Automatic detection of a phases of the cyclic alternating pattern during sleep

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.

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.

L-Tetrolet Pattern-Based Sleep Stage Classification Model Using Balanced EEG Datasets

Background: Sleep stage classification is a crucial process for the diagnosis of sleep or sleep-related diseases. Currently, this process is based on manual electroencephalogram (EEG) analysis, which is resource-intensive and error-prone. Various machine learning models have been recommended to standardize and automate the analysis process to address these problems. Materials and methods: The well-known cyclic alternating pattern (CAP) sleep dataset is used to train and test an L-tetrolet pattern-based sleep stage classification model in this research. By using this dataset, the following three cases are created, and they are: Insomnia, Normal, and Fused cases. For each of these cases, the machine learning model is tasked with identifying six sleep stages. The model is structured in terms of feature generation, feature selection, and classification. Feature generation is established with a new L-tetrolet (Tetris letter) function and multiple pooling decomposition for level creation. We fuse ReliefF and iterative neighborhood component analysis (INCA) feature selection using a threshold value. The hybrid and iterative feature selectors are named threshold selection-based ReliefF and INCA (TSRFINCA). The selected features are classified using a cubic support vector machine. Results: The presented L-tetrolet pattern and TSRFINCA-based sleep stage classification model yield 95.43%, 91.05%, and 92.31% accuracies for Insomnia, Normal dataset, and Fused cases, respectively. Conclusion: The recommended L-tetrolet pattern and TSRFINCA-based model push the envelope of current knowledge engineering by accurately classifying sleep stages even in the presence of sleep disorders.

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.

Automatic Cyclic Alternating Pattern (CAP) analysis: Local and multi-trace approaches

The Cyclic Alternating Pattern (CAP) is composed of cycles of two different electroencephalographic features: an activation A-phase followed by a B-phase representing the background activity. CAP is considered a physiological marker of sleep instability. Despite its informative nature, the clinical applications remain limited as CAP analysis is a time-consuming activity. In order to overcome this limit, several automatic detection methods were recently developed. In this paper, two new dimensions were investigated in the attempt to optimize novel, efficient and automatic detection algorithms: 1) many electroencephalographic leads were compared to identify the best local performance, and 2) the global contribution of the concurrent detection across several derivations to CAP identification. The developed algorithms were tested on 41 polysomnographic recordings from normal (n = 8) and pathological (n = 33) subjects. In comparison with the visual CAP analysis as the gold standard, the performance of each algorithm was evaluated. Locally, the detection on the F4-C4 derivation showed the best performance in comparison with all other leads, providing practical suggestions of electrode montage when a lean and minimally invasive approach is preferable. A further improvement in the detection was achieved by a multi-trace method, the Global Analysis—Common Events, to be applied when several recording derivations are available. Moreover, CAP time and CAP rate obtained with these algorithms positively correlated with the ones identified by the scorer. These preliminary findings support efficient automated ways for the evaluation of the sleep instability, generalizable to both normal and pathological subjects affected by different sleep disorders.

Automatic Sleep-Stage Scoring in Healthy and Sleep Disorder Patients Using Optimal Wavelet Filter Bank Technique with EEG Signals

Sleep stage classification plays a pivotal role in effective diagnosis and treatment of sleep related disorders. Traditionally, sleep scoring is done manually by trained sleep scorers. The analysis of electroencephalogram (EEG) signals recorded during sleep by clinicians is tedious, time-consuming and prone to human errors. Therefore, it is clinically important to score sleep stages using machine learning techniques to get accurate diagnosis. Several studies have been proposed for automated detection of sleep stages. However, these studies have employed only healthy normal subjects (good sleepers). The proposed study focuses on the automated sleep-stage scoring of subjects suffering from seven different kind of sleep disorders such as insomnia, bruxism, narcolepsy, nocturnal frontal lobe epilepsy (NFLE), periodic leg movement (PLM), rapid eye movement (REM) behavioural disorder and sleep-disordered breathing as well as normal subjects. The open source physionet's cyclic alternating pattern (CAP) sleep database is used for this study. The EEG epochs are decomposed into sub-bands using a new class of optimized wavelet filters. Two EEG channels, namely F4-C4 and C4-A1, combined are used for this work as they can provide more insights into the changes in EEG signals during sleep. The norm features are computed from six sub-bands coefficients of optimal wavelet filter bank and fed to various supervised machine learning classifiers. We have obtained the highest classification performance using an ensemble of bagged tree (EBT) classifier with 10-fold cross validation. The CAP database comprising of 80 subjects is divided into ten different subsets and then ten different sleep-stage scoring tasks are performed. Since, the CAP database is unbalanced with different duration of sleep stages, the balanced dataset also has been created using over-sampling and under-sampling techniques. The highest average accuracy of 85.3% and Cohen's Kappa coefficient of 0.786 and accuracy of 92.8% and Cohen's Kappa coefficient of 0.915 are obtained for unbalanced and balanced databases, respectively. The proposed method can reliably classify the sleep stages using single or dual channel EEG epochs of 30 s duration instead of using multimodal polysomnography (PSG) which are generally used for sleep-stage scoring. Our developed automated system is ready to be tested with more sleep EEG data and can be employed in various sleep laboratories to evaluate the quality of sleep in various sleep disorder patients and normal subjects.

Automated phase classification in cyclic alternating patterns in sleep stages using Wigner-Ville Distribution based features

Sleep is one of the most important body mechanisms responsible for the proper functioning of human body. Cyclic alternating patterns (CAP) play an indispensable role in the analysis of sleep quality and related disorders like nocturnal front lobe epilepsy, insomnia, narcolepsy etc. The traditional manual segregation methods of CAP phases by the medical experts are prone to human fatigue and errors which may lead to inaccurate diagnosis of sleep stages. In this paper, we present an automated approach for the classification of CAP phases (A and B) using Wigner-Ville Distribution (WVD) and Rényi entropy (RE) features. The WVD provides a high-resolution time-frequency analysis of the signals whereas RE provides least time-frequency uncertainty with WVD. The classification is performed using medium Gaussian kernel-based support vector machine with 10-fold cross-validation technique. We have presented the results for randomly sampled balanced data sets. The proposed approach does not require any pre-processing or post-processing stages, making it simple as compared to the existing techniques. The proposed method is able to achieve an average classification accuracy of 72.35% and 87.45% for balanced and unbalanced data sets respectively. The proposed method can aid the medical experts to analyze the cerebral stability as well as the sleep quality of a person.

Automatic identification of Cyclic Alternating Pattern (CAP) sequences based on the Teager Energy Operator

The Cyclic Alternating Pattern (CAP) is a periodic cerebral activity prevalent during Non-Rapid Eye Movement (NREM) sleep-stages. The CAP is composed by A-phases that are related to a change in amplitude, frequency or both from the background activity epochs, called B-phases. Depending on the type of increase the A-phase could be classified as A1, A2 or A3 subtype. This paper proposes the usage of the Teager Energy Operator (TEO) to analyze the amplitude changes in the different frequency-bands to detect A-phases subtypes. The TEO classification performance is compared with the performance of a state-of-the art EEG feature, applied previously for CAP scoring and referred as the macro-micro structure descriptor (MMSD). In general, the TEO is the best feature and the improved results were obtained in the delta band for the A1 and A2 sub-types. More precisely, a sensitivity and specificity of 80.31% and 82.93% were obtained for the A1 subtype, respectively. A2 phases were detected with 76.96% of sensitivity and 73.22% of specificity. The two features detected A3 subtype with approximately the same sensitivity (approx. 70%) and specificity (approx. 75%), however the results were improved by considering the highest frequency band. These results are consistent with the frequency content of the different sub-phases.

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.