep for college students in China. Based on sleep quality measurements, acoustic environment measurements, and a questionnaire survey with 90 participants in a typical residence hall in Harbin city, China, the results are as following: First, 68.89% of college students experienced sleep deprivation, and indoor noise was the most influential environmental factor among 15 disruptors that disturbed 50% of college students. Second, the number of occupants per room was a significant factor affecting the background sound level of sleep, which was highest when the number of occupants was two, and lowest when the number was five. Third, deep sleep time and rapid eye movements (REM) sleep time decreased 1.7 min and 1.4 min per 1 dBA (decibel with A-weight), with R² = 0.352 and 0.332, respectively (p < .001). In terms of the effect of sound sources on sleep, sleep was mostly disturbed by roommate conversation (77.42%), and noise caused by roommate sleep-related activities was the most common source of activities (67.74%). The present study can provide guidelines to help enhance the sleep quality of Chinese college students through improvements in the sound environment.

Objective sleep quality and metabolic risk in healthy weight children results from the randomized Childhood Adenotonsillectomy Trial (CHAT)

BACKGROUND

We hypothesized that cardiopulmonary coupling (CPC) sleep quality reflects cardiovascular and cardiometabolic health, in healthy weight children.

METHODS

Retrospective signal analysis of existing ECG data utilizing CPC, FDA cleared, software as medical device (SaMD). ECG signals were extracted from baseline polysomnography studies in the prospective Childhood Adenotonsillectomy Trial database, multicenter, single-blind, randomized controlled trial of 5.0-9.9-year-old children identified with obstructive sleep apnea syndrome without severe hypoxemia. Healthy weight was defined as age- and gender-specific BMI in the 5th-85th percentile range and overweight above the 85th percentile. The cohort was stratified based on CPC sleep quality Index (SQI) defined as high sleep quality (SQI  ≥ 80) or low sleep quality (SQI < 60). Cardiovascular, cardiometabolic, quality of life, and cognition were compared between the sleep quality groups.

RESULTS

Healthy weight children with low sleep quality had more fragmented sleep with significantly higher arousal index (10.0 ± 4.3 vs.7.2 ± 3.1; p = 0.00) and eLFC_BB (12.4 ± 4.9 vs. 0.9 ± 1.0; p < 0.001) CPC indicator of sleep fragmentation, higher average heart rate during sleep (84.5 ± 10.6 vs. 79.4 ± 7.1; p = 0.03) and worse insulin/glucose ratio (1.7 ± 1.6 vs. 1.1 ± 1.1; p = 0.03) and fasting insulin levels (7.9 ± 7.2 vs.5.3 ± 5.5; p = 0.05) when compared to healthy weight children with high sleep quality. SQI significantly correlates with average heart rate during sleep, insulin and triglyceride levels; for a unit increase in SQI, there is 0.154 unit decrease in average heart rate during sleep, 0.109 unit in insulin levels and 0.332 unit in triglyceride levels, respectively.

CONCLUSION

CPC sleep quality offers insights into pediatric sleep and how it affects cardiovascular and cardiometabolic health. ECG is simple signal to collect, which makes this method practical for testing sleep, over multiple nights, and on multiple occasions providing information on sleep dynamics not possible before.

TRIAL REGISTRATION

NCT00560859.

Family contexts and sleep during adolescence

Sleep deprivation among adolescents has received much attention from health researchers and policymakers. Recent research indicates that variation in sleep duration from night to night is associated with multiple health outcomes. While there is evidence that sleep deprivation is socially patterned, we know little about how social contexts are associated with nightly sleep variation during adolescence (a life course stage when nightly sleep variation is particularly high). Given the importance of family environments for influencing adolescents’ sleep patterns, we hypothesized that disadvantaged family contexts would be associated with higher intra-individual variation (IIV) in nightly sleep duration, in addition to lower average nightly sleep duration. We tested these hypotheses in a diverse, population-based sample of 11–17 year-olds (N = 1095) from the Adolescent Health and Development in Context Study. Using survey and ecological momentary assessment data and a novel form of multi-level regression modeling (location-scale mixed modeling), we found that adolescents living in unmarried-parent, low SES, economically insecure, and high caregiver stress families had higher IIV in sleep than adolescents in families with more resources and less caregiver stress. There were fewer family effects on average sleep duration. This suggests family social and economic contexts are associated with an under-researched aspect of adolescent sleep, nightly variation, and may contribute to adolescent sleep problems with implications for their health and health disparities.

•

Consistency in nightly sleep duration is important for adolescent health.

•

SES and family stress associated with variability in sleep duration in adolescents.

•

Caregiver distress also associated with lower mean sleep duration among adolescents.