Manual Sleep Staging Research Articles

A comparison of automated and manual sleep staging and respiratory event recognition in a portable sleep diagnostic device with in-lab sleep study.

The objectives were to develop and validate an algorithm for editing WatchPAT scoring and assess the accuracy in an unselected clinical population as well as age and sex substrata. Two hundred sixty-two participants were enrolled to undergo WatchPAT simultaneously with in-lab polysomnography (PSG) recordings for developing (n = 30), optimizing (n = 62), and validating (n = 170) an algorithm to review and edit respiratory events and sleep architecture of WatchPAT recordings, which was based on visual inspection of WatchPAT signals. Apnea-hypopnea index (AHI) and sleep indices were compared with PSG-derived and automated WatchPAT indices. Although estimation of total sleep time (TST) was comparable between automated and manual algorithm, estimation of rapid eye movement (REM) sleep time was markedly improved with manual editing from 0.48, 23.0 min (-43.9 to 89.8) to 0.64, 18.3 min (-32.6 to 69.1) (correlation with PSG, mean difference [reference range] from PSG, respectively). Manual scoring also improved correlation and agreement with PSG AHI from 0.65, 2.5 events/h (-24.0 to 28.9) to 0.81, -4.5 events/h (-22.5 to 13.6) as well as concordance for categorical agreement of sleep-disordered breathing severity and concordance for detecting severe REM-related sleep-disordered breathing. Interscorer reliabilities were excellent for TST and AHI, while good for REM sleep time. The automated algorithm performed better in younger than in older patients, while performed similarly between men and women with respect to concordance statistics. The manual algorithm markedly improved concordances more in older patients and women than in their counterparts. Our manual editing algorithm improves correlation and agreement with PSG-derived sleep and breathing indices. Sex and age influence the accuracy of automated analysis and the performance of manual editing on AHI concordance.

A Residual Based Attention Model for EEG Based Sleep Staging.

Sleep staging is to score the sleep state of a subject into different sleep stages such as Wake and Rapid Eye Movement (REM). It plays an indispensable role in the diagnosis and treatment of sleep disorders. As manual sleep staging through well-trained sleep experts is time consuming, tedious, and subjective, many automatic methods have been developed for accurate, efficient, and objective sleep staging. Recently, deep learning based methods have been successfully proposed for electroencephalogram (EEG) based sleep staging with promising results. However, most of these methods directly take EEG raw signals as input of convolutional neural networks (CNNs) without considering the domain knowledge of EEG staging. Apart from that, to capture temporal information, most of the existing methods utilize recurrent neural networks such as LSTM (Long Short Term Memory) which are not effective for modelling global temporal context and difficult to train. Therefore, inspired by the clinical guidelines of sleep staging such as AASM (American Academy of Sleep Medicine) rules where different stages are generally characterized by EEG waveforms of various frequencies, we propose a multi-scale deep architecture by decomposing an EEG signal into different frequency bands as input to CNNs. To model global temporal context, we utilize the multi-head self-attention module of the transformer model to not only improve performance, but also shorten the training time. In addition, we choose residual based architecture which makes training end-to-end. Experimental results on two widely used sleep staging datasets, Montreal Archive of Sleep Studies (MASS) and sleep-EDF datasets, demonstrate the effectiveness and significant efficiency (up to 12 times less training time) of our proposed method over the state-of-the-art.

Investigating the use of uni-directional and bi-directional long short-term memory models for automatic sleep stage scoring

Abstract In this paper, a study is conducted to investigate the use of a Long Short-Term Memory (LSTM) learning system in automatic sleep stage scoring. The developed algorithm will automatically learn to classify sleep stages from any acquired sleep signals data-set. This allows to resolve the difficulties that are facing experts in manual sleep stage scoring. A total of 39 Polysomnogram (PSG) recordings acquired from the online PhysioNet Sleep-EDF database are used in this study. The PSG recordings are chosen to be from the EEG Fpz-Cz signals only. The database comes with annotation files that include expert manual stage scoring based on the Rechtschaffen & Kales (R & K) scoring manual. The obtained signals go initially through a pre-processing procedure where sleep stages signals are extracted, normalized, and filtered. The resulting sleep signals are trained using a k-fold cross-validation scheme of 10-folds. Prior to the training and classification process, the LSTM network architecture is built using Uni- and Bi-directional structures to utilize both the forward and backward chains of data sequences. At the end, the developed algorithm performance is evaluated and a complete performance summary table is provided relative to other State-of-the-Art deep learning studies. The performance of this study is evaluated initially without the merging of S3 and S4 sleep stages following the R & K manual, which is considered challenging due to the minor differences between the signals. Then, the performance is evaluated following the recent American Academy of Sleep Medicine (AASM) scoring manual with the merging of the two stages as N3. The developed algorithm achieved higher results using the Bi-directional LSTM. In addition, it achieved the highest accuracy among all other studies in the field with 97.28 % . Furthermore, Cohen's kappa and F1-score were more than 72 % on average between all sleep stages. According to the confusion matrix, the algorithm successfully classified sleep signals with an overall True Positives percentage of 91.92 % . The performance of the algorithm improved following the AASM manual, where the Cohen's kappa value increased from 72.55 % to 77.73 % . The developed algorithm showed potential in automatic sleep stage classification. Future works include further enhancements on the LSTM algorithm to achieve higher levels of performance.

A Clinically Applicable Interactive Micro and Macro-Sleep Staging Algorithm for Elderly and Patients with Neurodegeneration.

Elderly and patients with neurodegenerative diseases (NDD) often complain about sleep problems and show altered sleep structure. Automated algorithms for efficient and specific sleep staging are needed. We propose a new algorithm using only one electroencephalographic and two electrooculographic channels to score wakefulness, rapid eye movement (REM) sleep and non-REM sleep in a cohort of elderly healthy controls (HC), patients with Parkinson's disease (PD), isolated REM sleep behavior disorder (iRBD), considered the prodromal stage of PD, and patients with PD and RBD (PD+RBD). The proposed method scores both standard 30-s epochs (macro-staging) and 5-s mini-epochs (micro-staging), whose evaluation may help to better understand sleep micro-structure. Moreover, the algorithm is interactive, as it labels the classified sleep epochs as either certain or uncertain, so that experts can manually review the uncertain ones. The algorithm performances were evaluated for macro-sleep staging, where it achieved overall accuracies of 0.87±0.05 in 41 HC, 0.86±0.10 in 57 PD, 0.76±0.10 in 31 iRBD and 0.77±0.10 in 30 PD+RBD patients when all 30-s epochs were considered. The accuracies increased to 0.91±0.05, 0.90±0.08, 0.85±0.09, 0.88±0.08 respectively when considering only the certain ones. The epochs labeled as uncertain were 9.95±4.15%, 11.13±7.86%, 18.39±7.38% and 18.90±8.00% in HC, PD, iRBD and PD+RBD respectively. The proposed interactive micro and macro sleep staging algorithm can be used in clinics to reduce the burden of manual sleep staging in elderly and patients with NDD.

SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach.

Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at https://github.com/SajadMo/SleepEEGNet.

Automatic Sleep Staging Employing Convolutional Neural Networks and Cortical Connectivity Images

Understanding of the neuroscientific sleep mechanisms is associated with mental/cognitive and physical well-being and pathological conditions. A prerequisite for further analysis is the identification of the sleep macroarchitecture through manual sleep staging. Several computer-based approaches have been proposed to extract time and/or frequency-domain features with accuracy ranging from 80% to 95% compared with the golden standard of manual staging. However, their acceptability by the medical community is still suboptimal. Recently, utilizing deep learning methodologies increased the research interest in computer-assisted recognition of sleep stages. Aiming to enhance the arsenal of automatic sleep staging, we propose a novel classification framework based on convolutional neural networks. These receive as input synchronizations features derived from cortical interactions within various electroencephalographic rhythms (delta, theta, alpha, and beta) for specific cortical regions which are critical for the sleep deepening. These functional connectivity metrics are then processed as multidimensional images. We also propose to augment the small portion of sleep onset (N1 stage) through the Synthetic Minority Oversampling Technique in order to deal with the great difference in its duration when compared with the remaining sleep stages. Our results (99.85%) indicate the flexibility of deep learning techniques to learn sleep-related neurophysiological patterns.

Pediatric Sleep Stage Classification Using Multi-Domain Hybrid Neural Networks

Sleep staging is an important part of clinical neurology. However, it is still performed manually by technical experts and is labor-intensive and time-consuming. To overcome these obstacles in the manual sleep staging process, a large number of machine learning-based classifiers with hand-engineered features have been proposed. Additionally, combinations of a deep neural network (DNN) have been recently highlighted as the state-of-the-art classifiers in view of their effectiveness for automatic sleep staging. In spite of the existence of a large number of these types of classifiers, to-this-date, no prior DNN-based approach has attempted sleep-stage classification using pediatric electroencephalographic (EEG) signals. In this paper, we propose a novel end-to-end classifier based on a multi-domain hybrid neural network (HNN-multi) approach consisting of a convolutional neural network and bidirectional long short-term memory for automatic sleep staging with pediatric scalp EEG recordings. To find effective temporal, spatial, and domain-specific conditions, we investigated noticeable changes in the classification performance corresponding to: 1) the length of input signals; 2) the number of channels; and 3) the types of input signals in the time and frequency domains. Our HNN-based classifier yielded the best performance metrics using 30-s time series in combination with an instantaneous frequency using a 19-channel, three-stage classification, with overall accuracy, F1 score, and Cohen’s Kappa, equal to 92.21%, 0.90, and 0.88, respectively. We suggest that an effective combination of temporal and spatial time-domain clues with time-varying frequency domain information plays a pivotal role in pediatric, automatic sleep staging. Sufficiently reasonable performance of our HNN-based approach coping with the highly complicated pediatric EEG signatures hopefully sheds light on the clinical feasibility of the DNN-based automatic sleep staging for pediatric neurology.

A Multi-Class Automatic Sleep Staging Method Based on Long Short-Term Memory Network Using Single-Lead Electrocardiogram Signals

To overcome the disadvantage of clinical manual sleep staging, a convenient, economical, and efficient multi-class automatic sleep staging method is proposed based on long short-term memory network (LSTM) using single-lead electrocardiogram signals. From electrocardiogram signals, heart rate variability and respiratory signals were calculated, and, then, totally 25 features were extracted. Four different classifiers, including the two-class classifier to distinguish between wake and sleep, the three-class classifier to distinguish wake, non-rapid eye movement sleep, and rapid eye movement, the four-class classifier to distinguish wake, light sleep, slow wave sleep, and rapid eye movement, and the five-class classifier to distinguish wake, sleep stage N1, sleep stage N2, sleep stage N3, and rapid eye movement, were constructed using the LSTM. The single-lead electrocardiogram data from 238 patients with full sleep stages during sleep were used for the training set and the data from other 60 patients were regarded as a validation set. The rest of 75 patients have left aside for testing set. The accuracy of two-class, three-class, four-class, and five-class sleep staging was 89.84%, 84.07%, 77.76%, and 71.16% and the Cohen’s kappa statistic $k$ was 0.52, 0.58, 0.55, and 0.52, respectively, which realized the moderate agreement with clinical analysis. When expanding the dataset to extra 1068 patients with missing sleep stages, the accuracy has no obvious reduction but the Cohen’s kappa statistic $k$ dropped to 0.51, 0.52, 0.48, and 0.43, respectively. The proposed method, in this paper, is promising for low-cost, efficient, and convenient sleep staging in home care monitoring.

A New Fully Automated Random-Forest Algorithm for Sleep Staging.

Rapid eye movement (REM) sleep behavior disorder is considered the prodromal stage of alpha-synucleinopathies. Its diagnosis requires careful detection of REM sleep and the gold standard manual sleep staging is inconsistent and expensive. This work proposes a new automatic sleep staging model to add robust automation to such applications, using only electroencephalography (EEG) and electrooculography (EOG) recordings. The publicly available ISRUC-Sleep database was used to optimize the design of the proposed model. The model was trained and tested on subgroup-I consisting of 100 subjects with evidence of having different sleep disorders and the polysomnographic data were manually scored by two individual experts. We divided the EOG and EEG recordings in overlapping moving 33-s epochs with step of 3s and for each of them we computed several time and frequency-domain features. The features were used to train a random forest classifier that was able to label each 33-s epoch with the probabilities of being wakefulness, REM and non-REM. The mean of the probability values of ten 33-s epochs were calculated, and the sleep stage with the highest probability was chosen to classify a 30-s epoch and matched with the manual staged hypnogram. The performance of the model was tested using 20-fold cross validation scheme. When the epochs where the scorers agreed were used, the classification achieved an overall accuracy of 92.6% and a Cohen's kappa of 0.856. Future validation on RBD patients is needed, but these performances are promising as first step of development of an automated diagnosis of RBD.

Achieving Accurate Automatic Sleep Staging on Manually Pre-processed EEG Data Through Synchronization Feature Extraction and Graph Metrics.

Sleep staging, the process of assigning labels to epochs of sleep, depending on the stage of sleep they belong, is an arduous, time consuming and error prone process as the initial recordings are quite often polluted by noise from different sources. To properly analyze such data and extract clinical knowledge, noise components must be removed or alleviated. In this paper a pre-processing and subsequent sleep staging pipeline for the sleep analysis of electroencephalographic signals is described. Two novel methods of functional connectivity estimation (Synchronization Likelihood/SL and Relative Wavelet Entropy/RWE) are comparatively investigated for automatic sleep staging through manually pre-processed electroencephalographic recordings. A multi-step process that renders signals suitable for further analysis is initially described. Then, two methods that rely on extracting synchronization features from electroencephalographic recordings to achieve computerized sleep staging are proposed, based on bivariate features which provide a functional overview of the brain network, contrary to most proposed methods that rely on extracting univariate time and frequency features. Annotation of sleep epochs is achieved through the presented feature extraction methods by training classifiers, which are in turn able to accurately classify new epochs. Analysis of data from sleep experiments on a randomized, controlled bed-rest study, which was organized by the European Space Agency and was conducted in the “ENVIHAB” facility of the Institute of Aerospace Medicine at the German Aerospace Center (DLR) in Cologne, Germany attains high accuracy rates, over 90% based on ground truth that resulted from manual sleep staging by two experienced sleep experts. Therefore, it can be concluded that the above feature extraction methods are suitable for semi-automatic sleep staging.

Assessing competency of Z3Score automated sleep stage scoring system with manual sleep stage scoring by multiple scorers

Assessing competency of Z3Score automated sleep stage scoring system with manual sleep stage scoring by multiple scorers

P 110 Manual sleep staging and coupling analysis in combined EEG and MEG sleep recordings

The study of sleep disorders is best done in a clinical sleep laboratory by polysomnography (PSG), which allows to record all physiological signals necessary to determine sleep macrostructure (sleep stages), sleep microstructure (arousal), as well as related behavior of cardio-respiratory parameters. PSG was extended by 125-channel-magnetoencephalography (MEG) running at the same time. A MEG laboratory consists of a magnetically shielded room (MSR) as MEG requires very low ambient magnetic fields in the range of pT and subjects slept for 3–4 h starting around midnight in the MEG laboratory. The PSG recordings were first analyzed manually to identify sleep stages. In a second step, common spectral properties of EEG and MEG were investigated using measures such as the time-frequency evolution across the scalp. Manual sleep staging served as input to the spectral analysis. Results show both combined and independent patterns in EEG and MEG demonstrating the potential of combined recordings in researching local brain activity during sleep.

Inter-scorer reliability of sleep assessment using EEG and EOG recording system in comparison to polysomnography

There are increasing needs for self-applicable methods assessing sleep in clinical and non-clinical settings. This study aimed to investigate the inter-scorer reliability for the sleep stage scoring and for the sleep variable assessments in the portable electroencephalography (EEG) and electro-oculography (EOG) recording system. Sleep recordings were performed simultaneously with polysomnography (PSG) and portable EEG/EOG recordings in 14 healthy adults. The inter-scorer concordance of the sleep stage scoring was assessed in the two recording methods. Sleep variables were compared between the two methods using the Bland–Altman plots in each scorer. The overall inter-scorer concordance rate of sleep stage scoring for the EEG/EOG data was 85.5 %, and the Cohen’s κ was 0.80 (p < 0.001), being equivalent to those for the PSG data (89.2 %, 0.85, p < 0.001) while that for StageN1 was relatively low (EEG/EOG 60.1 %, PSG 71.7 %). In both scorers, Bland–Altman plots showed that the mean difference between sleep variables obtained from the two systems was within the acceptable range although the inter-class correlations between the two systems were lower for StageN2 or StageR in either scorer. Although the results suggest that the sufficient inter-scorer reliability can be obtained with the EEG/EOG recording system based on manual sleep stage scoring in healthy young adults, the nature of the EEG/EOG recording system can influence the precisions in manually assessing sleep architectures in comparison to PSG.

Sleep Stage Classification Using EEG Signal Analysis: A Comprehensive Survey and New Investigation

Sleep specialists often conduct manual sleep stage scoring by visually inspecting the patient’s neurophysiological signals collected at sleep labs. This is, generally, a very difficult, tedious and time-consuming task. The limitations of manual sleep stage scoring have escalated the demand for developing Automatic Sleep Stage Classification (ASSC) systems. Sleep stage classification refers to identifying the various stages of sleep and is a critical step in an effort to assist physicians in the diagnosis and treatment of related sleep disorders. The aim of this paper is to survey the progress and challenges in various existing Electroencephalogram (EEG) signal-based methods used for sleep stage identification at each phase; including pre-processing, feature extraction and classification; in an attempt to find the research gaps and possibly introduce a reasonable solution. Many of the prior and current related studies use multiple EEG channels, and are based on 30 s or 20 s epoch lengths which affect the feasibility and speed of ASSC for real-time applications. Thus, in this paper, we also present a novel and efficient technique that can be implemented in an embedded hardware device to identify sleep stages using new statistical features applied to 10 s epochs of single-channel EEG signals. In this study, the PhysioNet Sleep European Data Format (EDF) Database was used. The proposed methodology achieves an average classification sensitivity, specificity and accuracy of 89.06%, 98.61% and 93.13%, respectively, when the decision tree classifier is applied. Finally, our new method is compared with those in recently published studies, which reiterates the high classification accuracy performance.

Detecting slow wave sleep using a single EEG signal channel

BackgroundIn addition to the cost and complexity of processing multiple signal channels, manual sleep staging is also tedious, time consuming, and error-prone. The aim of this paper is to propose an automatic slow wave sleep (SWS) detection method that uses only one channel of the electroencephalography (EEG) signal. New MethodThe proposed approach distinguishes itself from previous automatic sleep staging methods by using three specially designed feature groups. The first feature group characterizes the waveform pattern of the EEG signal. The remaining two feature groups are developed to resolve the difficulties caused by interpersonal EEG signal differences. Results and comparison with existing methodsThe proposed approach was tested with 1,003 subjects, and the SWS detection results show kappa coefficient at 0.66, an accuracy level of 0.973, a sensitivity score of 0.644 and a positive predictive value of 0.709. By excluding sleep apnea patients and persons whose age is older than 55, the SWS detection results improved to kappa coefficient, 0.76; accuracy, 0.963; sensitivity, 0.758; and positive predictive value, 0.812. ConclusionsWith newly developed signal features, this study proposed and tested a single-channel EEG-based SWS detection method. The effectiveness of the proposed approach was demonstrated by applying it to detect the SWS of 1003 subjects. Our test results show that a low SWS ratio and sleep apnea can degrade the performance of SWS detection. The results also show that a large and accurately staged sleep dataset is of great importance when developing automatic sleep staging methods.

Symbolic Fusion: A Novel Decision Support Algorithm for Sleep Staging Application

With the rapid extension of clinical data and knowledge, decision making becomes a complex task for manual sleep staging. In this process, there is a need for integrating and analyzing information from heterogeneous data sources with high accuracy. This paper proposes a novel decision support algorithm—Symbolic Fusion for sleep staging application. The proposed algorithm provides high accuracy by combining data from heterogeneous sources, like EEG, EOG and EMG. This algorithm is developed for implementation in portable embedded systems for automatic sleep staging at low complexity and cost. The proposed algorithm proved to be an efficient design support method and achieved up to 76% overall agreement rate on our database of 12 patients.

Coherence Validation of Alternative Sleep EEG Electrode Placements Using Wavelet Transform

Recent studies on automated sleep stage classification have started to adopt alternative sleep encephalography (EEG) electrode placements on the forehead as opposed to the traditional C3-C4 placement. The current study determines the validity of adopting the prefrontal EEG electrode placement. First, EEG signals were decomposed into four harmonic bands using the discrete wavelet transform and their power spectrum densities were extracted for comparison. The correlation coefficients of both signals were calculated and jackknifed to determine an unbiased statistical value. The signal and its power spectrum displayed moderate to very strong values of the correlation coefficient, respectively, with minute standard errors and biases. A strong coherence is exhibited between both electrode placements as viewed from the power spectra of different sleep stages. The magnitude-squared coherence values indicate that the reduction in the coefficient values for the beta band was due to a low correlation in a certain frequency band. Manual sleep stage classification was also conducted by a sleep technician and sleep stage classification software, with consistent results obtained. Sleep stage scoring using both methods indicated substantial agreement for the standard and alternative electrode placements. In conclusion, this work shows a strong coherence for the prefrontal and standard electrode placements and corroborates the hypothesis of using the alternative placements for performing quick, convenient, and efficient measurement and analysis of EEG signals.

A Computerized Algorithm for Arousal Detection in Healthy Adults and Patients With Parkinson Disease

Arousals occur from all sleep stages and can be identified as abrupt electroencephalogram (EEG) and electromyogram (EMG) changes. Manual scoring of arousals is time consuming with low interscore agreement. The aim of this study was to design an arousal detection algorithm capable of detecting arousals from non-rapid eye movement (REM) and REM sleep, independent of the subject's age and disease. The proposed algorithm uses features from EEG, EMG, and the manual sleep stage scoring as input to a feed-forward artificial neural network (ANN). The performance of the algorithm has been assessed using polysomnographic (PSG) recordings from a total of 24 subjects. Eight of the subjects were diagnosed with Parkinson disease (PD) and the rest (16) were healthy adults in various ages. The performance of the algorithm was validated in 3 settings: testing on the 8 patients with PD using the leave-one-out method, testing on the 16 healthy adults using the leave-one-out method, and finally testing on all 24 subjects using a 4-fold crossvalidation. For these 3 validations, the sensitivities were 89.8%, 90.3%, and 89.4%, and the positive predictive values (PPVs) were 88.8%, 89.4%, and 86.1%. These results are high compared with those of previously presented arousal detection algorithms and especially compared with the high interscore variability of manual scorings.

Performance of the frequency domain indices with respect to sleep staging

ObjectiveTo compare computerized staging using spectral analyses of various electrophysiological signals with manual sleep staging. MethodsSleep recordings from 21 normal subjects were scored by an experienced rater and by a dichotomous algorithm. The performance of the spectral indices was assessed by the largest kappa value (LKV). ResultsTheta/beta power ratio of the electroencephalogram, high frequency power (8–58Hz) of the electromyogram (PEMG), mean R–R interval, and total power (0–16Hz) of the body acceleration (PACCE) had high (>0.5) LKVs when differentiating between waking and sleep. To differentiate sleep with (stage 2 and slow wave sleep) and without (rapid eye movement and stage 1 sleep) spindles, sigma/beta power ratio had high LKVs. PEMG had a medium (>0.25) LKV to separate rapid eye movement from stage 1 sleep whereas delta/beta power ratio had a high LKV to separate stage 2 and slow wave sleep. ConclusionThe frequency components of electroencephalogram perform well in identifying sleep, sleep with spindles, and slow wave sleep. Electromyogram, heart rate, and body acceleration offer high agreement only when differentiating between wakefulness and sleep. SignificanceThe human–machine agreement is acceptable with spectral parameters, but heart rate and body acceleration still cannot substitute for electroencephalogram.

Artificial Neural Network and Wavelet Based Automated Detection of Sleep Spindles, REM Sleep and Wake States

Backpropagation artificial neural network (ANN) has been designed to classify sleep-wake stages. Four hours continuous three channel polygraphic signals such as EEG (electroencephalogram), EOG (electrooculogram) and EMG (electromyogram) from conscious subjects were digitally recorded and stored in computer. EOG and EMG signals were used for manual identification of sleep states before training and testing of ANN. The percentages power of the 2 s epochs of the digitized EEG signals from each of three sleep-wake patterns, sleep spindles (SS), rapid eye movement (REM) sleep and awake (AWA) sates, were calculated and analyzed to select the manually confirmed sleep-wake states for each epoch. Further, second order Daubechies mother wavelet has been used to get the wavelet coefficients for the selected EEG epochs. The wavelet coefficients for the EEG epochs (64 data) were selected as inputs for the training the network and to classify SS, REM sleep and AWA stages. The ANN architecture used (64-14-3) in present study shows overall very good agreement with manual sleep stage scoring with an average of 95.35% for all the 1,140 samples tested from SS, REM and AWA stages. This architecture of ANN was also found effectively differentiating the EEG power spectra from different sleep-wake states (96.84% in SS, 93.68% in REM sleep, 95.52% in AWA state). The high performance observed with the system based on wavelet coefficients along with the ANN, highlights the need of this computational tool into the field of sleep research.