Age and gender dependency of physiological networks in sleep

Quantifying the Suitability of Biosignals Acquired During Surgery for Multimodal Analysis

Goal: Recently, large datasets of biosignals acquired during surgery became available. As they offer multiple physiological signals measured in parallel, multimodal analysis - which involves their joint analysis - can be conducted and could provide deeper insights than unimodal analysis based on a single signal. However, it is unclear what percentage of intraoperatively acquired data is suitable for multimodal analysis. Due to the large amount of data, manual inspection and labelling into suitable and unsuitable segments are not feasible. Nevertheless, multimodal analysis is performed successfully in sleep studies since many years as their signals have proven suitable. Hence, this study evaluates the suitability to perform multimodal analysis on a surgery dataset (VitalDB) using a multi-center sleep dataset (SIESTA) as reference. Methods: We applied widely known algorithms entitled "signal quality indicators" to the common biosignals in both datasets, namely electrocardiography, electroencephalography, and respiratory signals split in segments of 10 s duration. As there are no multimodal methods available, we used only unimodal signal quality indicators. In case, all three signals were determined as being adequate by the indicators, we assumed that the whole signal segment was suitable for multimodal analysis. Results: 82% of SIESTA and 72% of VitalDB are suitable for multimodal analysis. Unsuitable signal segments exhibit constant or physiologically unreasonable values. Histogram examination indicated similar signal quality distributions between the datasets, albeit with potential statistical biases due to different measurement setups. Conclusions: The majority of data within VitalDB is suitable for multimodal analysis.

Self-reported quantity and quality of sleep in children and adolescents with a chronic condition compared to healthy controls

To assess self-reported quantity and quality of sleep in Dutch children with a chronic condition compared to healthy controls and to the recommended hours of sleep for youth. Sleep quantity and quality were analyzed in children with a chronic condition (cystic fibrosis, chronic kidney disease, congenital heart disease, (auto-)immune disease, and medically unexplained symptoms (MUS); n = 291; 15 ± 3.1 years, 63% female. A subset of 171 children with a chronic condition were matched to healthy controls using Propensity Score matching, based on age and sex, ratio 1:4. Self-reported sleep quantity and quality were assessed with established questionnaires. Children with MUS were analyzed separately to distinguish between chronic conditions with and without an identified pathophysiological cause. Generally, children with a chronic condition met the recommended amount of sleep, however 22% reported poor sleep quality. No significant differences in sleep quantity and quality were found between the diagnosis groups. Children with a chronic condition and with MUS slept significantly more than healthy controls at ages 13, 15, and 16. Both at primary and secondary school, poor sleep quality was least frequent reported in children with a chronic condition and most often reported in children with MUS.  Conclusion: Overall, children with chronic conditions, including MUS, met the recommended hours of sleep for youth, and slept more than healthy controls. However, it is important to obtain a better understanding of why a substantial subset of children with chronic conditions, mostly children with MUS, still perceived their sleep quality as poor. What is Known: • According to the Consensus statement of the American Academy of Sleep medicine, typically developing children (6 to 12 years) should sleep 9 to 12 h per night, and adolescents (13 to 18 years) should sleep 8 to 10 h per night. • Literature on the optimal quantity and quality of sleep in children with a chronic condition is very limited. What is New: Our findings are important and provide novel insights: • In general, children with a chronic condition sleep according to the recommended hours of sleep. • A substantial subset of children with chronic conditions, perceived their sleep quality as poor. Although this was reported mostly by children with medically unexplained symptoms (MUS), the found poor sleep quality was independent of specific diagnosis.

Sleep Efficiency and Total Sleep Time in Individuals with Type 2 Diabetes with and without Insomnia Symptoms

There is increasing awareness of the high prevalence of insomnia symptoms in individuals with type 2 diabetes (T2D). Past studies have established the importance of measuring sleep parameters using measures of central tendency and variability. Additionally, subjective and objective methods involve different constructs due to the discrepancies between the two approaches. Therefore, this study is aimed at comparing the averages of sleep parameters in individuals with T2D with and without insomnia symptoms and comparing the variability of sleep parameters in these individuals. This study assessed the between-group differences in the averages and variability of sleep efficiency (SE) and total sleep time (TST) of 59 participants with T2D with and without insomnia symptoms. Actigraph measurements and sleep diaries were used to assess sleep parameter averages and variabilities calculated by the coefficient of variation across 7 nights. Mann-Whitney U tests were utilized to compare group differences in the outcomes. Validated instruments were used to assess the symptoms of depression, anxiety, and pain as covariates. Objective SE was found to be statistically lower on average (85.98 ± 4.29) and highly variable (5.88 ± 2.57) for patients with T2D and insomnia symptoms than in those with T2D only (90.23 ± 6.44 and 3.82 ± 2.05, respectively). The subjective average and variability of SE were also worse in patients with T2D and insomnia symptoms, with symptoms of depression, anxiety, and pain potentially playing a role in this difference. TST did not significantly differ between the groups on averages or in variability even after controlling for age and symptoms of depression, anxiety, and pain. Future studies are needed to investigate the underlying mechanisms of worse averages and variability of SE in individuals with T2D and insomnia symptoms. Additionally, prompting the associated risk factors of insomnia symptoms in individuals with T2D might be warranted.

Effect of Cognitive Behavioral Therapy for Insomnia on Insomnia Symptoms for Individuals With Type 2 Diabetes: Protocol for a Pilot Randomized Controlled Trial

Background

Insomnia symptoms are a common form of sleep difficulty among people with type 2 diabetes (T2D) affecting sleep quality and health outcomes. Several interventional approaches have been used to improve sleep outcomes in people with T2D. Nonpharmacological approaches, such as cognitive behavioral therapy for insomnia (CBT-I), show promising results regarding safety and sustainability of improvements, although CBT-I has not been examined in people with T2D. Promoting sleep for people with insomnia and T2D could improve insomnia severity and diabetes outcomes.

Objective

The objective of this study is to establish a protocol for a pilot randomized controlled trial (RCT) to examine the effect of 6 sessions of CBT-I on insomnia severity (primary outcome), sleep variability, and other health-related outcomes in individuals with T2D and insomnia symptoms.

Methods

This RCT will use random mixed block size randomization with stratification to assign 28 participants with T2D and insomnia symptoms to either a CBT-I group or a health education group. Outcomes including insomnia severity; sleep variability; diabetes self-care behavior (DSCB); glycemic control (A_1c); glucose level; sleep quality; daytime sleepiness; and symptoms of depression, anxiety, and pain will be gathered before and after the 6-week intervention. Chi-square and independent t tests will be used to test for between-group differences at baseline. Independent t tests will be used to examine the effect of the CBT-I intervention on change score means for insomnia severity, sleep variability, DSCB, A_1c, fatigue, sleep quality, daytime sleepiness, and severity of depression, anxiety, and pain. For all analyses, alpha level will be set at .05.

Results

This study recruitment began in February 2019 and was completed in September 2019.

Conclusions

The intervention, including 6 sessions of CBT-I, will provide insight about its effect in improving insomnia symptoms, sleep variability, fatigue, and diabetes-related health outcomes in people with T2D and those with insomnia symptoms when compared with control.

Trial Registration

ClinicalTrials.gov NCT03713996; https://clinicaltrials.gov/ct2/show/NCT03713996

International Registered Report Identifier (IRRID)

DERR1-10.2196/14647

Network physiology in insomnia patients: Assessment of relevant changes in network topology with interpretable machine learning models

Network physiology describes the human body as a complex network of interacting organ systems. It has been applied successfully to determine topological changes in different sleep stages. However, the number of network links can quickly grow above the number of parameters that are typically analyzed with standard statistical methods. Artificial Neural Networks (ANNs) are a promising approach as they are successful in large parameter spaces, such as in digital imaging. On the other hand, ANN models do not provide an intrinsic approach to interpret their predictions, and they typically require large training data sets. Both aspects are critical in biomedical research. Medical decisions need to be explainable, and large data sets of quality assured patient and control data are rare. In this paper, different models for the classification of insomnia-a common sleep disorder-have been trained with 59 patients and age and gender matched controls, based on their physiological networks. Feature relevance evaluation is employed for all methods. For ANNs, the extrinsic interpretation method DeepLift is applied. The results are not identical across methods, but certain network links have been rated as relevant by all or most of the models. While ANNs show less classification accuracy (0.89) than advanced tree-based models (0.92 and 0.93), DeepLift provides an in-depth ANN interpretation with feature relevance scores for individual data samples. The analysis revealed modifications in the pulmonar, ocular, and cerebral subnetworks that have not been described before but are consistent with known findings on the physiological impact of insomnia.

Feature relevance in physiological networks for classification of obstructive sleep apnea

OBJECTIVE

Physiological networks (PN) model couplings between organs in a high-dimensional parameter space. Machine learning methods, in particular artifical neural networks (ANNs), are powerful on high-dimensional classification tasks. However, lack of interpretability of the resulting models has been a drawback in research. We assess relevant PN topology changes in obstructive sleep apnea (OSA) by novel ANN interpretation techniques.

APPROACH

ANNs are trained to classify OSA based on the PNs of 48 patients and 48 age and gender matched healthy controls. The PNs consisting of 2812 links are derived from overnight biosignal recordings. The interpretation technique DeepLift is applied to the resulting ANN models, enabling the determination of the relevant features for classification decisions on individual subjects. The mean relevance scores of the features are compared to other machine learning methods (decision tree and random forests) and statistical tests on group differences.

MAIN RESULTS

The ANN interpretation results show good agreement with the compared methods and 87% of the samples could be correctly classified. OSA patients show a significantly higher coupling (p [Formula: see text] 0.001) in light sleep (N2) between breathing rate and EEG [Formula: see text] power in all electrode locations and to chin and leg muscular tone. In deep sleep (N3), OSA leads to significantly lower coupling (p [Formula: see text] 0.01) in lateral connections of EEG [Formula: see text] and [Formula: see text] power in central and frontal positions. Misclassified OSA patients had all mild/moderate AHIs and did not show PN topology changes. Both nights of these patients have been consistently misclassified as healthy. This may indicate, that the impact of respiratory events differs in subjects, thus forming different phenotypes.

SIGNIFICANCE

The proposed PN analysis provides a powerful and robust method to quantify a broad range of physiological interactions. Interpretability of the ANN make them a promising tool to identify new diagnostic markers in data-driven approaches.