Beyond K-complex binary scoring during sleep: probabilistic classification using deep learning

Cognitive-behavioural therapy for insomnia mechanism of action: Exploring the homeostatic K-complex involvement

Investigating the mechanisms of action of cognitive-behavioural therapy for insomnia (CBT-I), the first-line treatment for chronic insomnia disorder (ID), can contribute to the overall understanding of insomnia and its treatment. To date, no study has examined the relationship between K-complexes (KC) and CBT-I, despite the known homeostatic and protective function of this relevant sleep brainwave. This retrospective multicentre study aims to explore the relationship between electroencephalographic (EEG) indices and CBT-I, with a particular focus on evaluating an index of sleep homeostasis identified by KC. This research is designed to assess the predictive value of this index for treatment outcomes and to examine its variations before and after intervention. Ninety eight patients with ID underwent a 6-8 week in-person CBT-I programme, with pre-and post-treatment evaluation conducted using polysomnography (PSG) and the Insomnia Severity Index (ISI). The main outcome was determined by calculating the slope of the linear equation indexing the KC density (number of KC/minutes of N2) in each non-artifacted NREM stage 2 epoch throughout the night (KCSlope). Furthermore, the sample was categorised into Responders (ISIdecrease ≥8) and non-Responders (ISIdecrease <8). The results indicate that the KC Slope is effective not only to predict treatment response (one-way ANOVA, F = 7.831 p = 0.007; Responders = -2.954*10-5 ± 3.346*10-5, non-Responders = -5.583*10-5 ± 5.305*10-5; adjusted for PSG wake after sleep onset at the baseline), but also to detect a statistically significant improvement in sleep pressure following CBT-I (Wilcoxon signed-rank test W = 3074.000 p = 0.022; KCSlope pre-treatment = -4.054*10-5 ± 4.446*10-5, KCSlope post-treatment = -4.797*10-5 ± 5.710*10-5). These findings suggest that CBT-I increases sleep pressure in patients with chronic insomnia, highlighting a novel and relevant biomarker in this context.

A robust deep learning detector for sleep spindles and K-complexes: towards population norms

Sleep spindles (SSs) and K-complexes (KCs) are brain patterns involved in cognitive functions that appear during sleep. Large-scale sleep studies would benefit from precise and robust automatic sleep event detectors, capable of adapting the variability in both electroencephalography (EEG) signals and expert annotation rules. We introduce the Sleep EEG Event Detector (SEED), a deep learning system that outperforms existing approaches in SS and KC detection, reaching an F1-score of 80.5% and 83.7%, respectively, on the MASS2 dataset. SEED transfers well and requires minimal fine-tuning for new datasets and annotation styles. Remarkably, SEED substantially reduces the required amount of annotated data by using a novel pretraining approach that leverages the rule-based detector A7. An analysis of 11,224 subjects revealed that SEED's detections provide better estimates of SS population statistics than existing approaches. SEED is a powerful resource for obtaining sleep-event statistics that could be useful for establishing population norms.

Establishing the acute physiological and sleep disruption characteristics of wind farm versus road traffic noise disturbances in sleep: a randomized controlled trial protocol

Study Objectives

Despite the global expansion of wind farms, effects of wind farm noise (WFN) on sleep remain poorly understood. This protocol details a randomized controlled trial designed to compare the sleep disruption characteristics of WFN versus road traffic noise (RTN).

Methods

This study was a prospective, seven night within-subjects randomized controlled in-laboratory polysomnography-based trial. Four groups of adults were recruited from; <10 km away from a wind farm, including those with, and another group without, noise-related complaints; an urban RTN exposed group; and a group from a quiet rural area. Following an acclimation night, participants were exposed, in random order, to two separate nights with 20-s or 3-min duration WFN and RTN noise samples reproduced at multiple sound pressure levels during established sleep. Four other nights tested for continuous WFN exposure during wake and/or sleep on sleep outcomes.

Results

The primary analyses will assess changes in electroencephalography (EEG) assessed as micro-arousals (EEG shifts to faster frequencies lasting 3-15 s) and awakenings (>15 s events) from sleep by each noise type with acute (20-s) and more sustained (3-min) noise exposures. Secondary analyses will compare dose-response effects of sound pressure level and noise type on EEG K-complex probabilities and quantitative EEG measures, and cardiovascular activation responses. Group effects, self-reported noise sensitivity, and wake versus sleep noise exposure effects will also be examined.

Conclusions

This study will help to clarify if wind farm noise has different sleep disruption characteristics compared to road traffic noise.

Clinical applications of artificial intelligence in sleep medicine: a sleep clinician's perspective

BACKGROUND

The past few years have seen a rapid emergence of artificial intelligence (AI)-enabled technology in the field of sleep medicine. AI refers to the capability of computer systems to perform tasks conventionally considered to require human intelligence, such as speech recognition, decision-making, and visual recognition of patterns and objects. The practice of sleep tracking and measuring physiological signals in sleep is widely practiced. Therefore, sleep monitoring in both the laboratory and ambulatory environments results in the accrual of massive amounts of data that uniquely positions the field of sleep medicine to gain from AI.

METHOD

The purpose of this article is to provide a concise overview of relevant terminology, definitions, and use cases of AI in sleep medicine. This was supplemented by a thorough review of relevant published literature.

RESULTS

Artificial intelligence has several applications in sleep medicine including sleep and respiratory event scoring in the sleep laboratory, diagnosing and managing sleep disorders, and population health. While still in its nascent stage, there are several challenges which preclude AI's generalizability and wide-reaching clinical applications. Overcoming these challenges will help integrate AI seamlessly within sleep medicine and augment clinical practice.

CONCLUSION

Artificial intelligence is a powerful tool in healthcare that may improve patient care, enhance diagnostic abilities, and augment the management of sleep disorders. However, there is a need to regulate and standardize existing machine learning algorithms prior to its inclusion in the sleep clinic.

A novel EEG marker predicts perceived sleepiness and poor sleep quality

STUDY OBJECTIVES

To determine if a novel EEG-derived continuous index of sleep depth/alertness, the odds ratio product (ORP), predicts self-reported daytime sleepiness and poor sleep quality in two large population-based cohorts.

METHODS

ORP values which range from 0 (deep sleep) to 2.5 (fully alert) were calculated in 3s intervals during awake periods (ORPwake) and NREM sleep (ORPNREM) determined from home sleep studies in the HypnoLaus (N = 2162: 1106 females, 1056 males) and men androgen inflammation lifestyle environment and stress (MAILES) cohorts (N = 754 males). Logistic regression was used to examine associations between ORPwake, ORPNREM, and traditional polysomnography measures (as comparators) with excessive sleepiness (Epworth sleepiness scale >10) and poor sleep quality (Pittsburgh sleep quality index >5) and insomnia symptoms.

RESULTS

High ORPwake was associated with a ~30% increase in poor sleep quality in both HypnoLaus (odds ratio, OR, and 95% CI) 1.28 (1.09, 1.51), and MAILES 1.36 (1.10, 1.68). High ORPwake was also associated with a ~28% decrease in excessive daytime sleepiness in the MAILES dataset. ORPNREM was associated with a ~30% increase in poor sleep quality in HypnoLaus but not in MAILES. No consistent associations across cohorts were detected using traditional polysomnography markers.

CONCLUSIONS

ORP, a novel EEG-derived metric, measured during wake periods predicts poor sleep quality in two independent cohorts. Consistent with insomnia symptomatology of poor perceived sleep in the absence of excessive daytime sleepiness, ORPwake may provide valuable objective mechanistic insight into physiological hyperarousal.

The association between sleep microarchitecture and cognitive function in middle-aged and older men: a community-based cohort study

STUDY OBJECTIVES

Sleep microarchitecture parameters determined by quantitative power spectral analysis (PSA) of electroencephalograms (EEGs) have been proposed as potential brain-specific markers of cognitive dysfunction. However, data from community samples remains limited. This study examined cross-sectional associations between sleep microarchitecture and cognitive dysfunction in community-dwelling men.

METHODS

Florey Adelaide Male Ageing Study participants (n=477) underwent home-based polysomnography (PSG) (2010-2011). All-night EEG recordings were processed using PSA following artefact exclusion. Cognitive testing (2007-2010) included the inspection time task, trail-making tests A (TMT-A) and B (TMT-B), and Fuld object memory evaluation. Complete case cognition, PSG, and covariate data were available in 366 men. Multivariable linear regression models controlling for demographic, biomedical, and behavioral confounders determined cross-sectional associations between sleep microarchitecture and cognitive dysfunction overall and by age-stratified subgroups.

RESULTS

In the overall sample, worse TMT-A performance was associated with higher NREM theta and REM theta and alpha but lower delta power (all p<0.05). In men ≥65 years, worse TMT-A performance was associated with lower NREM delta but higher NREM and REM theta and alpha power (all p<0.05). Furthermore, in men ≥65 years, worse TMT-B performance was associated with lower REM delta but higher theta and alpha power (all p<0.05).

CONCLUSIONS

Sleep microarchitecture parameters may represent important brain-specific markers of cognitive dysfunction, particularly in older community-dwelling men. Therefore, this study extends the emerging community-based cohort literature on a potentially important link between sleep microarchitecture and cognitive dysfunction. Utility of sleep microarchitecture for predicting prospective cognitive dysfunction and decline warrants further investigation.

Environmental noise-induced cardiovascular responses during sleep

STUDY OBJECTIVES

This study was designed to test the utility of cardiovascular responses as markers of potentially different environmental noise disruption effects of wind farm compared to traffic noise exposure during sleep.

METHODS

Twenty participants underwent polysomnography. In random order, and at six sound pressure levels from 33 dBA to 48 dBA in 3 dB increments, three types of wind farm and two types of road traffic noise recordings of 20-sec duration were played during established N2 or deeper sleep, each separated by 20 seconds without noise. Each noise sequence also included a no-noise control. Electrocardiogram and finger pulse oximeter recorded pulse wave amplitude changes from the pre-noise onset baseline following each noise exposure and were assessed algorithmically to quantify the magnitude of heart rate and finger vasoconstriction responses to noise exposure.

RESULTS

Higher sound pressure levels were more likely to induce drops in pulse wave amplitude. Sound pressure levels as low as 39 dBA evoked a pulse wave amplitude response (Odds ratio [95% confidence interval]; 1.52 [1.15, 2.02]). Wind farm noise with amplitude modulation was less likely to evoke a pulse wave amplitude response than the other noise types, but warrants cautious interpretation given low numbers of replications within each noise type.

CONCLUSION

These preliminary data support that drops in pulse wave amplitude are a particularly sensitive marker of noise-induced cardiovascular responses during. Larger trials are clearly warranted to further assess relationships between recurrent cardiovascular activation responses to environmental noise and potential long-term health effects.

New and Emerging Approaches to Better Define Sleep Disruption and Its Consequences

Current approaches to quantify and diagnose sleep disorders and circadian rhythm disruption are imprecise, laborious, and often do not relate well to key clinical and health outcomes. Newer emerging approaches that aim to overcome the practical and technical constraints of current sleep metrics have considerable potential to better explain sleep disorder pathophysiology and thus to more precisely align diagnostic, treatment and management approaches to underlying pathology. These include more fine-grained and continuous EEG signal feature detection and novel oxygenation metrics to better encapsulate hypoxia duration, frequency, and magnitude readily possible via more advanced data acquisition and scoring algorithm approaches. Recent technological advances may also soon facilitate simple assessment of circadian rhythm physiology at home to enable sleep disorder diagnostics even for “non-circadian rhythm” sleep disorders, such as chronic insomnia and sleep apnea, which in many cases also include a circadian disruption component. Bringing these novel approaches into the clinic and the home settings should be a priority for the field. Modern sleep tracking technology can also further facilitate the transition of sleep diagnostics from the laboratory to the home, where environmental factors such as noise and light could usefully inform clinical decision-making. The “endpoint” of these new and emerging assessments will be better targeted therapies that directly address underlying sleep disorder pathophysiology via an individualized, precision medicine approach. This review outlines the current state-of-the-art in sleep and circadian monitoring and diagnostics and covers several new and emerging approaches to better define sleep disruption and its consequences.

A Novel EEG Derived Measure of Disrupted Delta Wave Activity during Sleep Predicts All-Cause Mortality Risk

RATIONALE

Conventional markers of sleep disturbance, based on manual electroencephalography scoring, may not adequately capture important features of more fundamental electroencephalography-related sleep disturbance.

OBJECTIVES

This study aimed to determine if more comprehensive power-spectral measures of delta wave activity during sleep are stronger independent predictors of mortality than conventional sleep quality and disturbance metrics.

METHODS

Power spectral analysis of the delta frequency band and spectral entropy-based markers to quantify disruption of electroencephalography delta power during sleep were performed to examine potential associations with mortality risk in the Sleep Heart Health Study cohort (N = 5804). Adjusted Cox proportional hazard models were used to determine the association between disrupted delta wave activity at baseline and all-cause mortality over an ~11y follow-up period.

RESULTS

Disrupted delta electroencephalography power during sleep was associated with a 32% increased risk of all-cause mortality compared with no fragmentation (hazard ratios 1.32 [95% confidence interval 1.14, 1.50], after adjusting for total sleep time and other clinical and life-style related covariates including sleep apnea. The association was of similar magnitude to a reduction in total sleep time from 6.5h to 4.25h. Conventional measures of sleep quality, including wake after sleep onset and arousal index were not predictive of all-cause mortality.

CONCLUSIONS

Delta wave activity disruption during sleep is strongly associated with all-cause mortality risk, independent of traditional potential confounders. Future investigation into the potential role of delta sleep disruption on other specific adverse health consequences such as cardiometabolic, mental health and safety outcomes has considerable potential to provide unique neurophysiological insight.

Polysomnographic Predictors of Treatment Response to Cognitive Behavioral Therapy for Insomnia in Participants With Co-morbid Insomnia and Sleep Apnea: Secondary Analysis of a Randomized Controlled Trial

OBJECTIVE

Co-morbid insomnia and sleep apnea (COMISA) is a common and debilitating condition that is more difficult to treat compared to insomnia or sleep apnea-alone. Emerging evidence suggests that cognitive behavioral therapy for insomnia (CBTi) is effective in patients with COMISA, however, those with more severe sleep apnea and evidence of greater objective sleep disturbance may be less responsive to CBTi. Polysomnographic sleep study data has been used to predict treatment response to CBTi in patients with insomnia-alone, but not in patients with COMISA. We used randomized controlled trial data to investigate polysomnographic predictors of insomnia improvement following CBTi, versus control in participants with COMISA.

METHODS

One hundred and forty five participants with insomnia (ICSD-3) and sleep apnea [apnea-hypopnea index (AHI) ≥ 15] were randomized to CBTi (n = 72) or no-treatment control (n = 73). Mixed models were used to investigate the effect of pre-treatment AHI, sleep duration, and other traditional (AASM sleep macrostructure), and novel [quantitative electroencephalography (qEEG)] polysomnographic predictors of between-group changes in Insomnia Severity Index (ISI) scores from pre-treatment to post-treatment.

RESULTS

Compared to control, CBTi was associated with greater ISI improvement among participants with; higher AHI (interaction p = 0.011), less wake after sleep onset (interaction p = 0.045), and less N3 sleep (interaction p = 0.005). No quantitative electroencephalographic, or other traditional polysomnographic variables predicted between-group ISI change (all p > 0.09).

DISCUSSION

Among participants with COMISA, higher OSA severity predicted a greater treatment-response to CBTi, versus control. People with COMISA should be treated with CBTi, which is effective even in the presence of severe OSA and objective sleep disturbance.

An energy screening and morphology characterization-based hybrid expert scheme for automatic identification of micro-sleep event K-complex

BACKGROUND AND OBJECTIVE

K-complexes, as a significant indicator in sleep staging and sleep protection, are an important micro-event in sleep analysis. Clinically, K-complexes are recognized through the expert visual inspection of electroencephalogram (EEG) during sleep. Since this process is laborious and has high inter-observer variability, developing automated K-complex detection methods can alleviate the burden on clinicians while providing reliable recognition results. However, existing methods face the following issues. First, most work only identifies the K-complexes in stage 2, which requires distinguishing the sleep stages as the prerequisite for further events' identification. Second, most approaches can only detect the occurrence of events without the ability to predict their location and duration, which are also essential to sleep analysis.

METHODS

In this work, a novel hybrid expert scheme for K-complex detection is proposed by integrating signal morphology with expert knowledge into the decision-making process. To eliminate artifacts, and to minimize the individual variability in raw sleep EEG signals, the potential K-complex candidates are first screened by combining Teager energy operator (TEO) and personalized thresholds. Then, to distinguish signal shapes from background activity, a novel frame of filtering based on morphological filtering (MF) is devised to differentiate morphological components of K-complex waveforms from EEG series. Finally, K-complex waveforms are identified from the extracted morphological information by judgment rules, which are inspired by expert knowledge of micro-sleep events.

RESULTS

Detection performance is evaluated by its application on the public database MASS-C1 (Montreal archives of sleep studies cohort one) which includes the recordings of 19 healthy adults. The detection performance demonstrates an F-measure of 0.63 with a recall of 0.81 and a precision of 0.53 on average. The duration error between events and detections is 0.10 s.

CONCLUSIONS

The presented scheme has detected the occurrence of events. Meanwhile, it has recognized their locations and durations. The favorable results exhibit that the proposed scheme outperforms the state-of-the-art studies and has great potential to help release the burden of experts in sleep EEG analysis.

K-complexes are a sensitive marker of noise-related sensory processing during sleep: A pilot study

STUDY OBJECTIVES

The primary aim of this study was to examine dose-response relationships between sound pressure levels (SPLs) and K-complex occurrence probability for wind farm and road traffic noise. A secondary aim was to compare K-complex dose-responses to manually scored EEG arousals and awakenings.

METHODS

Twenty-five participants underwent polysomnography recordings and noise exposure during sleep in a laboratory. Wind farm and road traffic noise recordings of 20-sec duration were played in random order at 6 SPLs between 33 - 48 dBA during established N2 or deeper sleep. Noise periods were separated with periods of 23 dBA background noise. K-complexes were scored using a validated algorithm. K-complex occurrence probability was compared between noise types controlling for noise SPL, subjective noise sensitivity and measured hearing acuity.

RESULTS

Noise-induced K-complexes were observed in N2 sleep at SPLs as low as 33 dBA (Odds ratio, 33dBA vs 23 dBA, mean (95% confidence interval); 1.75 (1.16, 2.66)) and increased with SPL. EEG arousals and awakenings were only associated with noise above 39 dBA in N2 sleep. K-complexes were 2 times more likely to occur in response to noise than EEG arousals or awakenings. Subjective noise sensitivity and hearing acuity were associated with K-complex occurrence, but not arousal or awakening. Noise type did not detectably influence K-complexes, EEG arousals or awakening responses.

CONCLUSION

These findings support that K-complexes are a sensitive marker of sensory processing of environmental noise during sleep and that increased hearing acuity and decreased self-reported noise sensitivity increase K-complex probability.