The case for using digital EEG analysis in clinical sleep medicine

The association of odds ratio product with respiratory and arousal measures in post-stroke patients

STUDY OBJECTIVES

Obstructive Sleep Apnea (OSA) affects up to 70 % of post-stroke patients, complicating recovery and rehabilitation. This study aimed to evaluate the utility of the Odds Ratio Product (ORP), a continuous EEG-derived metric of sleep depth, in predicting conventional respiratory and arousal measures in stroke patients. We hypothesized that ORP metrics will predict conventional measures in patients with a history of stroke or Transient ischemic attack (TIA).

METHODS

A retrospective analysis was conducted on 113 stroke/TIA individuals who underwent in-laboratory polysomnography (PSG). ORP metrics, including ORPnrem, ORPrem, ORP9, and Wake Intrusion Indices (WIIs), were analyzed using multivariate linear regression models. Models were stratified by OSA status. Standardized coefficients were used to assess associations with the apnea-hypopnea index (AHI), respiratory disturbance index (RDI), and arousal indices.

RESULTS

ORP metrics demonstrated statistically significant associations with conventional respiratory and arousal measures, with varying predictive strength across models. Specifically, ORPnrem and WIIs exhibited strong predictive effects across all models. ORP9 significantly predicted respiratory and arousal measures in the overall sample and the OSA subgroup, but its predictive value diminished in the non-OSA subgroup. ORPrem was statistically significantly associated with respiratory and arousal measures; however, its associations with arousal measures were weaker in participants with OSA compared to those without OSA.

CONCLUSION

ORP metrics have the potential to refine OSA diagnoses and improve therapeutic strategies in post-stroke/TIA populations. Their integration into sleep assessments could facilitate early intervention and potentially optimize stroke recovery outcomes, addressing gaps in current evaluation methods.

Evaluation of Sleep Quality in Clinical Practice

A major problem in clinical sleep medicine is that the most comprehensive and sophisticated investigative tool, the polysomnography, fails to provide a reason for the patient's complaints in all but those with sleep apnea and movement disorders. The reasons why conventional metrics of sleep quality are of limited value are discussed in detail. This is followed by description of several well-established features that have not been implemented in clinical practice because of the impracticality of doing the measurements visually. Automation is pending. Finally, several automated features recently derived from spectral analysis of the electroencephalogram were described.

Association of Novel EEG Biomarkers of Sleep Depth and Cortical Arousability with Cardiac Autonomic Modulation in Adolescents

STUDY OBJECTIVES

To examine the developmental association of the odds ratio product (ORP), an electroencephalographic measure of sleep depth, during non-rapid eye movement (NREM) sleep with 24-hour heart rate variability (HRV), an electrocardiographic measure of cardiac autonomic modulation (CAM), in the transition to adolescence.

METHODS

Leveraging data from the Penn State Child Cohort, we performed longitudinal analyses on 313 children (median [Md] age 9 years) followed-up after Md=7.4y and cross-sectional analyses on 344 adolescents (Md=16y). We extracted ORP during NREM sleep and in the 9 seconds following cortical arousals (ORP-9) from 9-hour, in-lab polysomnography, and frequency- and time-domain HRV indices from 24-h Holter ECG monitoring. Longitudinal and cross-sectional, multivariable-adjusted, regression models examined the association between ORP and ORP-9 with adolescent 24-h HRV indices.

RESULTS

Longitudinally, a greater increase in ORP-9 since childhood was associated with lower daytime Log-LF, SDNN, RMSSD and higher HR in adolescence (p<0.05). A greater increase in ORP since childhood was associated with lower nighttime Log-LF and SDNN (p<0.05). Cross-sectionally, higher ORP and ORP-9 were associated with lower daytime and nighttime Log-LF, SDNN or RMSSD and higher HR within adolescence (p<0.05).

CONCLUSIONS

A greater increase in cortical arousability since childhood is a strong developmental predictor of daytime cardiac autonomic imbalance in adolescence. Shallower sleep depth additionally arises as a proximal determinant of both daytime and nighttime cardiac autonomic imbalance within adolescence. These data suggest a coupling between fine-grained spectral measures of the sleeping brain and those of CAM, which may inform sleep-related cardiovascular risk early in life.

Association between sleep microarchitecture and cognition in obstructive sleep apnea

STUDY OBJECTIVES

Obstructive sleep apnea (OSA) increases the risk of cognitive impairment. Measures of sleep microarchitecture from EEG may help identify patients at risk of this complication.

METHODS

Participants with suspected OSA (n = 1142) underwent in-laboratory polysomnography and completed sleep and medical history questionnaires, and tests of global cognition (Montreal Cognitive Assessment, MoCA), memory (Rey Auditory Verbal Learning Test, RAVLT) and information processing speed (Digit-Symbol Coding, DSC). Associations between cognitive scores and stage 2 non-rapid eye movement (NREM) sleep spindle density, power, frequency and %-fast (12-16Hz), odds-ratio product (ORP), normalized EEG power (EEGNP), and the delta:alpha ratio were assessed using multivariable linear regression (MLR) adjusted for age, sex, education, and total sleep time. Mediation analyses were performed to determine if sleep microarchitecture indices mediate the negative effect of OSA on cognition.

RESULTS

All spindle characteristics were lower in participants with moderate and severe OSA (p ≤ .001, vs. no/mild OSA) and positively associated with MoCA, RAVLT, and DSC scores (false discovery rate corrected p-value, q ≤ 0.026), except spindle power which was not associated with RAVLT (q = 0.185). ORP during NREM sleep (ORPNREM) was highest in severe OSA participants (p ≤ .001) but neither ORPNREM (q ≥ 0.230) nor the delta:alpha ratio were associated with cognitive scores in MLR analyses (q ≥ 0.166). In mediation analyses, spindle density and EEGNP (p ≥ .048) mediated moderate-to-severe OSA's negative effect on MoCA scores while ORPNREM, spindle power, and %-fast spindles mediated OSA's negative effect on DSC scores (p ≤ .018).

CONCLUSIONS

Altered spindle activity, ORP and normalized EEG power may be important contributors to cognitive deficits in patients with OSA.

Design of an injectable, self-adhesive, and highly stable hydrogel electrode for sleep recording

High-quality and continuous electroencephalogram (EEG) monitoring is desirable for sleep research, sleep monitoring, and the evaluation and treatment of sleep disorders. Existing continuous EEG monitoring technologies suffer from fragile connections, long-term stability, and complex preparation for electrodes under real-life conditions. Here, we report an injectable and spontaneously cross-linked hydrogel electrode for long-term EEG applications. Specifically, our electrodes have a long-term low impedance on hairy scalp regions of 17.53 kΩ for more than 8 h of recording, high adhesiveness on the skin of 0.92 N cm-1 with repeated attachment capability, and long-term wearability during daily activities and overnight sleep. In addition, our electrodes demonstrate a superior signal-to-noise-ratio of 23.97 decibels (dB) in comparison with commercial wet electrodes of 17.98 dB and share a high agreement of sleep stage classification with commercial wet electrodes during multichannel recording. These results exhibit the potential of our on-site-formed electrodes for high-quality, prolonged EEG monitoring in various scenarios.

Decentralized Data-Privacy Preserving Deep-Learning Approaches for Enhancing Inter-Database Generalization in Automatic Sleep Staging

Automatic sleep staging has been an active field of development. Despite multiple efforts, the area remains a focus of research interest. Indeed, while promising results have reported in past literature, uptake of automatic sleep scoring in the clinical setting remains low. One of the current issues regards the difficulty to generalization performance results beyond the local testing scenario, i.e. across data from different clinics. Issues derived from data-privacy restrictions, that generally apply in the medical domain, pose additional difficulties in the successful development of these methods. We propose the use of several decentralized deep-learning approaches, namely ensemble models and federated learning, for robust inter-database performance generalization and data-privacy preservation in automatic sleep staging scenario. Specifically, we explore four ensemble combination strategies (max-voting, output averaging, size-proportional weighting, and Nelder-Mead) and present a new federated learning algorithm, so-called sub-sampled federated stochastic gradient descent (ssFedSGD). To evaluate generalization capabilities of such approaches, experimental procedures are carried out using a leaving-one-database-out direct-transfer scenario on six independent and heterogeneous public sleep staging databases. The resulting performance is compared with respect to two baseline approaches involving single-database and centralized multiple-database derived models. Our results show that proposed decentralized learning methods outperform baseline local approaches, and provide similar generalization results to centralized database-combined approaches. We conclude that these methods are more preferable choices, as they come with additional advantages concerning improved scalability, flexible design, and data-privacy preservation.

New insights and potential clinical implications of the odds ratio product

The odds ratio product (ORP) is a continuous metric of sleep depth that ranges from 0 (very deep sleep) to 2. 5 (full wakefulness). Its advantage over the conventional method recommended by AASM is that it discloses different levels of stage wake (sleep propensity) and different sleep depths within the same sleep stage. As such, it can be used to identify differences in sleep depth between subjects, and in the same subjects under different circumstances, when differences are not discernible by conventional staging. It also identifies different sleep depths within stage rapid-eye-movement sleep, with possible implications to disorders during this stage. Epoch-by-epoch ORP can be displayed graphically across the night or as average values in conventional sleep stages. In addition, ORP can be reported as % of recording time in specific ORP ranges (e.g., deciles of the total ORP range) where it produces distinct distribution patterns (ORP-architecture) that have been associated with different clinical disorders and outcomes. These patterns offer unique research opportunities to identify different mechanisms and potential therapy for various sleep complaints and disorders. In this review I will discuss how ORP is measured, its validation, differences from delta power, and the various phenotypes, and their postulated mechanisms, identified by ORP architecture and the opportunities for research to advance management of sleep-disordered breathing, insomnia and idiopathic hypersomnia.

Challenges of Applying Automated Polysomnography Scoring at Scale

Automatic polysomnography analysis can be leveraged to shorten scoring times, reduce associated costs, and ultimately improve the overall diagnosis of sleep disorders. Multiple and diverse strategies have been attempted for implementation of this technology at scale in the routine workflow of sleep centers. The field, however, is complex and presents unsolved challenges in a number of areas. Recent developments in computer science and artificial intelligence are nevertheless closing the gap. Technological advances are also opening new pathways for expanding our current understanding of the domain and its analysis.

Exploration of sleep function connection and classification strategies based on sub-period sleep stages

Background

As a medium for developing brain-computer interface systems, EEG signals are complex and difficult to identify due to their complexity, weakness, and differences between subjects. At present, most of the current research on sleep EEG signals are single-channel and dual-channel, ignoring the research on the relationship between different brain regions. Brain functional connectivity is considered to be closely related to brain activity and can be used to study the interaction relationship between brain areas.

Methods

Phase-locked value (PLV) is used to construct a functional connection network. The connection network is used to analyze the connection mechanism and brain interaction in different sleep stages. Firstly, the entire EEG signal is divided into multiple sub-periods. Secondly, Phase-locked value is used for feature extraction on the sub-periods. Thirdly, the PLV of multiple sub-periods is used for feature fusion. Fourthly, the classification performance optimization strategy is used to discuss the impact of different frequency bands on sleep stage classification performance and to find the optimal frequency band. Finally, the brain function network is constructed by using the average value of the fusion features to analyze the interaction of brain regions in different frequency bands during sleep stages.

Results

The experimental results have shown that when the number of sub-periods is 30, the α (8-13 Hz) frequency band has the best classification effect, The classification result after 10-fold cross-validation reaches 92.59%.

Conclusion

The proposed algorithm has good sleep staging performance, which can effectively promote the development and application of an EEG sleep staging system.

Sleep architecture based on sleep depth and propensity: patterns in different demographics and sleep disorders and association with health outcomes

Study Objectives

Conventional metrics of sleep quantity/depth have serious shortcomings. Odds-Ratio-Product (ORP) is a continuous metric of sleep depth ranging from 0 (very deep sleep) to 2.5 (full-wakefulness). We describe an ORP-based approach that provides information on sleep disorders not apparent from traditional metrics.

Methods

We analyzed records from the Sleep-Heart-Health-Study and a study of performance deficit following sleep deprivation. ORP of all 30-second epochs in each PSG and percent of epochs in each decile of ORPs range were calculated. Percentage of epochs in deep sleep (ORP < 0.50) and in full-wakefulness (ORP > 2.25) were each assigned a rank, 1–3, representing first and second digits, respectively, of nine distinct types (“1,1”, “1,2” … ”3,3”). Prevalence of each type in clinical groups and their associations with demographics, sleepiness (Epworth-Sleepiness-Scale, ESS) and quality of life (QOL; Short-Form-Health-Survey-36) were determined.

Results

Three types (“1,1”, “1,2”, “1,3”) were prevalent in OSA and were associated with reduced QOL. Two (“1,3” and “2,3”) were prevalent in insomnia with short-sleep-duration (insomnia-SSD), but only “1,3” was associated with poor sleep depth and reduced QOL, suggesting two phenotypes in insomnia-SSD. ESS was high in types “1,1” and “1,2”, and low in “1,3” and “2,3”. Prevalence of some types increased with age while in others it decreased. Other types were either rare (“1,1” and “3,3”) or high (“2,2”) at all ages.

Conclusions

The proposed ORP histogram offers specific and unique information on the underlying neurophysiological characteristics of sleep disorders not captured by routine metrics, with potential of advancing diagnosis and management of these disorders.

Association of a novel EEG metric of sleep depth/intensity with attention-deficit/hyperactivity, learning, and internalizing disorders and their pharmacotherapy in adolescence

STUDY OBJECTIVES

Psychiatric/learning disorders are associated with sleep disturbances, including those arising from abnormal cortical activity. The odds ratio product (ORP) is a standardized electroencephalogram metric of sleep depth/intensity validated in adults, while ORP data in youth are lacking. We tested ORP as a measure of sleep depth/intensity in adolescents with and without psychiatric/learning disorders.

METHODS

Four hundred eighteen adolescents (median 16 years) underwent a 9-hour, in-lab polysomnography. Of them, 263 were typically developing (TD), 89 were unmedicated, and 66 were medicated for disorders including attention-deficit/hyperactivity (ADHD), learning (LD), and internalizing (ID). Central ORP during non-rapid eye movement (NREM) sleep was the primary outcome. Secondary/exploratory outcomes included central and frontal ORP during NREM stages, in the 9-seconds following arousals (ORP-9), in the first and second halves of the night, during REM sleep and wakefulness.

RESULTS

Unmedicated youth with ADHD/LD had greater central ORP than TD during stage 3 and in central and frontal regions during stage 2 and the second half of the sleep period, while ORP in youth with ADHD/LD on stimulants did not significantly differ from TD. Unmedicated youth with ID did not significantly differ from TD in ORP, while youth with ID on antidepressants had greater central and frontal ORP than TD during NREM and REM sleep, and higher ORP-9.

CONCLUSIONS

The greater ORP in unmedicated youth with ADHD/LD, and normalized levels in those on stimulants, suggests ORP is a useful metric of decreased NREM sleep depth/intensity in ADHD/LD. Antidepressants are associated with greater ORP/ORP-9, suggesting these medications induce cortical arousability.

Characteristics and reproducibility of novel sleep EEG biomarkers and their variation with sleep apnea and insomnia in a large community-based cohort

STUDY OBJECTIVES

New electroencephalogram (EEG) features became available for use in polysomnography and have shown promise in early studies. They include a continuous index of sleep depth (odds-ratio-product: ORP), agreement between right and left sleep depth (R/L coefficient), dynamics of sleep recovery following arousals (ORP-9), general EEG amplification (EEG Power), alpha intrusion and arousal intensity. This study was undertaken to establish ranges and reproducibility of these features in subjects with different demographics and clinical status.

METHODS

We utilized data from the two phases of the Sleep-Heart-Health-Study (SHHS1 and SHHS2). Polysomnograms of 5,804 subjects from SHHS1 were scored to determine the above features. Feature values were segregated according to clinical status of obstructive sleep apnea (OSA), insomnia, insomnia plus OSA, no clinical sleep disorder, and demographics (age, gender, and race). Results from SHHS visit2 were compared with SHHS1 results.

RESULTS

All features varied widely among clinical groups and demographics. Relative to participants with no sleep disorder, wake ORP was higher in participants reporting insomnia symptoms and lower in those with OSA (p < 0.0001 for both), reflecting opposite changes in sleep pressure, while NREM ORP was higher in both insomnia and OSA (p<0.0001), reflecting lighter sleep in both groups. There were significant associations with age, gender, and race. EEG Power, and REM ORP were highly reproducible across the two studies (ICC > 0.75).

CONCLUSIONS

The reported results serve as bases for interpreting studies that utilize novel sleep EEG biomarkers and identify characteristic EEG changes that vary with age, gender and may help distinguish insomnia from OSA.

An automatic sleep disorder detection based on EEG cross-frequency coupling and random forest model

Objective. Sleep disorders are medical disorders of a subject's sleep architecture and based on their severity, they can interfere with mental, emotional and physical functioning. The most common ones are insomnia, narcolepsy, sleep apnea, bruxism, etc. There is an increased risk of developing sleep disorders in elderly like insomnia, periodic leg movements, rapid eye movement behavior disorders, sleep disorder breathing, etc. Consequently, their accurate diagnosis and classification are important steps towards an early stage treatment that could save the life of a patient.Approach. The electroencephalographic (EEG) signal is the most sensitive and important biosignal, which is able to capture the brain sleep activity that is sensitive to sleep. In this study, we attempt to analyze EEG sleep activity via complementary cross-frequency coupling (CFC) estimates, which further feed a classifier, aiming to discriminate sleep disorders. We adopted an open EEG database with recordings that were grouped into seven sleep disorders and a healthy control. The EEG brain activity from common sensors has been analyzed with two basic types of CFC.Main results. Finally, a random forest (RF) classification model was built on CFC patterns, which were extracted from non-cyclic alternating pattern epochs. Our RF^CFCmodel achieved a 74% multiclass accuracy. Both types of CFC, phase-to-amplitude and amplitude-amplitude coupling patterns contribute to the accuracy of the RF model, thus supporting their complementary information.Significance. CFC patterns, in conjunction with the RF classifier proved a valuable biomarker for the classification of sleep disorders.

Maturational trajectories of non-rapid eye movement slow wave activity and odds ratio product in a population-based sample of youth

BACKGROUND

Brain maturation is reflected in the sleep electroencephalogram (EEG) by a decline in non-rapid eye movement (NREM) slow wave activity (SWA) throughout adolescence and a related decrease in sleep depth. However, this trajectory and its sex and pubertal differences lack replication in population-based samples. We tested age-related changes in SWA (0.4-4 Hz) power and odds ratio product (ORP), a standardized measure of sleep depth.

METHODS

We analyzed the sleep EEG of 572 subjects aged 6-21 y (48% female, 26% racial/ethnic minority) and 332 subjects 5-12 y followed-up at 12-22 y. Multivariable-adjusted analyses tested age-related cross-sectional and longitudinal trajectories of SWA and ORP.

RESULTS

SWA remained stable from age 6 to 10, decreased between ages 11 and 17, and plateaued from age 18 to 21 (p-cubic<0.001); females showed a longitudinal decline 23% greater than males by 13 y, while males experienced a steeper slope after 14 y and their longitudinal decline was 21% greater by 19 y. More mature adolescents (75% female) experienced a greater longitudinal decline in SWA than less mature adolescents by 14 y. ORP showed an age-related increasing trajectory (p-linear<0.001) with no sex or pubertal differences.

CONCLUSIONS

We provide population-level evidence for the maturational decline and sex and pubertal differences in SWA in the transition from childhood to adolescence, while introducing ORP as a novel metric in youth. Along with previous studies, the distinct trajectories observed suggest that age-related changes in SWA reflect brain maturation and local/synaptic processes during this developmental period, while those of ORP may reflect global/state control of NREM sleep depth.

EEG-Based Sleep Staging Analysis with Functional Connectivity

Sleep staging is important in sleep research since it is the basis for sleep evaluation and disease diagnosis. Related works have acquired many desirable outcomes. However, most of current studies focus on time-domain or frequency-domain measures as classification features using single or very few channels, which only obtain the local features but ignore the global information exchanging between different brain regions. Meanwhile, brain functional connectivity is considered to be closely related to brain activity and can be used to study the interaction relationship between brain areas. To explore the electroencephalography (EEG)-based brain mechanisms of sleep stages through functional connectivity, especially from different frequency bands, we applied phase-locked value (PLV) to build the functional connectivity network and analyze the brain interaction during sleep stages for different frequency bands. Then, we performed the feature-level, decision-level and hybrid fusion methods to discuss the performance of different frequency bands for sleep stages. The results show that (1) PLV increases in the lower frequency band (delta and alpha bands) and vice versa during different stages of non-rapid eye movement (NREM); (2) alpha band shows a better discriminative ability for sleeping stages; (3) the classification accuracy of feature-level fusion (six frequency bands) reaches 96.91% and 96.14% for intra-subject and inter-subjects respectively, which outperforms decision-level and hybrid fusion methods.

Deep Learning in Automatic Sleep Staging With a Single Channel Electroencephalography

This study centers on automatic sleep staging with a single channel electroencephalography (EEG), with some significant findings for sleep staging. In this study, we proposed a deep learning-based network by integrating attention mechanism and bidirectional long short-term memory neural network (AT-BiLSTM) to classify wakefulness, rapid eye movement (REM) sleep and non-REM (NREM) sleep stages N1, N2 and N3. The AT-BiLSTM network outperformed five other networks and achieved an accuracy of 83.78%, a Cohen's kappa coefficient of 0.766 and a macro F1-score of 82.14% on the PhysioNet Sleep-EDF Expanded dataset, and an accuracy of 81.72%, a Cohen's kappa coefficient of 0.751 and a macro F1-score of 80.74% on the DREAMS Subjects dataset. The proposed AT-BiLSTM network even achieved a higher accuracy than the existing methods based on traditional feature extraction. Moreover, better performance was obtained by the AT-BiLSTM network with the frontal EEG derivations than with EEG channels located at the central, occipital or parietal lobe. As EEG signal can be easily acquired using dry electrodes on the forehead, our findings might provide a promising solution for automatic sleep scoring without feature extraction and may prove very useful for the screening of sleep disorders.

ENT Manifestations of Celiac Disease: A Scholarly Review

OBJECTIVES

Celiac disease is a common multisystemic autoimmune disorder. It is now increasingly recognized that it may present with extraintestinal manifestations which contribute to the difficulty in its diagnosis. The objective of this scholarly review was to examine the extraintestinal ENT manifestations of celiac disease and its pathophysiology and management, in order to highlight that some patients with celiac disease may present initially to the otolaryngologist. Improving awareness of celiac disease among otolaryngologists may aid in the correct diagnosis and correct management plan.

METHODS

A literature review was conducted using the PubMed database to identify original articles related to celiac disease and ENT manifestations between the years 2000 and 2020. The search was performed using the search string: ("coeliac disease" OR "celiac disease") AND ("ENT manifestations" OR "hearing loss" OR "epistaxis" OR "nasal septal perforation" OR "obstructive sleep apnoea" OR "vertigo" OR "tonsillitis" OR "sinusitis"). Only articles written in English were reviewed.

RESULTS

A total of 17 papers met the inclusion criteria. Extraintestinal ENT manifestations of celiac disease include sensorineural hearing loss, obstructive sleep apnea, nasal septal perforation, epistaxis, and vertigo with nystagmus. Sensorineural hearing loss, obstructive sleep apnea, nasal septal perforation, vertigo, and nystagmus are thought to result from immunologically mediated mechanisms, with intestinal malabsorption resulting in epistaxis.

CONCLUSIONS

Celiac disease can cause extraintestinal ENT manifestations and requires a high index of suspicion from the otolaryngologist to diagnose and suitably manage. A gluten-free diet may result in sufficient symptom resolution for most manifestations. Sensorineural hearing loss due to celiac disease appears to be progressive and permanent and may require frequent audiological monitoring.

Obstructive Sleep Apnea and Its Treatment in Aging: Effects on Alzheimer's disease Biomarkers, Cognition, Brain Structure and Neurophysiology

Here we review the impact of obstructive sleep apnea (OSA) on biomarkers of Alzheimer's disease (AD) pathogenesis, neuroanatomy, cognition and neurophysiology, and present the research investigating the effects of continuous positive airway pressure (CPAP) therapy. OSA is associated with an increase in AD markers amyloid-β and tau measured in cerebrospinal fluid (CSF), by Positron Emission Tomography (PET) and in blood serum. There is some evidence suggesting CPAP therapy normalizes AD biomarkers in CSF but since mechanisms for amyloid-β and tau production/clearance in humans are not completely understood, these findings remain preliminary. Deficits in the cognitive domains of attention, vigilance, memory and executive functioning are observed in OSA patients with the magnitude of impairment appearing stronger in younger people from clinical settings than in older community samples. Cognition improves with varying degrees after CPAP use, with the greatest effect seen for attention in middle age adults with more severe OSA and sleepiness. Paradigms in which encoding and retrieval of information are separated by periods of sleep with or without OSA have been done only rarely, but perhaps offer a better chance to understand cognitive effects of OSA than isolated daytime testing. In cognitively normal individuals, changes in EEG microstructure during sleep, particularly slow oscillations and spindles, are associated with biomarkers of AD, and measures of cognition and memory. Similar changes in EEG activity are reported in AD and OSA, such as "EEG slowing" during wake and REM sleep, and a degradation of NREM EEG microstructure. There is evidence that CPAP therapy partially reverses these changes but large longitudinal studies demonstrating this are lacking. A diagnostic definition of OSA relying solely on the Apnea Hypopnea Index (AHI) does not assist in understanding the high degree of inter-individual variation in daytime impairments related to OSA or response to CPAP therapy. We conclude by discussing conceptual challenges to a clinical trial of OSA treatment for AD prevention, including inclusion criteria for age, OSA severity, and associated symptoms, the need for a potentially long trial, defining relevant primary outcomes, and which treatments to target to optimize treatment adherence.

Mechanism of excessive wake time when associated with obstructive sleep apnea or periodic limb movements

STUDY OBJECTIVES

It is uncertain whether obstructive apnea (OSA) or periodic limb movements (PLMs) contribute to excessive wake time (EWT) when EWT and these disorders coexist. We hypothesized that such EWT is an independent disorder related to central regulation of sleep depth. Accordingly, we compared sleep depth in patients with EWT and OSA/PLMs (EWT+P) with patients with EWT and no OSA/PLMs (EWT-NP) and patients with a normal wake time.

METHODS

A total of 267 participants were divided into five groups: (1) EWT+P: n = 100 (wake time > 20% total recording time; TRT) with OSA (apnea-hypopnea index 5-110 events/h) and/or PLMs (PLM index 10-151 events/h); (2) EWT-NP: n = 49 (wake time > 20%TRT), no associated pathology; (3) normal wake time (NWT)+P: n = 54 (wake time < 20%TRT, with OSA/PLMs); (4) NWT-NP: n = 26; (5) Healthy participants: n = 38 (no sleep complaints, NWT and no OSA/PLMs). Sleep depth was evaluated by the odds ratio product (ORP; 0 = deep sleep, 2.5 = fully alert). We also measured ORP in the 9 seconds immediately following arousals (ORP-9) to distinguish between peripheral and central mechanisms of light sleep.

RESULTS

ORP during sleep was higher (lighter sleep) in both EWT groups than in the three NWT groups (P < 1E-11) with no difference between those with and those without OSA/PLMs. ORP-9 was also significantly higher in the EWT groups than in the NWT groups (P < 1E-19), also with no difference between those with and without OSA/PLMs, indicating that the lighter sleep was of central origin. There were highly significant correlations between wake time and ORP-9 across all groups (P < 1E-35).

CONCLUSIONS

EWT associated with OSA/PLMs is independent of OSA/PLMs and related to abnormal central regulation of sleep depth.

Deep residual networks for automatic sleep stage classification of raw polysomnographic waveforms

We have developed an automatic sleep stage classification algorithm based on deep residual neural networks and raw polysomnogram signals. Briefly, the raw data is passed through 50 convolutional layers before subsequent classification into one of five sleep stages. Three model configurations were trained on 1850 polysomnogram recordings and subsequently tested on 230 independent recordings. Our best performing model yielded an accuracy of 84.1% and a Cohen's kappa of 0.746, improving on previous reported results by other groups also using only raw polysomnogram data. Most errors were made on non-REM stage 1 and 3 decisions, errors likely resulting from the definition of these stages. Further testing on independent cohorts is needed to verify performance for clinical use.

An original method for staging sleep based on dynamical analysis of a single EEG signal

BACKGROUND

The dynamical complexity of brain electrical activity manifested in the EEG is quantifiable using recurrence analysis (RA). Employing RA, we described and validated an originative method for automatically classifying epochs of sleep that is conceptually and instrumentally distinct from the existing method.

NEW METHOD

Complexity in single overnight EEGs was characterized second-by-second using four RA variables that were each averaged over consecutive 30-sec epochs to form four-component vectors. The vectors were staged using four-component cluster analysis. Method validity and utility were established by showing: (1) inter- and intra-subject consistency of staging results (method insusceptible to nonstationarity of the EEG); (2) use of method to eliminate costly and arduous visual staging in a binary classifications task for detecting a neurogenic disorder; (3) ability of method to provide new physiological insights into brain activity during sleep.

RESULTS

RA of sleep-acquired EEGs yielded four continuous measures of complexity and its change-rate that allowed automatic classification of epochs into four statistically distinct clusters ("stages"). Matched subjects with and without mental distress were accurately classified using biomarkers based on stage designations.

COMPARISON WITH EXISTING METHODS

For binary-classification purposes, the method was cheaper, faster, and at least as accurate as the existing staging method. Epoch-by-epoch comparison of new versus existing methods revealed that the latter assigned epochs having widely different dynamical complexities into the same stage (dynamical incoherence).

CONCLUSIONS

Sleep can be automatically staged using an originative method that is fundamentally different from the existing method.

Opportunities for utilizing polysomnography signals to characterize obstructive sleep apnea subtypes and severity

BACKGROUND

Obstructive sleep apnea (OSA) is a heterogeneous sleep disorder with many pathophysiological pathways to disease. Currently, the diagnosis and classification of OSA is based on the apnea-hypopnea index, which poorly correlates to underlying pathology and clinical consequences. A large number of in-laboratory sleep studies are performed around the world every year, already collecting an enormous amount of physiological data within an individual. Clinically, we have not yet fully taken advantage of this data, but combined with existing analytical approaches, we have the potential to transform the way OSA is managed within an individual patient. Currently, respiratory signals are used to count apneas and hypopneas, but patterns such as inspiratory flow signals can be used to predict optimal OSA treatment. Electrocardiographic data can reveal arrhythmias, but patterns such as heart rate variability can also be used to detect and classify OSA. Electroencephalography is used to score sleep stages and arousals, but specific patterns such as the odds-ratio product can be used to classify how OSA patients responds differently to arousals.

OBJECTIVE

In this review, we examine these and many other existing computer-aided polysomnography signal processing algorithms and how they can reflect an individual's manifestation of OSA.

SIGNIFICANCE

Together with current technological advance, it is only a matter of time before advanced automatic signal processing and analysis is widely applied to precision medicine of OSA in the clinical setting.

Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics

Sleep staging, the process of assigning labels to epochs of sleep, depending on the stage of sleep they belong, is an arduous, time consuming and error prone process as the initial recordings are quite often polluted by noise from different sources. To properly analyze such data and extract clinical knowledge, noise components must be removed or alleviated. In this paper a pre-processing and subsequent sleep staging pipeline for the sleep analysis of electroencephalographic signals is described. Two novel methods of functional connectivity estimation (Synchronization Likelihood/SL and Relative Wavelet Entropy/RWE) are comparatively investigated for automatic sleep staging through manually pre-processed electroencephalographic recordings. A multi-step process that renders signals suitable for further analysis is initially described. Then, two methods that rely on extracting synchronization features from electroencephalographic recordings to achieve computerized sleep staging are proposed, based on bivariate features which provide a functional overview of the brain network, contrary to most proposed methods that rely on extracting univariate time and frequency features. Annotation of sleep epochs is achieved through the presented feature extraction methods by training classifiers, which are in turn able to accurately classify new epochs. Analysis of data from sleep experiments on a randomized, controlled bed-rest study, which was organized by the European Space Agency and was conducted in the "ENVIHAB" facility of the Institute of Aerospace Medicine at the German Aerospace Center (DLR) in Cologne, Germany attains high accuracy rates, over 90% based on ground truth that resulted from manual sleep staging by two experienced sleep experts. Therefore, it can be concluded that the above feature extraction methods are suitable for semi-automatic sleep staging.

Large-Scale Automated Sleep Staging

Study Objectives

Automated sleep staging has been previously limited by a combination of clinical and physiological heterogeneity. Both factors are in principle addressable with large data sets that enable robust calibration. However, the impact of sample size remains uncertain. The objectives are to investigate the extent to which machine learning methods can approximate the performance of human scorers when supplied with sufficient training cases and to investigate how staging performance depends on the number of training patients, contextual information, model complexity, and imbalance between sleep stage proportions.

Methods

A total of 102 features were extracted from six electroencephalography (EEG) channels in routine polysomnography. Two thousand nights were partitioned into equal (n = 1000) training and testing sets for validation. We used epoch-by-epoch Cohen's kappa statistics to measure the agreement between classifier output and human scorer according to American Academy of Sleep Medicine scoring criteria.

Results

Epoch-by-epoch Cohen's kappa improved with increasing training EEG recordings until saturation occurred (n = ~300). The kappa value was further improved by accounting for contextual (temporal) information, increasing model complexity, and adjusting the model training procedure to account for the imbalance of stage proportions. The final kappa on the testing set was 0.68. Testing on more EEG recordings leads to kappa estimates with lower variance.

Conclusion

Training with a large data set enables automated sleep staging that compares favorably with human scorers. Because testing was performed on a large and heterogeneous data set, the performance estimate has low variance and is likely to generalize broadly.