A knowledge discovery methodology from EEG data for cyclic alternating pattern detection

Deep-Learning-Based Classification of Cyclic-Alternating-Pattern Sleep Phases

Determining the cyclic-alternating-pattern (CAP) phases in sleep using electroencephalography (EEG) signals is crucial for assessing sleep quality. However, most current methods for CAP classification primarily rely on classical machine learning techniques, with limited implementation of deep-learning-based tools. Furthermore, these methods often require manual feature extraction. Herein, we propose a fully automatic deep-learning-based algorithm that leverages convolutional neural network architectures to classify the EEG signals via their time-frequency representations. Through our investigation, we explored using time-frequency analysis techniques and found that Wigner-based representations outperform the commonly used short-time Fourier transform for CAP classification. Additionally, our algorithm incorporates contextual information of the EEG signals and employs data augmentation techniques specifically designed to preserve the time-frequency structure. The model is developed using EEG signals of healthy subjects from the publicly available CAP sleep database (CAPSLPDB) on Physionet. An experimental study demonstrates that our algorithm surpasses existing machine-learning-based methods, achieving an accuracy of 77.5% on a balanced test set and 81.8% when evaluated on an unbalanced test set. Notably, the proposed algorithm exhibits efficiency and scalability, making it suitable for on-device implementation to enhance CAP identification procedures.

CAPSCNet: A novel scattering network for automated identification of phasic cyclic alternating patterns of human sleep using multivariate EEG signals

The Cyclic Alternating Pattern (CAP) can be considered a physiological marker of sleep instability. The CAP can examine various sleep-related disorders. Certain short events (A and B phases) manifest related to a specific physiological process or pathology during non-rapid eye movement (NREM) sleep. These phases unexpectedly modify EEG oscillations; hence, manual detection is challenging. Therefore, it is highly desirable to have an automated system for detecting the A-phases (AP). Deep convolution neural networks (CNN) have shown high performance in various healthcare applications. A variant of the deep neural network called the Wavelet Scattering Network (WSN) has been used to overcome the specific limitations of CNN, such as the need for a large amount of data to train the model. WSN is an optimized network that can learn features that help discriminate patterns hidden inside signals. Also, WSNs are invariant to local perturbations, making the network significantly more reliable and effective. It can also help improve performance on tasks where data is minimal. In this study, we proposed a novel WSN-based CAPSCNet to automatically detect AP using EEG signals. Seven dataset variants of cyclic alternating pattern (CAP) sleep cohort is employed for this study. Two electroencephalograms (EEG) derivations, namely: C4-A1 and F4-C4, are used to develop the CAPSCNet. The model is examined using healthy subjects and patients tormented by six different sleep disorders, namely: sleep-disordered breathing (SDB), insomnia, nocturnal frontal lobe epilepsy (NFLE), narcolepsy, periodic leg movement disorder (PLM) and rapid eye movement behavior disorder (RBD) subjects. Several different machine-learning algorithms were used to classify the features obtained from the WSN. The proposed CAPSCNet has achieved the highest average classification accuracy of 83.4% using a trilayered neural network classifier for the healthy data variant. The proposed CAPSCNet is efficient and computationally faster.

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.

Computerized detection of cyclic alternating patterns of sleep: A new paradigm, future scope and challenges

BACKGROUND AND OBJECTIVES

Sleep quality is associated with wellness, and its assessment can help diagnose several disorders and diseases. Sleep analysis is commonly performed based on self-rating indices, sleep duration, environmental factors, physiologically and polysomnographic-derived parameters, and the occurrence of disorders. However, the correlation that has been observed between the subjective assessment and objective measurements of sleep quality is small. Recently, a few automated systems have been suugested to measure sleep quality to address this challenge. Sleep quality can be assessed by evaluating macrostructure-based sleep analysis via the examination of sleep cycles, namely Rapid Eye Movement (REM) and Non Rapid Eye Movement (NREM) with N1, N2, and N3 stages. However, macrostructure sleep analysis does not consider transitory phenomena like K-complexes and transient fluctuations, which are indispensable in diagnosing various sleep disorders. The CAP, part of the microstructure of sleep, may offer a more precise and relevant examination of sleep and can be considered one of the candidates to measure sleep quality and identify sleep disorders such as insomnia and apnea. CAP is characterized by very subtle changes in the brain's electroencephalogram (EEG) signals that occur during the NREM stage of sleep. The variations among these patterns in healthy subjects and subjects with sleep disorders can be used to identify sleep disorders. Studying CAP is highly arduous for human experts; thus, developing automated systems for assessing CAP is gaining momentum. Developing new techniques for automated CAP detection installed in clinical setups is essential. This paper aims to analyze the algorithms and methods presented in the literature for the automatic assessment of CAP and the development of CAP-based sleep markers that may enhance sleep quality assessment, helping diagnose sleep disorders.

METHODS

This literature survey examined the automated assessment of CAP and related parameters. We have reviewed 34 research articles, including fourteen ML, nine DL, and ten based on some other techniques.

RESULTS

The review includes various algorithms, databases, features, classifiers, and classification performances and their comparisons, advantages, and limitations of automated systems for CAP assessment.

CONCLUSION

A detailed description of state-of-the-art research findings on automated CAP assessment and associated challenges has been presented. Also, the research gaps have been identified based on our review. Further, future research directions are suggested for sleep quality assessment using CAP.

Sleep Micro-Macro-structures in Psychophysiological Insomnia. PSG Study

Study Objectives

To address sleep micro-macro-structures in psychophysiological insomnia (PPI) as denoted by cyclic alternating pattern (CAP), Sleep spindles, and hyperarousal as microstructures and sleep characteristics such as sleep stages' variables, and heart rate as macrostructures.

Methods

Two statistical populations, with 20 participants in each, are addressed: good sleepers (GS) and patients with psychophysiological insomnia (PPI). The sleep polysomnography (PSG) for one night was performed and sleep macro-micro-structures extraction was implemented for each participant. Cyclic alternating patterns were scored manually and other structures were monitored by the original PSG's device software. Analytical methods are used to dissect the results.

Result

The findings imply: (a) psychophysiological insomnia is characterized by CAP differences from good sleepers which are associated with hyperarousal; (b) Regarding microstructure, more microarousals in sleep stages caused more number of wake index. (c) The ratio of sleep stages, sleep latency and heart rate as sleep macrostructure are significantly changed. (d) There is no significant difference between PPI and GS groups on spindles length in our research.

Conclusion

Regarding all sleep disorders and especially PPI, CAP variables, EEG arousals, and sleep spindles as microstructures and Total Sleep Time, Sleep Latency, number of waking, REM duration, and Heart Rate as macrostructures were found to be critical for the diagnosis of psychophysiological insomnia The analysis contributes to understanding better approaches in the quantitative specification of psychophysiological insomnia compare to good sleepers.

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.

EEG-Brain Activity Monitoring and Predictive Analysis of Signals Using Artificial Neural Networks

Predictive observation and real-time analysis of the values of biomedical signals and automatic detection of epileptic seizures before onset are beneficial for the development of warning systems for patients because the patient, once informed that an epilepsy seizure is about to start, can take safety measures in useful time. In this article, Daubechies discrete wavelet transform (DWT) was used, coupled with analysis of the correlations between biomedical signals that measure the electrical activity in the brain by electroencephalogram (EEG), electrical currents generated in muscles by electromyogram (EMG), and heart rate monitoring by photoplethysmography (PPG). In addition, we used artificial neural networks (ANN) for automatic detection of epileptic seizures before onset. We analyzed 30 EEG recordings 10 min before a seizure and during the seizure for 30 patients with epilepsy. In this work, we investigated the ANN dimensions of 10, 50, 100, and 150 neurons, and we found that using an ANN with 150 neurons generates an excellent performance in comparison to a 10-neuron-based ANN. However, this analyzes requests in an increased amount of time in comparison with an ANN with a lower neuron number. For real-time monitoring, the neurons number should be correlated with the response time and power consumption used in wearable devices.

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.

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.