Characterization of A phases during the cyclic alternating pattern of sleep

The dynamics of cyclic-periodic phenomena during non-rapid and rapid eye movement sleep

Sleep is a complex physiological state characterized by distinct stages, each exhibiting unique electroencephalographic patterns and physiological phenomena. Sleep research has unveiled the presence of intricate cyclic-periodic phenomena during both non-rapid eye movement and rapid eye movement sleep stages. These phenomena encompass a spectrum of rhythmic oscillations and periodic events, including cyclic alternating pattern, periodic leg movements during sleep, respiratory-related events such as apneas, and heart rate variability. This narrative review synthesizes empirical findings and theoretical frameworks to elucidate the dynamics, interplay and implications of cyclic-periodic phenomena within the context of sleep physiology. Furthermore, it invokes the clinical relevance of these phenomena in the diagnosis and management of sleep disorders.

Towards automatic EEG cyclic alternating pattern analysis: a systematic review

This study conducted a systematic review to determine the feasibility of automatic Cyclic Alternating Pattern (CAP) analysis. Specifically, this review followed the 2020 Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) guidelines to address the formulated research question: is automatic CAP analysis viable for clinical application? From the identified 1,280 articles, the review included 35 studies that proposed various methods for examining CAP, including the classification of A phase, their subtypes, or the CAP cycles. Three main trends were observed over time regarding A phase classification, starting with mathematical models or features classified with a tuned threshold, followed by using conventional machine learning models and, recently, deep learning models. Regarding the CAP cycle detection, it was observed that most studies employed a finite state machine to implement the CAP scoring rules, which depended on an initial A phase classifier, stressing the importance of developing suitable A phase detection models. The assessment of A-phase subtypes has proven challenging due to various approaches used in the state-of-the-art for their detection, ranging from multiclass models to creating a model for each subtype. The review provided a positive answer to the main research question, concluding that automatic CAP analysis can be reliably performed. The main recommended research agenda involves validating the proposed methodologies on larger datasets, including more subjects with sleep-related disorders, and providing the source code for independent confirmation.

A-phase index: an alternative view for sleep stability analysis based on automatic detection of the A-phases from the cyclic alternating pattern

STUDY OBJECTIVES

Sleep stability can be studied by evaluating the cyclic alternating pattern (CAP) in electroencephalogram (EEG) signals. The present study presents a novel approach for assessing sleep stability, developing an index based on the CAP A-phase characteristics to display a sleep stability profile for a whole night's sleep.

METHODS

Two ensemble classifiers were developed to automatically score the signals, one for "A-phase" and the other for "non-rapid eye movement" estimation. Both were based on three one-dimension convolutional neural networks. Six different inputs were produced from the EEG signal to feed the ensembles' classifiers. A proposed heuristic-oriented search algorithm individually tuned the classifiers' structures. The outputs of the two ensembles were combined to estimate the A-phase index (API). The models can also assess the A-phase subtypes, their API, and the CAP cycles and rate.

RESULTS

Four dataset variations were considered, examining healthy and sleep-disordered subjects. The A-phase average estimation's accuracy, sensitivity, and specificity range was 82%-87%, 72%-80%, and 82%-88%, respectively. A similar performance was attained for the A-phase subtype's assessments, with an accuracy range of 82%-88%. Furthermore, in the examined dataset's variations, the API metric's average error varied from 0.15 to 0.25 (with a median range of 0.11-0.24). These results were attained without manually removing wake or rapid eye movement periods, leading to a methodology suitable to produce a fully automatic CAP scoring algorithm.

CONCLUSIONS

Metrics based on API can be understood as a new view for CAP analysis, where the goal is to produce and examine a sleep stability profile.

Multiple Time Series Fusion Based on LSTM: An Application to CAP A Phase Classification Using EEG

The Cyclic Alternating Pattern (CAP) is a periodic activity detected in the electroencephalogram (EEG) signals. This pattern was identified as a marker of unstable sleep with several possible clinical applications; however, there is a need to develop automatic methodologies to facilitate real-world applications based on CAP assessment. Therefore, a deep learning-based EEG channels' feature level fusion was proposed in this work and employed for the CAP A phase classification. Two optimization algorithms optimized the channel selection, fusion, and classification procedures. The developed methodologies were evaluated by fusing the information from multiple EEG channels for patients with nocturnal frontal lobe epilepsy and patients without neurological disorders. Results showed that both optimization algorithms selected a comparable structure with similar feature level fusion, consisting of three electroencephalogram channels (Fp2-F4, C4-A1, F4-C4), which is in line with the CAP protocol to ensure multiple channels' arousals for CAP detection. Moreover, the two optimized models reached an area under the receiver operating characteristic curve of 0.82, with average accuracy ranging from 77% to 79%, a result in the upper range of the specialist agreement and best state-of-the-art works, despite a challenging dataset. The proposed methodology also has the advantage of providing a fully automatic analysis without requiring any manual procedure. Ultimately, the models were revealed to be noise-resistant and resilient to multiple channel loss, being thus suitable for real-world application.

Heuristic Optimization of Deep and Shallow Classifiers: An Application for Electroencephalogram Cyclic Alternating Pattern Detection

Methodologies for automatic non-rapid eye movement and cyclic alternating pattern analysis were proposed to examine the signal from one electroencephalogram monopolar derivation for the A phase, cyclic alternating pattern cycles, and cyclic alternating pattern rate assessments. A population composed of subjects free of neurological disorders and subjects diagnosed with sleep-disordered breathing was studied. Parallel classifications were performed for non-rapid eye movement and A phase estimations, examining a one-dimension convolutional neural network (fed with the electroencephalogram signal), a long short-term memory (fed with the electroencephalogram signal or with proposed features), and a feed-forward neural network (fed with proposed features), along with a finite state machine for the cyclic alternating pattern cycle scoring. Two hyper-parameter tuning algorithms were developed to optimize the classifiers. The model with long short-term memory fed with proposed features was found to be the best, with accuracy and area under the receiver operating characteristic curve of 83% and 0.88, respectively, for the A phase classification, while for the non-rapid eye movement estimation, the results were 88% and 0.95, respectively. The cyclic alternating pattern cycle classification accuracy was 79% for the same model, while the cyclic alternating pattern rate percentage error was 22%.

Automated Characterization of Cyclic Alternating Pattern Using Wavelet-Based Features and Ensemble Learning Techniques with EEG Signals

Sleep is highly essential for maintaining metabolism of the body and mental balance for increased productivity and concentration. Often, sleep is analyzed using macrostructure sleep stages which alone cannot provide information about the functional structure and stability of sleep. The cyclic alternating pattern (CAP) is a physiological recurring electroencephalogram (EEG) activity occurring in the brain during sleep and captures microstructure of the sleep and can be used to identify sleep instability. The CAP can also be associated with various sleep-related pathologies, and can be useful in identifying various sleep disorders. Conventionally, sleep is analyzed using polysomnogram (PSG) in various sleep laboratories by trained physicians and medical practitioners. However, PSG-based manual sleep analysis by trained medical practitioners is onerous, tedious and unfavourable for patients. Hence, a computerized, simple and patient convenient system is highly desirable for monitoring and analysis of sleep. In this study, we have proposed a system for automated identification of CAP phase-A and phase-B. To accomplish the task, we have utilized the openly accessible CAP sleep database. The study is performed using two single-channel EEG modalities and their combination. The model is developed using EEG signals of healthy subjects as well as patients suffering from six different sleep disorders namely nocturnal frontal lobe epilepsy (NFLE), sleep-disordered breathing (SDB), narcolepsy, periodic leg movement disorder (PLM), insomnia and rapid eye movement behavior disorder (RBD) subjects. An optimal orthogonal wavelet filter bank is used to perform the wavelet decomposition and subsequently, entropy and Hjorth parameters are extracted from the decomposed coefficients. The extracted features have been applied to different machine learning algorithms. The best performance is obtained using ensemble of bagged tress (EBagT) classifier. The proposed method has obtained the average classification accuracy of 84%, 83%, 81%, 78%, 77%, 76% and 72% for NFLE, healthy, SDB, narcolepsy, PLM, insomnia and RBD subjects, respectively in discriminating phases A and B using a balanced database. Our developed model yielded an average accuracy of 78% when all 77 subjects including healthy and sleep disordered patients are considered. Our proposed system can assist the sleep specialists in an automated and efficient analysis of sleep using sleep microstructure.

On the use of patterns obtained from LSTM and feature-based methods for time series analysis: application in automatic classification of the CAP A phase subtypes

The cyclic alternating pattern is a marker of sleep instability identified in the electroencephalogram signals whose sequence of transient variations compose the A phases. These phases are divided into three subtypes (A1, A2, and A3) according to the presented patterns. The traditional approach of manually scoring the cyclic alternating pattern events for the full night is unpractical, with a high probability of miss classification, due to the large quantity of information that is produced during a full night recording. To address this concern, automatic methodologies were proposed using a long short-term memory to perform the classification of one electroencephalogram monopolar derivation signal. The proposed model is composed of three classifiers, one for each subtype, performing binary classification in a one versus all procedure. Two methodologies were tested: feed the pre-processed electroencephalogram signal to the classifiers; create features from the pre-processed electroencephalogram signal which were fed to the classifiers (feature-based methods). It was verified that the A1 subtype classification performance was similar for both methods and the A2 subtype classification was higher for the feature-based methods. However, the A3 subtype classification was found to be the most challenging to be performed, and for this classification, the feature-based methods were superior. A characterization analysis was also performed using a recurrence quantification analysis to further examine the subtypes characteristics. The average accuracy and area under the receiver operating characteristic curve for the A1, A2, and A3 subtypes of the feature-based methods were respectively: 82% and 0.92; 80% and 0.88; 85% and 0.86.

Matrix of Lags: A tool for analysis of multiple dependent time series applied for CAP scoring

BACKGROUND

Multiple methods have been developed to assess what happens between and within time series. In a particular type of these series, the previous values of the currently observed series are contingent on the lagged values of another series. These cases can commonly be addressed by regression. However, a model selection criteria should be employed to evaluate the compromise between the amount of information provided and the model complexity. This is the basis for the development of the Matrix of Lags (MoL), a tool to study dependent time series.

METHODS

For each input, multiple regressions were applied to produce a model for each lag and a model selection criterion identifies the lags that will populate an auxiliary matrix. Afterwards, the energy of the lags (that are in the auxiliary matrix) was used to define a row of the MoL. Therefore, each input corresponds to a row of the MoL. To test the proposed tool, the heart rate variability and the electrocardiogram derived respiration were employed to perform the indirect estimation of the electroencephalography cyclic alternating pattern (CAP) cycles. Therefore, a support vector machine was fed with the MoL to perform the CAP cycle classification for each input signal. Multiple tests were carried out to further examine the proposed tool, including the effect of balancing the datasets, application of other regression methods and employment of two feature section models. The first was based on sequential backward selection while the second examined characteristics of a return map.

RESULTS

The best performance of the subject independent model was attained by feeding the lags, selected by sequential backward selection, to a support vector machine, achieving an average accuracy, sensitivity, specificity and area under the receiver operating characteristic curve of, respectively, 77%, 71%, 82% and 0.77.

CONCLUSIONS

The developed model allows to perform a measurement of a characteristic marker of sleep instability (the CAP cycle) and the results are in the upper bound of the specialist agreement range with visual analysis. Thus, the developed method could possibly be used for clinical diagnosis.

Improved A-phase Detection of Cyclic Alternating Pattern Using Deep Learning

In recent years, machine learning algorithms have become increasingly popular for analyzing biomedical signals. This includes the detection of cyclic alternating pattern (CAP) in electroencephalography recordings. Here, we investigate the performance gain of a recurrent neural network (RNN) for CAP scoring in comparison to standard classification methods. We analyzed 15 recordings (n1-n15) from the publicly available CAP Sleep Database on Physionet to evaluate each machine learning method. A long short-term memory (LSTM) network increases the accuracy and F₁-score by 0.5-3.5% and 3.5-8%, respectively, compared to commonly used classification algorithms such as linear discriminant analysis, k-nearest neighbour or feed-forward neural network. Our results show that by using a LSTM classifier the quantity of correctly detected CAP events can be increased and the number of wrongly classified periods reduced. RNNs significantly improve the precision in CAP scoring by taking advantage of available information from the past for deciding current classification.

A Portable Wireless Device for Cyclic Alternating Pattern Estimation from an EEG Monopolar Derivation

Quality of sleep can be assessed by analyzing the cyclic alternating pattern, a long-lasting periodic activity that is composed of two alternate electroencephalogram patterns, which is considered to be a marker of sleep instability. Experts usually score this pattern through a visual examination of each one-second epoch of an electroencephalogram signal, a repetitive and time-consuming task that is prone to errors. To address these issues, a home monitoring device was developed for automatic scoring of the cyclic alternating pattern by analyzing the signal from one electroencephalogram derivation. Three classifiers, specifically, two recurrent networks (long short-term memory and gated recurrent unit) and one one-dimension convolutional neural network, were developed and tested to determine which was more suitable for the cyclic alternating pattern phase’s classification. It was verified that the network based on the long short-term memory attained the best results with an average accuracy, sensitivity, specificity and area under the receiver operating characteristic curve of, respectively, 76%, 75%, 77% and 0.752. The classified epochs were then fed to a finite state machine to determine the cyclic alternating pattern cycles and the performance metrics were 76%, 71%, 84% and 0.778, respectively. The performance achieved is in the higher bound of the experts’ expected agreement range and considerably higher than the inter-scorer agreement of multiple experts, implying the usability of the device developed for clinical analysis.

Sleep Macrostructure and NREM Sleep Instability Analysis in Pediatric Developmental Coordination Disorder

Developmental Coordination Disorder (DCD) is considered to be abnormal motor skills learning, identified by clumsiness, slowness, and/or motor inaccuracy impairing the daily-life activities in all ages of life, in the absence of sensory, cognitive, or neurological deficits impairment. The present research focuses on studying DCD sleep structure and Cyclic Alternating Pattern (CAP) parameters with a full overnight polysomnography and to study the putative correlations between sleep architecture and CAP parameters with motor coordination skills. The study was a cross-sectional design involving 42 children (26M/16F; mean age 10.12 ± 1.98) selected as a DCD group compared with 79 children (49M/30F; mean age 9.94 ± 2.84) identified as typical (no-DCD) for motor ability and sleep macrostructural parameters according to the MABC-2 and polysomnographic (PSG) evaluations. The two groups (DCD and non-DCD) were similar for age (p = 0.715) and gender (p = 0.854). More significant differences in sleep architecture and CAP parameters were found between two groups and significant correlations were identified between sleep parameters and motor coordination skills in the study population. In conclusion, our data show relevant abnormalities in sleep structure of DCD children and suggest a role for rapid components of A phases on motor coordination development

Automatic A-Phase Detection of Cyclic Alternating Patterns in Sleep Using Dynamic Temporal Information

The identification of recurrent, transient perturbations in brain activity during sleep, so called cyclic alternating patterns (CAP), is of significant interest as they have been linked to neurological pathologies. CAP sequences comprise multiple, consecutive cycles of phasic activation (A-phases). Here, we propose a novel, automated system exploiting the dynamical, temporal information in electroencephalography (EEG) recordings for the classification of A-phases and their subtypes. Using recurrent neural networks (RNN), crucial information in the temporal behavior of the EEG is extracted. The automatic classification system is equipped to deal with the biasing issue of imbalanced data sets and uses state-of-the-art signal processing methods to reduce inter-subject variation. To evaluate our system, we applied recordings from the publicly available CAP Sleep Database on Physionet. Our results show that the RNN improved the detection accuracy by 3-5% and the F₁-score by approximately 7% on two data sets compared to a normal feed-forward neural network. Our system achieves a sensitivity of approximately 76-78% and F₁-score between 63-68%, significantly outperforming existing technologies. Moreover, its sensitivity for subtype classification of 60-63% (A1), 42-45% (A2), and 71-74% (A3) indicates superior multi-class classification performance for CAP detection. In conclusion, we have developed a fully automated high performance CAP scoring system that includes A-phase subtype classification. RNN classifiers yield a significant improvement in accuracy and sensitivity compared to previously proposed systems.

Correlation of sleep microstructure with daytime sleepiness and cognitive function in young and middle-aged adults with obstructive sleep apnea syndrome

PURPOSE

To compare microstructural features of sleep in young and middle-aged adults with differing severities of obstructive sleep apnea syndrome (OSAS), and to investigate the relationship between sleep microstructural fragmentation and cognitive impairment, as well as daytime sleepiness, in these patients.

METHODS

A total of 134 adults with snoring (mean age, 37.54 ± 7.66 years) were classified into four groups based on apnea-hypopnea index: primary snoring, mild OSAS, moderate OSAS, and severe OSAS. Overnight polysomnography was performed to assess respiratory, sleep macrostructure (N1, N2, N3, and R), and sleep microstructure (arousal, cyclic alternating pattern [CAP]) parameters. Cognitive function and daytime sleepiness were assessed using Montreal Cognitive Assessment (MoCA) and Epworth Sleepiness Scale (ESS).

RESULTS

As OSAS severity increased, MoCA gradually decreased and ESS gradually increased. N1%, N2%, and N3% sleep were significantly different between the severe OSAS group and the primary snoring, mild OSAS, and moderate OSAS groups (all P < 0.05). Overall arousal index, respiratory-related arousal index, CAP time, CAP rate, phase A index, number of CAP cycles, and phase A average time differed significantly in the moderate and severe OSAS groups compared with the mild OSAS and primary snoring groups (all P < 0.05). The strongest correlations identified by stepwise multiple regression analysis were between phase A3 index and the MoCA and ESS scores.

CONCLUSIONS

Sleep microstructure exhibited significant fragmentation in patients with moderate and severe OSAS, which was associated with decreased MoCA and increased ESS scores. This suggests that phase A3 index is a sensitive indicator of sleep fragmentation in OSAS.

EEG segmentation for improving automatic CAP detection

OBJECTIVE

The aim of this study is to provide an improved method for the automatic classification of the Cyclic Alternating Pattern (CAP) sleep by applying a segmentation technique to the computation of descriptors from the EEG.

METHODS

A dataset of 16 polysomnographic recordings from healthy subjects was employed, and the EEG traces underwent first an automatic isolation of NREM sleep portions by means of an Artificial Neural Network and then a segmentation process based on the Spectral Error Measure. The information content of the descriptors was evaluated by means of ROC curves and compared with that of descriptors obtained without the use of segmentation. Finally, the descriptors were used to train a discriminant function for the automatic classification of CAP phases A.

RESULTS

A significant improvement with respect to previous scoring methods in terms of both information content carried by the descriptors and accuracy of the classification was obtained.

CONCLUSIONS

EEG segmentation proves to be a useful step in the computation of descriptors for CAP scoring.

SIGNIFICANCE

This study provides a complete method for CAP analysis, which is entirely automatic and allows the recognition of A phases with a high accuracy thanks to EEG segmentation.

Nonlinear analysis of the change points between A and B phases during the Cyclic Alternating Pattern under normal sleep

This study analyzes the nonlinear properties of the EEG at transition points of the sequences that build the Cyclic Alternating Pattern (CAP). CAP is a sleep phenomenon built up by consecutive sequences of activations and non-activations observed during the sleep time. The sleep condition can be evaluated from the patterns formed by these sequences. Eleven recordings from healthy and good sleepers were included in this study. We investigated the complexity properties of the signal at the onset and offset of the activations. The results show that EEG signals present significant differences (p&#60;0.05) between activations and non-activations in the Sample Entropy and Tsallis Entropy indices. These indices could be useful in the development of automatic methods for detecting the onset and offset of the activations, leading to significant savings of the physician's time by simplifying the manual inspection task.

A novel method to assist the detection of the Cyclic Alternating Pattern (CAP)

This study proposes a novel method to assist the detection of the components that build up the Cyclic Alternating Pattern (CAP). CAP is a sleep phenomenon formed by consecutive sequences of activations (A1, A2, A3) and non-activations during nonREM sleep. The main importance of CAP evaluation is the possibility of defining the sleep process more accurately. Ten recordings from healthy and good sleepers were included in this study. The method is based on inferential statistics to define the initial and ending points of the CAP components based only on an initialization point given by the expert. The results show concordance up to 95% for A1, 85% for A2 and 60% for A3, together with an overestimation of 1.5 s in A1, 1.3 s in A2 and 0 s in A3. The total CAP rate presents a total underestimation of 7 min. Those results suggest that the method is able to accurately detect the initial and ending points of the activations, and may be helpful for the physicians by reducing the time dedicated to the manual inspection task.

Automatic detection of CAP on central and fronto-central EEG leads via Support Vector Machines

The aim of this study is to implement a high-accuracy automatic detector of the Cyclic Alternating Pattern (CAP) during sleep. EEG data from four healthy subjects were used. Both the C4-A1 and the F4-C4 leads were analyzed for this study. Seven features were extracted from each of the two leads and two separate studies were performed for each set of descriptors. For both sets, a Support Vector Machine was trained and tested on the data with the Leave One Out cross-validation method. The two final classifications obtained on the two sets were merged, by considering a CAP A phase scored only if it had been recognized both on the central and on the frontal lead. The length of the A phase was then determined by the result on the fronto-central lead. This method leads to encouraging results, with a classification sensitivity on the whole dataset equal to 73.82%, specificity equal to 85.93%, accuracy equal to 84,05% and Cohen's kappa equal to 0.50.