Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization

Unveil sleep spindles with concentration of frequency and time (ConceFT)

Objective.Sleep spindles contain crucial brain dynamics information. We introduce the novel non-linear time-frequency (TF) analysis tool 'Concentration of Frequency and Time' (ConceFT) to create an interpretable automated algorithm for sleep spindle annotation in EEG data and to measure spindle instantaneous frequencies (IFs).Approach.ConceFT effectively reduces stochastic EEG influence, enhancing spindle visibility in the TF representation. Our automated spindle detection algorithm, ConceFT-Spindle (ConceFT-S), is compared to A7 (non-deep learning) and SUMO (deep learning) using Dream and Montreal Archive of Sleep Studies (MASS) benchmark databases. We also quantify spindle IF dynamics.Main results.ConceFT-S achieves F1 scores of 0.765 in Dream and 0.791 in MASS, which surpass A7 and SUMO. We reveal that spindle IF is generally nonlinear.Significance.ConceFT offers an accurate, interpretable EEG-based sleep spindle detection algorithm and enables spindle IF quantification.

A personalized semi-automatic sleep spindle detection (PSASD) framework

BACKGROUND

Sleep spindles are distinct electroencephalogram (EEG) patterns of brain activity that have been posited to play a critical role in development, learning, and neurological disorders. Manual scoring for sleep spindles is labor-intensive and tedious but could supplement automated algorithms to resolve challenges posed with either approaches alone.

NEW METHODS

A Personalized Semi-Automatic Sleep Spindle Detection (PSASD) framework was developed to combine the strength of automated detection algorithms and visual expertise of human scorers. The underlying model in the PSASD framework assumes a generative model for EEG sleep spindles as oscillatory components, optimized to EEG amplitude, with remaining signals distributed into transient and low-frequency components.

RESULTS

A single graphical user interface (GUI) allows both manual scoring of sleep spindles (model training data) and verification of automatically detected spindles. A grid search approach allows optimization of parameters to balance tradeoffs between precision and recall measures.

COMPARISON WITH EXISTING METHODS

PSASD outperformed DETOKS in F1-score by 19% and 4% on the DREAMS and P-DROWS-E datasets, respectively. It also outperformed YASA in F1-score by 25% in the P-DROWS-E dataset. Further benchmarking analysis showed that PSASD outperformed four additional widely used sleep spindle detectors in F1-score in the P-DROWS-E dataset. Titration analysis revealed that four 30-second epochs are sufficient to fine-tune the model parameters of PSASD. Associations of frequency, duration, and amplitude of detected sleep spindles matched those previously reported with automated approaches.

CONCLUSIONS

Overall, PSASD improves detection of sleep spindles in EEG data acquired from both younger healthy and older adult patient populations.

The stability of slow-wave sleep and EEG oscillations across two consecutive nights of laboratory polysomnography in cognitively normal older adults

Laboratory polysomnography provides gold-standard measures of sleep physiology, but multi-night investigations are resource intensive. We assessed the night-to-night stability via reproducibility metrics for sleep macrostructure and electroencephalography oscillations in a group of cognitively normal adults attending two consecutive polysomnographies. Electroencephalographies were analysed using an automatic algorithm for detection of slow-wave activity, spindle and K-complex densities. Average differences between nights for sleep macrostructure, electroencephalography oscillations and sleep apnea severity were assessed, and test-retest reliability was determined using two-way intraclass correlations. Agreement was calculated using the smallest real differences between nights for all measures. Night 2 polysomnographies showed significantly greater time in bed, total sleep time (6.3 hr versus 6.8 hr, p < 0.001) and percentage of rapid eye movement sleep (17.5 versus 19.7, p < 0.001). Intraclass correlations were low for total sleep time, percentage of rapid eye movement sleep and sleep efficiency, moderate for percentage of slow-wave sleep and percentage of non-rapid eye movement 2 sleep, good for slow-wave activity and K-complex densities, and excellent for spindles and apnea-hypopnea index with hypopneas defined according to 4% oxygen desaturation criteria only. The smallest real difference values were proportionally high for most sleep macrostructure measures, indicating moderate agreement, and proportionally lower for most electroencephalography microstructure variables. Slow waves, K-complexes, spindles and apnea severity indices are highly reproducible across two consecutive nights of polysomnography. In contrast, sleep macrostructure measures all demonstrated poor reproducibility as indicated by low intraclass correlation values and moderate agreement. Although there were average differences in percentage of rapid eye movement sleep and total sleep time, these were numerically small and perhaps functionally or clinically less significant. One night of in-laboratory polysomnography is enough to provide stable, reproducible estimates of an individual's sleep concerning measures of slow-wave activity, spindles, K-complex densities and apnea severity.

An examination of sleep spindle metrics in the Sleep Heart Health Study: superiority of automated spindle detection over total sigma power in assessing age-related spindle decline

BACKGROUND

Sleep spindle activity is commonly estimated by measuring sigma power during stage 2 non-rapid eye movement (NREM2) sleep. However, spindles account for little of the total NREM2 interval and therefore sigma power over the entire interval may be misleading. This study compares derived spindle measures from direct automated spindle detection with those from gross power spectral analyses for the purposes of clinical trial design.

METHODS

We estimated spindle activity in a set of 8,440 overnight electroencephalogram (EEG) recordings from 5,793 patients from the Sleep Heart Health Study using both sigma power and direct automated spindle detection. Performance of the two methods was evaluated by determining the sample size required to detect decline in age-related spindle coherence with each method in a simulated clinical trial.

RESULTS

In a simulated clinical trial, sigma power required a sample size of 115 to achieve 95% power to identify age-related changes in sigma coherence, while automated spindle detection required a sample size of only 60.

CONCLUSIONS

Measurements of spindle activity utilizing automated spindle detection outperformed conventional sigma power analysis by a wide margin, suggesting that many studies would benefit from incorporation of automated spindle detection. These results further suggest that some previous studies which have failed to detect changes in sigma power or coherence may have failed simply because they were underpowered.

Sleep electroencephalography biomarkers of cognition in obstructive sleep apnea

Obstructive sleep apnea has been associated with cognitive impairment and may be linked to disorders of cognitive function. These associations may be a result of intermittent hypoxaemia, sleep fragmentation and changes in sleep microstructure in obstructive sleep apnea. Current clinical metrics of obstructive sleep apnea, such as the apnea-hypopnea index, are poor predictors of cognitive outcomes in obstructive sleep apnea. Sleep microstructure features, which can be identified on sleep electroencephalography of traditional overnight polysomnography, are increasingly being characterized in obstructive sleep apnea and may better predict cognitive outcomes. Here, we summarize the literature on several major sleep electroencephalography features (slow-wave activity, sleep spindles, K-complexes, cyclic alternating patterns, rapid eye movement sleep quantitative electroencephalography, odds ratio product) identified in obstructive sleep apnea. We will review the associations between these sleep electroencephalography features and cognition in obstructive sleep apnea, and examine how treatment of obstructive sleep apnea affects these associations. Lastly, evolving technologies in sleep electroencephalography analyses will also be discussed (e.g. high-density electroencephalography, machine learning) as potential predictors of cognitive function in obstructive sleep apnea.

A study on feature selection using multi-domain feature extraction for automated k-complex detection

Background

K-complex detection plays a significant role in the field of sleep research. However, manual annotation for electroencephalography (EEG) recordings by visual inspection from experts is time-consuming and subjective. Therefore, there is a necessity to implement automatic detection methods based on classical machine learning algorithms. However, due to the complexity of EEG signal, current feature extraction methods always produce low relevance to k-complex detection, which leads to a great performance loss for the detection. Hence, finding compact yet effective integrated feature vectors becomes a crucially core task in k-complex detection.

Method

In this paper, we first extract multi-domain features based on time, spectral analysis, and chaotic theory. Those features are extracted from a 0.5-s EEG segment, which is obtained using the sliding window technique. As a result, a vector containing twenty-two features is obtained to represent each segment. Next, we explore several feature selection methods and compare their performance in detecting k-complex. Based on the analysis of the selected features, we identify compact features which are fewer than twenty-two features and deemed as relevant and proceeded to the next step. Additionally, three classical classifiers are employed to evaluate the performance of the feature selection models.

Results

The results demonstrate that combining different features significantly improved the k-complex detection performance. The best performance is achieved by applying the feature selection method, which results in an accuracy of 93.03%± 7.34, sensitivity of 93.81%± 5.62%, and specificity 94.13± 5.81, respectively, using a smaller number of the combined feature sets.

Conclusion

The proposed method in this study can serve as an efficient tool for the automatic detection of k-complex, which is useful for neurologists or doctors in the diagnosis of sleep research.

A RUSBoosted tree method for k-complex detection using tunable Q-factor wavelet transform and multi-domain feature extraction

Background

K-complex detection traditionally relied on expert clinicians, which is time-consuming and onerous. Various automatic k-complex detection-based machine learning methods are presented. However, these methods always suffered from imbalanced datasets, which impede the subsequent processing steps.

New method

In this study, an efficient method for k-complex detection using electroencephalogram (EEG)-based multi-domain features extraction and selection method coupled with a RUSBoosted tree model is presented. EEG signals are first decomposed using a tunable Q-factor wavelet transform (TQWT). Then, multi-domain features based on TQWT are pulled out from TQWT sub-bands, and a self-adaptive feature set is obtained from a feature selection based on the consistency-based filter for the detection of k-complexes. Finally, the RUSBoosted tree model is used to perform k-complex detection.

Results

Experimental outcomes manifest the efficacy of our proposed scheme in terms of the average performance of recall measure, AUC, and F10-score. The proposed method yields 92.41 ± 7.47%, 95.4 ± 4.32%, and 83.13 ± 8.59% for k-complex detection in Scenario 1 and also achieves similar results in Scenario 2.

Comparison to state-of-the-art methods

The RUSBoosted tree model was compared with three other machine learning classifiers [i.e., linear discriminant analysis (LDA), logistic regression, and linear support vector machine (SVM)]. The performance based on the kappa coefficient, recall measure, and F10-score provided evidence that the proposed model surpassed other algorithms in the detection of the k-complexes, especially for the recall measure.

Conclusion

In summary, the RUSBoosted tree model presents a promising performance in dealing with highly imbalanced data. It can be an effective tool for doctors and neurologists to diagnose and treat sleep disorders.

Automated real-time EEG sleep spindle detection for brain-state-dependent brain stimulation

Sleep spindles are a hallmark electroencephalographic feature of non-rapid eye movement sleep, and are believed to be instrumental for sleep-dependent memory reactivation and consolidation. However, direct proof of their causal relevance is hard to obtain, and our understanding of their immediate neurophysiological consequences is limited. To investigate their causal role, spindles need to be targeted in real-time with sensory or non-invasive brain-stimulation techniques. While fully automated offline detection algorithms are well established, spindle detection in real-time is highly challenging due to their spontaneous and transient nature. Here, we present the real-time spindle detector, a robust multi-channel electroencephalographic signal-processing algorithm that enables the automated triggering of stimulation during sleep spindles in a phase-specific manner. We validated the real-time spindle detection method by streaming pre-recorded sleep electroencephalographic datasets to a real-time computer system running a Simulink® Real-Time™ implementation of the algorithm. Sleep spindles were detected with high levels of Sensitivity (~83%), Precision (~78%) and a convincing F1-Score (~81%) in reference to state-of-the-art offline algorithms (which reached similar or lower levels when compared with each other), for both naps and full nights, and largely independent of sleep scoring information. Detected spindles were comparable in frequency, duration, amplitude and symmetry, and showed the typical time-frequency characteristics as well as a centroparietal topography. Spindles were detected close to their centre and reliably at the predefined target phase. The real-time spindle detection algorithm therefore empowers researchers to target spindles during human sleep, and apply the stimulation method and experimental paradigm of their choice.

The Portiloop: A deep learning-based open science tool for closed-loop brain stimulation

Closed-loop brain stimulation refers to capturing neurophysiological measures such as electroencephalography (EEG), quickly identifying neural events of interest, and producing auditory, magnetic or electrical stimulation so as to interact with brain processes precisely. It is a promising new method for fundamental neuroscience and perhaps for clinical applications such as restoring degraded memory function; however, existing tools are expensive, cumbersome, and offer limited experimental flexibility. In this article, we propose the Portiloop, a deep learning-based, portable and low-cost closed-loop stimulation system able to target specific brain oscillations. We first document open-hardware implementations that can be constructed from commercially available components. We also provide a fast, lightweight neural network model and an exploration algorithm that automatically optimizes the model hyperparameters to the desired brain oscillation. Finally, we validate the technology on a challenging test case of real-time sleep spindle detection, with results comparable to off-line expert performance on the Massive Online Data Annotation spindle dataset (MODA; group consensus). Software and plans are available to the community as an open science initiative to encourage further development and advance closed-loop neuroscience research [https://github.com/Portiloop].

[Sleep spindles-Function, detection and use as biomarker for diagnostics in psychiatry]

BACKGROUND

The sleep spindle is a graphoelement of an electroencephalogram (EEG), which can be observed in light and deep sleep. Alterations in spindle activity have been described for a range of psychiatric disorders. Due to their relatively constant properties, sleep spindles may therefore be potential biomarkers in psychiatric diagnostics.

METHOD

This article presents an overview of the state of the science on the characteristics and functions of the sleep spindle as well as known alterations of spindle activity in psychiatric disorders. Various methodological approaches and developments of spindle detection are explained with respect to their potential for application in psychiatric diagnostics.

RESULTS AND CONCLUSION

Although alterations in spindle activity in psychiatric disorders are known and have been described in detail, their exact potential for psychiatric diagnostics has yet to be fully determined. In this respect, the acquisition of knowledge in research is currently constrained by manual and automated methods for spindle detection, which require high levels of resources and are error prone. Newer approaches to spindle detection based on deep-learning procedures could overcome the difficulties of previous detection methods, and thus open up new possibilities for the practical application of sleep spindles as biomarkers in the psychiatric practice.

Advanced sleep spindle identification with neural networks

Sleep spindles are neurophysiological phenomena that appear to be linked to memory formation and other functions of the central nervous system, and that can be observed in electroencephalographic recordings (EEG) during sleep. Manually identified spindle annotations in EEG recordings suffer from substantial intra- and inter-rater variability, even if raters have been highly trained, which reduces the reliability of spindle measures as a research and diagnostic tool. The Massive Online Data Annotation (MODA) project has recently addressed this problem by forming a consensus from multiple such rating experts, thus providing a corpus of spindle annotations of enhanced quality. Based on this dataset, we present a U-Net-type deep neural network model to automatically detect sleep spindles. Our model’s performance exceeds that of the state-of-the-art detector and of most experts in the MODA dataset. We observed improved detection accuracy in subjects of all ages, including older individuals whose spindles are particularly challenging to detect reliably. Our results underline the potential of automated methods to do repetitive cumbersome tasks with super-human performance.

A Clinical Decision Support System for Sleep Staging Tasks With Explanations From Artificial Intelligence: User-Centered Design and Evaluation Study

Background

Despite the unprecedented performance of deep learning algorithms in clinical domains, full reviews of algorithmic predictions by human experts remain mandatory. Under these circumstances, artificial intelligence (AI) models are primarily designed as clinical decision support systems (CDSSs). However, from the perspective of clinical practitioners, the lack of clinical interpretability and user-centered interfaces hinders the adoption of these AI systems in practice.

Objective

This study aims to develop an AI-based CDSS for assisting polysomnographic technicians in reviewing AI-predicted sleep staging results. This study proposed and evaluated a CDSS that provides clinically sound explanations for AI predictions in a user-centered manner.

Methods

Our study is based on a user-centered design framework for developing explanations in a CDSS that identifies why explanations are needed, what information should be contained in explanations, and how explanations can be provided in the CDSS. We conducted user interviews, user observation sessions, and an iterative design process to identify three key aspects for designing explanations in the CDSS. After constructing the CDSS, the tool was evaluated to investigate how the CDSS explanations helped technicians. We measured the accuracy of sleep staging and interrater reliability with macro-F1 and Cohen κ scores to assess quantitative improvements after our tool was adopted. We assessed qualitative improvements through participant interviews that established how participants perceived and used the tool.

Results

The user study revealed that technicians desire explanations that are relevant to key electroencephalogram (EEG) patterns for sleep staging when assessing the correctness of AI predictions. Here, technicians wanted explanations that could be used to evaluate whether the AI models properly locate and use these patterns during prediction. On the basis of this, information that is closely related to sleep EEG patterns was formulated for the AI models. In the iterative design phase, we developed a different visualization strategy for each pattern based on how technicians interpreted the EEG recordings with these patterns during their workflows. Our evaluation study on 9 polysomnographic technicians quantitatively and qualitatively investigated the helpfulness of the tool. For technicians with <5 years of work experience, their quantitative sleep staging performance improved significantly from 56.75 to 60.59 with a P value of .05. Qualitatively, participants reported that the information provided effectively supported them, and they could develop notable adoption strategies for the tool.

Conclusions

Our findings indicate that formulating clinical explanations for automated predictions using the information in the AI with a user-centered design process is an effective strategy for developing a CDSS for sleep staging.

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.

SpindleU-Net: An Adaptive U-Net Framework for Sleep Spindle Detection in Single-Channel EEG

The sleep spindles in EEG have become one type of biomarker used to assess cognitive abilities and related disorders, and thus their detection is crucial for clinical research. This task, traditionally performed by sleep experts, is time-consuming. Many methods have been proposed to automate this process, yet an increase in performance is still expected. Inspired by the application in image segmentation, we propose a point-wise spindle detection method based on the U-Net framework with an attention module (SpindleU-Net). It maps the sequences of arbitrary-length EEG inputs to those of dense labels of spindle or non-spindle on freely chosen intervals. The attention module that focuses on the salient spindle region allows better performance, and a task-specific loss function is defined to alleviate the problem of imbalanced classification. As a deep learning method, SpindleU-Net outperforms state-of-the-art methods on the widely used benchmark dataset of MASS as well as the DREAMS dataset with a small number of samples. On MASS dataset it achieves average F1 scores of 0.854 and 0.803 according to its consistency with the annotations by two sleep experts respectively. On DREAMS dataset, it shows the average F1 score of 0.739. Its cross-dataset performance is also better compared to other methods, showing the good generalization ability for cross-dataset applications.

Altered K-complex morphology during sustained inspiratory airflow limitation is associated with next-day lapses in vigilance in obstructive sleep apnea

STUDY OBJECTIVES

Determine if changes in K-complexes associated with sustained inspiratory airflow limitation (SIFL) during N2 sleep are associated with next-day vigilance and objective sleepiness.

METHODS

Data from thirty subjects with moderate-to-severe obstructive sleep apnea who completed three in-lab polysomnograms: diagnostic, on therapeutic continuous positive airway pressure (CPAP), and on suboptimal CPAP (4 cmH2O below optimal titrated CPAP level) were analyzed. Four 20-min psychomotor vigilance tests (PVT) were performed after each PSG, every 2 h. Changes in the proportion of spontaneous K-complexes and spectral characteristics surrounding K-complexes were evaluated for K-complexes associated with both delta (∆SWAK), alpha (∆αK) frequencies.

RESULTS

Suboptimal CPAP induced SIFL (14.7 (20.9) vs 2.9 (9.2); %total sleep time, p < 0.001) with a small increase in apnea-hypopnea index (AHI3A: 6.5 (7.7) vs 1.9 (2.3); p < 0.01) versus optimal CPAP. K-complex density (num./min of stage N2) was higher on suboptimal CPAP (0.97 ± 0.7 vs 0.65±0.5, #/min, mean ± SD, p < 0.01) above and beyond the effect of age, sex, AHI3A, and duration of SIFL. A decrease in ∆SWAK with suboptimal CPAP was associated with increased PVT lapses and explained 17% of additional variance in PVT lapses. Within-night during suboptimal CPAP K-complexes appeared to alternate between promoting sleep and as arousal surrogates. Electroencephalographic changes were not associated with objective sleepiness.

CONCLUSIONS

Sustained inspiratory airflow limitation is associated with altered K-complex morphology including the increased occurrence of K-complexes with bursts of alpha as arousal surrogates. These findings suggest that sustained inspiratory flow limitation may be associated with nonvisible sleep fragmentation and contribute to increased lapses in vigilance.

Detection of k-complexes in EEG signals using a multi-domain feature extraction coupled with a least square support vector machine classifier

Sleep scoring is one of the primary tasks for the classification of sleep stages using electroencephalogram (EEG) signals. It is one of the most important diagnostic methods in sleep research and must be carried out with a high degree of accuracy because any errors in the scoring in the patient's sleep EEG recordings can cause serious problems. The aim of this research is to develop a new automatic method for detecting the most important characteristics in sleep stage 2 such as k-complexes based on multi-domain features. In this study, each EEG signal is divided into a set of segments using a sliding window technique. Based on extensive experiments during the training phase, the size of the sliding window is set to 0.5 s (s). Then a set of statistical, fractal, frequency and non-linear features are extracted from each epoch based on the time domain, Katz's algorithm, power spectrum density (PSD) and tunable Q-factor wavelet transform (TQWT). As a result, a vector of twenty-two features is obtained to represent each EEG segment. In order to detect k-complexes, the extracted features were analysed for their ability to detect the k-complex waveforms. Based on the analysis of the features, twelve out of twenty-two features are selected and forwarded to a least square support vector machine (LS-SVM) classifier to identify k-complexes in EEG signals. A set of various classification techniques of K-means and extreme learning machine classifiers are used to compare the obtained results and to evaluate the performance of the proposed method.The experimental results showed that the proposed method, based on multi-domain features, achieved better recognition results than other methods and classifiers. An average accuracy, sensitivity and specificity of 97.7 %, 97 %, and 94.2 % were obtained, respectively, with the CZ-A1 channel according to the R&K standard. The experimental results with high classification performance demonstrated that the technique can help doctors optimize the diagnosis and treatment of sleep disorders.

Effects of obstructive sleep apnea on human spatial navigational memory processing in cognitively normal older individuals

STUDY OBJECTIVES

Obstructive sleep apnea (OSA) prevalence increases with age, but whether OSA-related sleep disruption could interrupt the processing of previously encoded wake information thought to normally occur during sleep in cognitively normal older adults remains unknown.

METHODS

Fifty-two older (age = 66.9 ± 7.7 years, 56% female), community-dwelling, cognitively normal adults explored a 3-D maze environment and then performed 3 timed trials before (evening) and after (morning) sleep recorded with polysomnography with a 20-minute morning psychomotor vigilance test.

RESULTS

Twenty-two (22) participants had untreated OSA [apnea-hypopnea index (AHI4%) ≥ 5 events/h] where severity was mild on average [median (interquartile range); AHI4% = 11.0 (20.7) events/h] and 30 participants had an AHI4% < 5 events/h. No significant differences were observed in overnight percent change in completion time or in the pattern of evening presleep maze performance. However, during the morning postsleep trials, there was a significant interaction between OSA group and morning trial number such that participants with OSA performed worse on average with each subsequent morning trial, whereas those without OSA showed improvements. There were no significant differences in morning psychomotor vigilance test performance, suggesting that vigilance is unlikely to account for this difference in morning maze performance. Increasing relative frontal slow wave activity was associated with better overnight maze performance improvement in participants with OSA (r = .51, P = .02) but not in those without OSA, and no differences in slow wave activity were observed between groups.

CONCLUSIONS

OSA alters morning performance in spatial navigation independent of a deleterious effect on morning vigilance or evening navigation performance. Relative frontal slow wave activity is associated with overnight performance change in older participants with OSA, but not those without.

Spindles are highly heritable as identified by different spindle detectors

STUDY OBJECTIVES

Sleep spindles, a defining feature of stage N2 sleep, are maximal at central electrodes and are found in the frequency range of the electroencephalogram (EEG) (sigma 11-16 Hz) that is known to be heritable. However, relatively little is known about the heritability of spindles. Two recent studies investigating the heritability of spindles reported moderate heritability, but with conflicting results depending on scalp location and spindle type. The present study aimed to definitively assess the heritability of sleep spindle characteristics.

METHODS

We utilized the polysomnography data of 58 monozygotic and 40 dizygotic same-sex twin pairs to identify heritable characteristics of spindles at C3/C4 in stage N2 sleep including density, duration, peak-to-peak amplitude, and oscillation frequency. We implemented and tested a variety of spindle detection algorithms and used two complementary methods of estimating trait heritability.

RESULTS

We found robust evidence to support strong heritability of spindles regardless of detector method (h2 > 0.8). However not all spindle characteristics were equally heritable, and each spindle detection method produced a different pattern of results.

CONCLUSIONS

The sleep spindle in stage N2 sleep is highly heritable, but the heritability differs for individual spindle characteristics and depends on the spindle detector used for analysis.

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.

A robust two-stage sleep spindle detection approach using single-channel EEG

Objective.Sleep spindles in the electroencephalogram (EEG) are significant in sleep analysis related to cognitive functions and neurological diseases, and thus are of great clinical interests. An automatic sleep spindle detection algorithm could help decrease the workload of visual inspection by sleep clinicians.Approach.We propose a robust two-stage approach for sleep spindle detection using single-channel EEG. In the pre-detection stage, a stable number of sleep spindle candidates are discovered using the Teager energy operator with adaptive parameters, where the number of true sleep spindles are ensured as many as possible to maximize the detection sensitivity. In the refinement stage, representative features are designed and a bagging classifier is exploited to further recognize the true spindles from all candidates, in order to remove the false detection in the first stage.Main results.Using the union of all experts' annotations as the ground truth, its performance outperforms state-of-the-art works in terms of F1-score (F1) on two public databases (F1: 0.814 for Montreal archive of sleep studies dataset and 0.690 for DREAMS dataset). The annotation consistency between the proposed method and certain selected expert as the trainer could exceed the consistency between two human experts.Significance.The proposed sleep spindle detection method is based on single-channel EEG thus introduces as less interference to the subjects as possible. It is robust to subject variations between databases and is capable of learning certain annotation rules, which is expected to help facilitate the manual labeling of certain experts. In addition, this method is fast enough for real-time applications.

Protocol for the Prognosticating Delirium Recovery Outcomes Using Wakefulness and Sleep Electroencephalography (P-DROWS-E) study: a prospective observational study of delirium in elderly cardiac surgical patients

INTRODUCTION

Delirium is a potentially preventable disorder characterised by acute disturbances in attention and cognition with fluctuating severity. Postoperative delirium is associated with prolonged intensive care unit and hospital stay, cognitive decline and mortality. The development of biomarkers for tracking delirium could potentially aid in the early detection, mitigation and assessment of response to interventions. Because sleep disruption has been posited as a contributor to the development of this syndrome, expression of abnormal electroencephalography (EEG) patterns during sleep and wakefulness may be informative. Here we hypothesise that abnormal EEG patterns of sleep and wakefulness may serve as predictive and diagnostic markers for postoperative delirium. Such abnormal EEG patterns would mechanistically link disrupted thalamocortical connectivity to this important clinical syndrome.

METHODS AND ANALYSIS

P-DROWS-E (Prognosticating Delirium Recovery Outcomes Using Wakefulness and Sleep Electroencephalography) is a 220-patient prospective observational study. Patient eligibility criteria include those who are English-speaking, age 60 years or older and undergoing elective cardiac surgery requiring cardiopulmonary bypass. EEG acquisition will occur 1-2 nights preoperatively, intraoperatively, and up to 7 days postoperatively. Concurrent with EEG recordings, two times per day postoperative Confusion Assessment Method (CAM) evaluations will quantify the presence and severity of delirium. EEG slow wave activity, sleep spindle density and peak frequency of the posterior dominant rhythm will be quantified. Linear mixed-effects models will be used to evaluate the relationships between delirium severity/duration and EEG measures as a function of time.

ETHICS AND DISSEMINATION

P-DROWS-E is approved by the ethics board at Washington University in St. Louis. Recruitment began in October 2018. Dissemination plans include presentations at scientific conferences, scientific publications and mass media.

TRIAL REGISTRATION NUMBER

NCT03291626.

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

STUDY OBJECTIVES

K-complexes (KCs) are a recognized electroencephalography marker of sensory processing and a defining feature of sleep stage 2. KC frequency and morphology may also be reflective of sleep quality, aging, and a range of sleep and sensory processing deficits. However, manual scoring of K-complexes is impractical, time-consuming, and thus costly and currently not well-standardized. Although automated KC detection methods have been developed, performance and uptake remain limited.

METHODS

The proposed algorithm is based on a deep neural network and Gaussian process, which gives the input waveform a probability of being a KC ranging from 0% to 100%. The algorithm was trained on half a million synthetic KCs derived from manually scored sleep stage 2 KCs from the Montreal Archive of Sleep Study containing 19 healthy young participants. Algorithm performance was subsequently assessed on 700 independent recordings from the Cleveland Family Study using sleep stages 2 and 3 data.

RESULTS

The developed algorithm showed an F1 score (a measure of binary classification accuracy) of 0.78 and thus outperforms currently available KC scoring algorithms with F1 = 0.2-0.6. The probabilistic approach also captured expected variability in KC shape and amplitude within individuals and across age groups.

CONCLUSIONS

An automated probabilistic KC classification is well suited and effective for systematic KC detection for a more in-depth exploration of potential relationships between KCs during sleep and clinical outcomes such as health impacts and daytime symptomatology.

Sleep spindle abnormalities related to Alzheimer's disease: a systematic mini-review

Accumulating evidence supports a bidirectional relationship between sleep disruption and Alzheimer's disease (AD) pathology. Among various sleep electroencephalography activities, the sleep spindle is one specific electroencephalographic rhythm that has potential to be a biomarker for AD. This review explores the association between sleep spindles and AD-related dementia from a neuropsychological perspective by a systematic re-examining of recent findings. In general, sleep spindles, characterized by density, amplitude, duration, and frequency, are disrupted in AD. Moreover, its functional coupling with slow oscillation also suffers in AD. While preliminary, our observations and comparisons suggest that spindle density rather than frequency and fast spindles rather than slow spindles could be more sensitive to AD-related dementia, and spindle plasticity provides possibilities for targeted interference. In conclusion, quantitative and qualitative features of sleep spindles represent potential non-invasive and cost-effective biomarkers for AD and provide both therapeutic and public health implications.

Massive online data annotation, crowdsourcing to generate high quality sleep spindle annotations from EEG data

Spindle event detection is a key component in analyzing human sleep. However, detection of these oscillatory patterns by experts is time consuming and costly. Automated detection algorithms are cost efficient and reproducible but require robust datasets to be trained and validated. Using the MODA (Massive Online Data Annotation) platform, we used crowdsourcing to produce a large open-source dataset of high quality, human-scored sleep spindles (5342 spindles, from 180 subjects). We evaluated the performance of three subtype scorers: “experts, researchers and non-experts”, as well as 7 previously published spindle detection algorithms. Our findings show that only two algorithms had performance scores similar to human experts. Furthermore, the human scorers agreed on the average spindle characteristics (density, duration and amplitude), but there were significant age and sex differences (also observed in the set of detected spindles). This study demonstrates how the MODA platform can be used to generate a highly valid open source standardized dataset for researchers to train, validate and compare automated detectors of biological signals such as the EEG.

K-complexes Detection in EEG Signals using Fractal and Frequency Features Coupled with an Ensemble Classification Model

K-complexes are important transient bio-signal waveforms in sleep stage 2. Detecting k-complexes visually requires a highly qualified expert. In this study, an efficient method for detecting k-complexes from electroencephalogram (EEG) signals based on fractal and frequency features coupled with an ensemble model of three classifiers is presented. EEG signals are first partitioned into segments, using a sliding window technique. Then, each EEG segment is decomposed using a dual-tree complex wavelet transform (DT-CWT) to a set of real and imaginary parts. A total of 10 sub-bands are used based on four levels of decomposition, and the high sub-bands are considered in this research for feature extraction. Fractal and frequency features based on DT-CWT and Higuchi's algorithm are pulled out from each sub-band and then forwarded to an ensemble classifier to detect k-complexes. A twelve-feature set is finally used to detect the sleep EEG characteristics using the ensemble model. The ensemble model is designed using a combination of three classification techniques including a least square support vector machine (LS-SVM), k-means and Naïve Bayes. The proposed method for the detection of the k-complexes achieves an average accuracy rate of 97.3 %. The results from the ensemble classifier were compared with those by individual classifiers. Comparisons were also made with existing k-complexes detection approaches for which the same datasets were used. The results demonstrate that the proposed approach is efficient in identifying the k-complexes in EEG signals; it yields optimal results with a window size 0.5 s. It can be an effective tool for sleep stages classification and can be useful for doctors and neurologists for diagnosing sleep disorders.

Detection of EEG K-Complexes Using Fractal Dimension of Time Frequency Images Technique Coupled With Undirected Graph Features

K-complexes identification is a challenging task in sleep research. The detection of k-complexes in electroencephalogram (EEG) signals based on visual inspection is time consuming, prone to errors, and requires well-trained knowledge. Many existing methods for k-complexes detection rely mainly on analyzing EEG signals in time and frequency domains. In this study, an efficient method is proposed to detect k-complexes from EEG signals based on fractal dimension (FD) of time frequency (T-F) images coupled with undirected graph features. Firstly, an EEG signal is partitioned into smaller segments using a sliding window technique. Each EEG segment is passed through a spectrogram of short time Fourier transform (STFT) to obtain the T-F images. Secondly, the box counting method is applied to each T-F image to discover the FDs in EEG signals. A vector of FD features are extracted from each T-F image and then mapped into an undirected graph. The structural properties of the graphs are used as the representative features of the original EEG signals for the input of a least square support vector machine (LS-SVM) classifier. Key graphic features are extracted from the undirected graphs. The extracted graph features are forwarded to the LS-SVM for classification. To investigate the classification ability of the proposed feature extraction combined with the LS-SVM classifier, the extracted features are also forwarded to a k-means classifier for comparison. The proposed method is compared with several existing k-complexes detection methods in which the same datasets were used. The findings of this study shows that the proposed method yields better classification results than other existing methods in the literature. An average accuracy of 97% for the detection of the k-complexes is obtained using the proposed method. The proposed method could lead to an efficient tool for the scoring of automatic sleep stages which could be useful for doctors and neurologists in the diagnosis and treatment of sleep disorders and for sleep research.

A deep learning approach for real-time detection of sleep spindles

OBJECTIVE

Sleep spindles have been implicated in memory consolidation and synaptic plasticity during NREM sleep. Detection accuracy and latency in automatic spindle detection are critical for real-time applications.

APPROACH

Here we propose a novel deep learning strategy (SpindleNet) to detect sleep spindles based on a single EEG channel. While the majority of spindle detection methods are used for off-line applications, our method is well suited for online applications.

MAIN RESULTS

Compared with other spindle detection methods, SpindleNet achieves superior detection accuracy and speed, as demonstrated in two publicly available expert-validated EEG sleep spindle datasets. Our real-time detection of spindle onset achieves detection latencies of 150-350 ms (~two-three spindle cycles) and retains excellent performance under low EEG sampling frequencies and low signal-to-noise ratios. SpindleNet has good generalization across different sleep datasets from various subject groups of different ages and species.

SIGNIFICANCE

SpindleNet is ultra-fast and scalable to multichannel EEG recordings, with an accuracy level comparable to human experts, making it appealing for long-term sleep monitoring and closed-loop neuroscience experiments.

DOSED: A deep learning approach to detect multiple sleep micro-events in EEG signal

BACKGROUND

Electroencephalography (EEG) monitors brain activity during sleep and is used to identify sleep disorders. In sleep medicine, clinicians interpret raw EEG signals in so-called sleep stages, which are assigned by experts to every 30s window of signal. For diagnosis, they also rely on shorter prototypical micro-architecture events which exhibit variable durations and shapes, such as spindles, K-complexes or arousals. Annotating such events is traditionally performed by a trained sleep expert, making the process time consuming, tedious and subject to inter-scorer variability. To automate this procedure, various methods have been developed, yet these are event-specific and rely on the extraction of hand-crafted features.

NEW METHOD

We propose a novel deep learning architecture called Dreem One Shot Event Detector (DOSED). DOSED jointly predicts locations, durations and types of events in EEG time series. The proposed approach, applied here on sleep related micro-architecture events, is inspired by object detectors developed for computer vision such as YOLO and SSD. It relies on a convolutional neural network that builds a feature representation from raw EEG signals, as well as two modules performing localization and classification respectively.

RESULTS AND COMPARISON WITH OTHER METHODS

The proposed approach is tested on 4 datasets and 3 types of events (spindles, K-complexes, arousals) and compared to the current state-of-the-art detection algorithms.

CONCLUSIONS

Results demonstrate the versatility of this new approach and improved performance compared to the current state-of-the-art detection methods.

Slow-wave activity surrounding stage N2 K-complexes and daytime function measured by psychomotor vigilance test in obstructive sleep apnea

STUDY OBJECTIVE

To better understand the inter-individual differences in neurobehavioral impairment in obstructive sleep apnea (OSA) and its treatment with continuous positive airway pressure (CPAP), we examined how changes in sleep electroencephalography (EEG) slow waves were associated with next-day psychomotor vigilance test (PVT) performance.

METHODS

Data from 28 OSA subjects (Apnea-Hypopnea Index with 3% desaturation and/or with an associated arousal [AHI3A] > 15/hour; AHI3A = sum of all apneas and hypopneas with 3% O2 desaturation and/or an EEG arousal, divided by total sleep time [TST]), who underwent three full in-lab nocturnal polysomnographies (NPSGs: chronic OSA, CPAP-treated OSA, and acute OSA), and 19 healthy sleepers were assessed. Four 20-minute PVTs were performed after each NPSG along with subjective and objective assessment of sleepiness. Three EEG metrics were calculated: K-complex (KC) Density (#/minute of N2 sleep), change in slow-wave activity in 1-second envelopes surrounding KCs (ΔSWAK), and relative frontal slow-wave activity during non-rapid eye movement (NREM) (%SWA).

RESULTS

CPAP treatment of OSA resulted in a decrease in KC Density (chronic: 3.9 ± 2.2 vs. treated: 2.7 ± 1.1; p < 0.01; mean ± SD) and an increase in ΔSWAK (chronic: 2.6 ± 2.3 vs. treated: 4.1 ± 2.4; p < 0.01) and %SWA (chronic: 20.9 ± 8.8 vs. treated: 26.6 ± 8.6; p < 0.001). Cross-sectionally, lower ΔSWAK values were associated with higher PVT Lapses (chronic: rho = -0.55, p < 0.01; acute: rho = -0.46, p = 0.03). Longitudinally, improvement in PVT Lapses with CPAP was associated with an increase in ΔSWAK (chronic to treated: rho = -0.48, p = 0.02; acute to treated: rho = -0.5, p = 0.03). In contrast, OSA severity or global sleep quality metrics such as arousal index, NREM, REM, or TST were inconsistently associated with PVT Lapses.

CONCLUSION

Changes in EEG slow waves, in particular ∆SWAK, explain inter-individual differences in PVT performance better than conventional NPSG metrics, suggesting that ΔSWAK is a night-time correlate of next-day vigilance in OSA.

Sleep oscillation-specific associations with Alzheimer's disease CSF biomarkers: novel roles for sleep spindles and tau

BACKGROUND

Based on associations between sleep spindles, cognition, and sleep-dependent memory processing, here we evaluated potential relationships between levels of CSF Aβ42, P-tau, and T-tau with sleep spindle density and other biophysical properties of sleep spindles in a sample of cognitively normal elderly individuals.

METHODS

One-night in-lab nocturnal polysomnography (NPSG) and morning to early afternoon CSF collection were performed to measure CSF Aβ42, P-tau and T-tau. Seven days of actigraphy were collected to assess habitual total sleep time.

RESULTS

Spindle density during NREM stage 2 (N2) sleep was negatively correlated with CSF Aβ42, P-tau and T-tau. From the three, CSF T-tau was the most significantly associated with spindle density, after adjusting for age, sex and ApoE4. Spindle duration, count and fast spindle density were also negatively correlated with T-tau levels. Sleep duration and other measures of sleep quality were not correlated with spindle characteristics and did not modify the associations between sleep spindle characteristics and the CSF biomarkers of AD.

CONCLUSIONS

Reduced spindles during N2 sleep may represent an early dysfunction related to tau, possibly reflecting axonal damage or altered neuronal tau secretion, rendering it a potentially novel biomarker for early neuronal dysfunction. Given their putative role in memory consolidation and neuroplasticity, sleep spindles may represent a mechanism by which tau impairs memory consolidation, as well as a possible target for therapeutic interventions in cognitive decline.

Spindler: a framework for parametric analysis and detection of spindles in EEG with application to sleep spindles

OBJECTIVE

EEG spindles, narrow-band oscillatory signal bursts, are widely-studied biomarkers of subject state and neurological function. Most existing methods for spindle detection select algorithm parameters by optimizing agreement with expert labels. We propose a new framework for selecting algorithm parameters based on stability of spindle properties and elucidate the dependence of these properties on parameter selection for several algorithms.

APPROACH

To demonstrate this approach we developed a new algorithm (Spindler) that decomposes the signal using matching pursuit with Gabor atoms and computes the spindles for each point in a fine grid of parameter values. After computing characteristic surfaces as a function of parameters, Spindler selects algorithm parameters based on the stability of characteristic surface geometry.

MAIN RESULTS

Spindler performs well relative to several common supervised and unsupervised EEG sleep spindle detection methods. Spindler is available as an open-source MATLAB toolbox (https://github.com/VisLab/EEG-Spindles). In addition to Spindler, the toolbox provides implementations of several other spindle detection algorithms as well as standardized methods for matching ground truth to predictions and a framework for understanding algorithm parameter surfaces.

SIGNIFICANCE

This work demonstrates that parameter selection based on physical constraints rather than labelled data can provide effective, fully-automated, unsupervised spindle detection. This work also exposes the dangers of applying cross-validation without considering the dependence of spindle properties on parameters. Parameters selected to optimize one performance metric or matching method are not optimized for others. Furthermore, elucidation of the stability of predicted indicators with respect to algorithm parameter selection is critical to practical application of these algorithms.

Identifying sleep spindles with multichannel EEG and classification optimization

Researchers classify critical neural events during sleep called spindles that are related to memory consolidation using the method of scalp electroencephalography (EEG). Manual classification is time consuming and is susceptible to low inter-rater agreement. This could be improved using an automated approach. This study presents an optimized filter based and thresholding (FBT) model to set up a baseline for comparison to evaluate machine learning models using naïve features, such as raw signals, peak frequency, and dominant power. The FBT model allows us to formally define sleep spindles using signal processing but may miss examples most human scorers would agree are spindles. Machine learning methods in theory should be able to approach performance of human raters but they require a large quantity of scored data, proper feature representation, intensive feature engineering, and model selection. We evaluate both the FBT model and machine learning models with naïve features. We show that the machine learning models derived from the FBT model improve classification performance. An automated approach designed for the current data was applied to the DREAMS dataset [1]. With one of the expert's annotation as a gold standard, our pipeline yields an excellent sensitivity that is close to a second expert's scores and with the advantage that it can classify spindles based on multiple channels if more channels are available. More importantly, our pipeline could be modified as a guide to aid manual annotation of sleep spindles based on multiple channels quickly (6-10 s for processing a 40-min EEG recording), making spindle detection faster and more objective.

Sleep: An Open-Source Python Software for Visualization, Analysis, and Staging of Sleep Data

We introduce Sleep, a new Python open-source graphical user interface (GUI) dedicated to visualization, scoring and analyses of sleep data. Among its most prominent features are: (1) Dynamic display of polysomnographic data, spectrogram, hypnogram and topographic maps with several customizable parameters, (2) Implementation of several automatic detection of sleep features such as spindles, K-complexes, slow waves, and rapid eye movements (REM), (3) Implementation of practical signal processing tools such as re-referencing or filtering, and (4) Display of main descriptive statistics including publication-ready tables and figures. The software package supports loading and reading raw EEG data from standard file formats such as European Data Format, in addition to a range of commercial data formats. Most importantly, Sleep is built on top of the VisPy library, which provides GPU-based fast and high-level visualization. As a result, it is capable of efficiently handling and displaying large sleep datasets. Sleep is freely available (http://visbrain.org/sleep) and comes with sample datasets and an extensive documentation. Novel functionalities will continue to be added and open-science community efforts are expected to enhance the capacities of this module.

Multichannel sleep spindle detection using sparse low-rank optimization

BACKGROUND

Automated single-channel spindle detectors, for human sleep EEG, are blind to the presence of spindles in other recorded channels unlike visual annotation by a human expert.

NEW METHOD

We propose a multichannel spindle detection method that aims to detect global and local spindle activity in human sleep EEG. Using a non-linear signal model, which assumes the input EEG to be the sum of a transient and an oscillatory component, we propose a multichannel transient separation algorithm. Consecutive overlapping blocks of the multichannel oscillatory component are assumed to be low-rank whereas the transient component is assumed to be piecewise constant with a zero baseline. The estimated oscillatory component is used in conjunction with a bandpass filter and the Teager operator for detecting sleep spindles.

RESULTS AND COMPARISON WITH OTHER METHODS

The proposed method is applied to two publicly available databases and compared with 7 existing single-channel automated detectors. F₁ scores for the proposed spindle detection method averaged 0.66 (0.02) and 0.62 (0.06) for the two databases, respectively. For an overnight 6 channel EEG signal, the proposed algorithm takes about 4min to detect sleep spindles simultaneously across all channels with a single setting of corresponding algorithmic parameters.

CONCLUSIONS

The proposed method attempts to mimic and utilize, for better spindle detection, a particular human expert behavior where the decision to mark a spindle event may be subconsciously influenced by the presence of a spindle in EEG channels other than the central channel visible on a digital screen.

The Accuracy, Night-to-Night Variability, and Stability of Frontopolar Sleep Electroencephalography Biomarkers

STUDY OBJECTIVES

To assess the validity of sleep architecture and sleep continuity biomarkers obtained from a portable, multichannel forehead electroencephalography (EEG) recorder.

METHODS

Forty-seven subjects simultaneously underwent polysomnography (PSG) while wearing a multichannel frontopolar EEG recording device (Sleep Profiler). The PSG recordings independently staged by 5 registered polysomnographic technologists were compared for agreement with the autoscored sleep EEG before and after expert review. To assess the night-to-night variability and first night bias, 2 nights of self-applied, in-home EEG recordings obtained from a clinical cohort of 63 patients were used (41% with a diagnosis of insomnia/depression, 35% with insomnia/obstructive sleep apnea, and 17.5% with all three). The between-night stability of abnormal sleep biomarkers was determined by comparing each night's data to normative reference values.

RESULTS

The mean overall interscorer agreements between the 5 technologists were 75.9%, and the mean kappa score was 0.70. After visual review, the mean kappa score between the autostaging and five raters was 0.67, and staging agreed with a majority of scorers in at least 80% of the epochs for all stages except stage N1. Sleep spindles, autonomic activation, and stage N3 exhibited the least between-night variability (P < .0001) and strongest between-night stability. Antihypertensive medications were found to have a significant effect on sleep quality biomarkers (P < .02).

CONCLUSIONS

A strong agreement was observed between the automated sleep staging and human-scored PSG. One night's recording appeared sufficient to characterize abnormal slow wave sleep, sleep spindle activity, and heart rate variability in patients, but a 2-night average improved the assessment of all other sleep biomarkers.

COMMENTARY

Two commentaries on this article appear in this issue on pages 771 and 773.

K-complexes, spindles, and ERPs as impulse responses: unification via neural field theory

To interrelate K-complexes, spindles, evoked response potentials (ERPs), and spontaneous electroencephalography (EEG) using neural field theory (NFT), physiology-based NFT of the corticothalamic system is used to model cortical excitatory and inhibitory populations and thalamic relay and reticular nuclei. The impulse response function of the model is used to predict the responses to impulses, which are compared with transient waveforms in sleep studies. Fits to empirical data then allow underlying brain physiology to be inferred and compared with other waves. Spontaneous K-complexes, spindles, and other transient waveforms can be reproduced using NFT by treating them as evoked responses to impulsive stimuli with brain parameters appropriate to spontaneous EEG in sleep stage 2. Using this approach, spontaneous K-complexes and sleep spindles can be analyzed using the same single theory as previously been used to account for waking ERPs and other EEG phenomena. As a result, NFT can explain a wide variety of transient waveforms that have only been phenomenologically classified to date. This enables noninvasive fitting to be used to infer underlying physiological parameters. This physiology-based model reproduces the time series of different transient EEG waveforms; it has previously reproduced experimental EEG spectra, and waking ERPs, and many other observations, thereby unifying transient sleep waveforms with these phenomena.

Meet Spinky: An Open-Source Spindle and K-Complex Detection Toolbox Validated on the Open-Access Montreal Archive of Sleep Studies (MASS)

Sleep spindles and K-complexes are among the most prominent micro-events observed in electroencephalographic (EEG) recordings during sleep. These EEG microstructures are thought to be hallmarks of sleep-related cognitive processes. Although tedious and time-consuming, their identification and quantification is important for sleep studies in both healthy subjects and patients with sleep disorders. Therefore, procedures for automatic detection of spindles and K-complexes could provide valuable assistance to researchers and clinicians in the field. Recently, we proposed a framework for joint spindle and K-complex detection (Lajnef et al., 2015a) based on a Tunable Q-factor Wavelet Transform (TQWT; Selesnick, 2011a) and morphological component analysis (MCA). Using a wide range of performance metrics, the present article provides critical validation and benchmarking of the proposed approach by applying it to open-access EEG data from the Montreal Archive of Sleep Studies (MASS; O'Reilly et al., 2014). Importantly, the obtained scores were compared to alternative methods that were previously tested on the same database. With respect to spindle detection, our method achieved higher performance than most of the alternative methods. This was corroborated with statistic tests that took into account both sensitivity and precision (i.e., Matthew's coefficient of correlation (MCC), F1, Cohen κ). Our proposed method has been made available to the community via an open-source tool named Spinky (for spindle and K-complex detection). Thanks to a GUI implementation and access to Matlab and Python resources, Spinky is expected to contribute to an open-science approach that will enhance replicability and reliable comparisons of classifier performances for the detection of sleep EEG microstructure in both healthy and patient populations.

Staging Sleep in Polysomnograms: Analysis of Inter-Scorer Variability

STUDY OBJECTIVES

To determine the reasons for inter-scorer variability in sleep staging of polysomnograms (PSGs).

METHODS

Fifty-six PSGs were scored (5-stage sleep scoring) by 2 experienced technologists, (first manual, M1). Months later, the technologists edited their own scoring (second manual, M2) based upon feedback from the investigators that highlighted differences between their scoring. The PSGs were then scored with an automatic system (Auto) and the technologists edited them, epoch-by-epoch (Edited-Auto). This resulted in 6 different manual scores for each PSG. Epochs were classified as scorer errors (one M1 score differed from the other 5 scores), scorer bias (all 3 scores of each technologist were similar, but differed from the other technologist) and equivocal (sleep scoring was inconsistent within and between technologists).

RESULTS

Percent agreement after M1 was 78.9% ± 9.0% and was unchanged after M2 (78.1% ± 9.7%) despite numerous edits (≈40/PSG) by the scorers. Agreement in Edited-Auto was higher (86.5% ± 6.4%, p < 1E-9). Scorer errors (< 2% of epochs) and scorer bias (3.5% ± 2.3% of epochs) together accounted for < 20% of M1 disagreements. A large number of epochs (92 ± 44/PSG) with scoring agreement in M1 were subsequently changed in M2 and/or Edited-Auto. Equivocal epochs, which showed scoring inconsistency, accounted for 28% ± 12% of all epochs, and up to 76% of all epochs in individual patients. Disagreements were largely between awake/NREM, N1/N2, and N2/N3 sleep.

CONCLUSION

Inter-scorer variability is largely due to epochs that are difficult to classify. Availability of digitally identified events (e.g., spindles) or calculated variables (e.g., depth of sleep, delta wave duration) during scoring may greatly reduce scoring variability.

Mild Airflow Limitation during N2 Sleep Increases K-complex Frequency and Slows Electroencephalographic Activity

STUDY OBJECTIVES

To determine the effects of mild airflow limitation on K-complex frequency and morphology and electroencephalogram (EEG) spectral power.

METHODS

Transient reductions in continuous positive airway pressure (CPAP) during stable N2 sleep were performed to induce mild airflow limitation in 20 patients with obstructive sleep apnea (OSA) and 10 healthy controls aged 44 ± 13 y. EEG at C3 and airflow were measured in 1-min windows to quantify K-complex properties and EEG spectral power immediately before and during transient reductions in CPAP. The frequency and morphology (amplitude and latency of P200, N550 and N900 components) of K-complexes and EEG spectral power were compared between conditions.

RESULTS

During mild airflow limitation (18% reduction in peak inspiratory airflow from baseline, 0.38 ± 0.11 versus 0.31 ± 0.1 L/sec) insufficient to cause American Academy of Sleep Medicine-defined cortical arousal, K-complex frequency (9.5 ± 4.5 versus 13.7 ± 6.4 per min, P < 0.01), N550 amplitude (25 ± 3 versus 27 ± 3 μV, P < 0.01) and EEG spectral power (delta: 147 ± 48 versus 230 ± 99 μV(2), P < 0.01 and theta bands: 31 ± 14 versus 34 ± 13 μV(2), P < 0.01) significantly increased whereas beta band power decreased (14 ± 5 versus 11 ± 4 μV(2), P < 0.01) compared to the preceding non flow-limited period on CPAP. K-complex frequency, morphology, and timing did not differ between patients and controls.

CONCLUSION

Mild airflow limitation increases K-complex frequency, N550 amplitude, and spectral power of delta and theta bands. In addition to providing mechanistic insight into the role of mild airflow limitation on K-complex characteristics and EEG activity, these findings may have important implications for respiratory conditions in which airflow limitation during sleep is common (e.g., snoring and OSA).

Sleep spindle and K-complex detection using tunable Q-factor wavelet transform and morphological component analysis

A novel framework for joint detection of sleep spindles and K-complex events, two hallmarks of sleep stage S2, is proposed. Sleep electroencephalography (EEG) signals are split into oscillatory (spindles) and transient (K-complex) components. This decomposition is conveniently achieved by applying morphological component analysis (MCA) to a sparse representation of EEG segments obtained by the recently introduced discrete tunable Q-factor wavelet transform (TQWT). Tuning the Q-factor provides a convenient and elegant tool to naturally decompose the signal into an oscillatory and a transient component. The actual detection step relies on thresholding (i) the transient component to reveal K-complexes and (ii) the time-frequency representation of the oscillatory component to identify sleep spindles. Optimal thresholds are derived from ROC-like curves (sensitivity vs. FDR) on training sets and the performance of the method is assessed on test data sets. We assessed the performance of our method using full-night sleep EEG data we collected from 14 participants. In comparison to visual scoring (Expert 1), the proposed method detected spindles with a sensitivity of 83.18% and false discovery rate (FDR) of 39%, while K-complexes were detected with a sensitivity of 81.57% and an FDR of 29.54%. Similar performances were obtained when using a second expert as benchmark. In addition, when the TQWT and MCA steps were excluded from the pipeline the detection sensitivities dropped down to 70% for spindles and to 76.97% for K-complexes, while the FDR rose up to 43.62 and 49.09%, respectively. Finally, we also evaluated the performance of the proposed method on a set of publicly available sleep EEG recordings. Overall, the results we obtained suggest that the TQWT-MCA method may be a valuable alternative to existing spindle and K-complex detection methods. Paths for improvements and further validations with large-scale standard open-access benchmarking data sets are discussed.