Edson Estrada

Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients

Currently in the world there is an alarming number of people who suffer from sleep disorders. A number of biomedical signals, such as EEG, EMG, ECG and EOG are used in sleep labs among others for diagnosis and treatment of sleep related disorders. The usual method for sleep stage classification is visual inspection by a sleep specialist. This is a very time consuming and laborious exercise. Automatic sleep stage classification can facilitate this process. The definition of sleep stages and the sleep literature show that EEG signals are similar in Stage1 of non-rapid eye movement (NREM) sleep and rapid eye movement (REM) sleep. Therefore, in this work an attempt was made to classify four sleep stages consisting of Awake, Stage1 + REM, Stage 2 and Slow Wave Stage based on the EEG signal alone. Wavelet packet coefficients and artificial neural networks were deployed for this purpose. Seven all night recordings from Physionet database were used in the study. The results demonstrated that these four sleep stages could be automatically discriminated from each other with a specificity of 94.4 ± 4.5%, a of sensitivity 84.2+3.9% and an accuracy of 93.0 ± 4.0%.

Wavelet-based EEG denoising for automatic sleep stage classification

In automatic sleep stage classification, as in any other signal processing task involving the easily contaminated EEG signals, denoising constitutes a crucial pre-processing step that must be addressed before carrying out further analysis on the EEG signals. Discrete wavelet transform offers an effective solution for denoising nonstationary signals such as EEG due to its shrinkage property. In this paper, we explored the application of wavelet denoising method to EEG signals acquired during different sleep stages classified according to the RK rules, with the objective to identify suitable thresholding rules and threshold values. Preliminary results showed that the combination of soft thresholding rule applied to the Detailed wavelet coefficients with the Universal threshold value produced better performance measures such as a smaller Minimum Squared Error (MSE) and a larger signal-to-Noise Ratio (SNR). Similarly improved results were obtained for Stage 1, Stage 2, Stage 3, Stage 4 and REM stage EEG signals using this combination. Such thresholding rule and values are equally well applicable to denoising EEG epochs acquired from deep sleep stages.

Itakura Distance: A Useful Similarity Measure between EEG and EOG Signals in Computer-aided Classification of Sleep Stages

Sleep is a natural periodic state of rest for the body, in which the eyes usually close and consciousness is completely or partially lost. Consequently, there is a decrease in bodily movements and responsiveness to external stimuli. Slow wave sleep is of immense interest as it is the most restorative sleep stage during which the body recovers from weariness. During this sleep stage, electroencephalographic (EEG) and electro-oculographic (EOG) signals interfere with each other and they share a temporal similarity. In this investigation we used the EEG and EOG signals acquired from 10 patients undergoing overnight polysomnography with their sleep stages determined by certified sleep specialists based on RK rules. In this pilot study, we performed spectral estimation of EEG signals by autoregressive (AR) modeling, and then used Itakura distance to measure the degree of similarity between EEG and EOG signals. We finally calculated the statistics of the results and displayed them in an easy to visualize fashion to observe tendencies for each sleep stage. We found that Itakura distance is the smallest for sleep stages 3 and 4. We intend to deploy this feature as an important element in automatic classification of sleep stages

EOG and EMG: two important switches in automatic sleep stage classification.

Sleep is a natural periodic state of rest for the body, in which the eyes are usually closed and consciousness is completely or partially lost. In this investigation we used the EOG and EMG signals acquired from 10 patients undergoing overnight polysomnography with their sleep stages determined by expert sleep specialists based on RK rules. Differentiation between Stage 1, Awake and REM stages challenged a well trained neural network classifier to distinguish between classes when only EEG-derived signal features were used. To meet this challenge and improve the classification rate, extra features extracted from EOG and EMG signals were fed to the classifier. In this study, two simple feature extraction algorithms were applied to EOG and EMG signals. The statistics of the results were calculated and displayed in an easy to visualize fashion to observe tendencies for each sleep stage. Inclusion of these features show a great promise to improve the classification rate towards the target rate of 100%

EEG and HRV signal features for automatic sleep staging and apnea detection

Sleep is a circadian rhythm essential for human life. Many events occur in the body during this state. In the past, significant efforts have been made to provide clinicians with reliable and less intrusive tools to automatically classify the sleep stages and detect apnea events. A few systems are available in the market to accomplish this task. However, sleep specialists may not have full confidence and trust in such systems due to issues related to their accuracy, sensitivity and specificity. The main objective of this work is to explore possible relationships among sleep stages and apneic events and improve on the accuracy of algorithms for sleep classification and apnea detection. Electroencephalogram (EEG) and Heart Rate Variability (HRV) will be assessed using advanced signal processing approaches such as Detrend Fluctuation Analysis (DFA). In this paper, we present a compendium of features extracted from EEG and Heart Rate Variability (HRV) data acquired from twenty five patients (21 males and 4 females) suffering from sleep apnea (age: 50 ± 10 years, range 28–68 years undergoing polysomnography). Polysomnographic data were available online from the Physionet database. Results show that trends detected by these features could distinguish between different sleep stages at a very significant level (p≪0.01). These features could prove helpful in computer-aided detection of sleep apnea.

EEG signal features for computer-aided sleep stage detection

Sleep apnea is a disorder in which individuals stop breathing during their sleep. Sleep apnea is categorized as obstructive, central or mixed. New techniques for sleep stage classification are being developed by bioengineers and clinicians for appropriate and timely detection of sleep disorders. The material presented in this work, includes a compendium of features extracted from the sleep studies of patients suffering from sleep apnea. Twenty-five subjects (21 males and 4 females) were selected (age: 50 ± 10 years, range 28–68 years, data was available online at the physionet database. Time and frequency domain algorithms were applied to polysomnographic signals such as EEG, EMG, and EOG signals. Results show that trends provided by this indicators could be used to automatically distinguish between sleep stages at a highly significant level (p ≪ 0.01.) This could prove very helpful in sleep apnea detection.

Assessment of Itakura Distance as a Valuable Feature for Computer-aided Classification of Sleep Stages

Staging and detection of various states of sleep derived from EEG and other biomedical signals have proven to be very helpful in diagnosis, prognosis and remedy of various sleep related disorders. The time consuming and costly process of visual scoring of sleep stages by a specialist has always motivated researchers to develop an automatic sleep scoring system and the first step toward achieving this task is finding discriminating characteristics (or features) for each stage. A vast variety of these features and methods have been investigated in the sleep literature with different degrees of success. In this study, we investigated the performance of a newly introduced measure: the Itakura Distance (ID), as a similarity measure between EEG and EOG signals. This work demonstrated and further confirmed the outcomes of our previous research that the Itakura Distance serves as a valuable similarity measure to differentiate between different sleep stages.

Vibration training improves disability status in multiple sclerosis: A pretest-posttest pilot study

The purpose of this study was to examine the effects of an 8-week vibration training program on changing the disability level in people with multiple sclerosis (MS). Twenty-five adults with clinically-confirmed MS underwent an 8-week vibration training on a side-alternating vibration platform. The vibration frequency and peak-to-peak displacement were set at 20Hz and 2.6mm, respectively. Prior to and following the training course, the disability status was assessed for all participants characterized by the Patient Determined Disability Steps (PDDS) and MS Functional Composite (MSFC) scores. The training program significantly improved the PDDS (3.66±1.88 vs. 3.05±1.99, p=0.009) and the MSFC scores (0.00±0.62 vs 0.36±0.68, p<0.0001). All three MSFC components were improved: lower extremity function (9.37±4.92 vs. 8.13±4.08s, p=0.011), upper extremity function (dominant hand: 27.81±5.96 vs. 26.20±5.82s, p=0.053; non-dominant hand: 28.47±7.40 vs. 27.43±8.33s, p=0.059), and cognitive function (30.55±13.54 vs. 36.95±15.07 points, p=0.004). Our findings suggested that vibration training could be a promising alternative modality to reduce the disability level among people with MS.

Symmetric Itakura Distance as an EEG Signal Feature for Sleep Depth Determination

Sleep is a natural periodic state of rest for the body, in which the eyes are usually closed and consciousness is completely or partially lost. Consequently, there is a decrease in bodily movements and responsiveness to external stimuli. In this pilot study, we performed power spectral estimation of EEG signals by Autoregressive (AR) modeling, and then used Itakura Distance to measure the degree of similarity between an EEG baseline and EEG epochs for the entire sleep study. Sleep data from twenty-five subjects (21 males and 4 females, age: 50 ± 10 years, range 28–68 years) from Physionet database were used. We found that Itakura Distance was the smallest for sleep stages similar to the baseline. We intend to deploy this feature as an important element in automatic classification of sleep stages. Results show that trends provided by this feature could discern between sleep stages with a very high level of statistical significance p<0.01.Copyright

HRV and EEG Signal Features for Computer-Aided Detection of Sleep Apnea

Sleep apnea is a disorder in which individuals stop breathing during their sleep. Sleep apnea is categorized as obstructive, central or mixed. As an attempt to advance obstructive sleep apnea treatment, in recent years new techniques for sleep stage classification have been developed by biomedical engineers and clinicians for sensitive and timely detection of sleep disorders. In this paper, we present a compendium of features extracted from polysomnographic data acquired from twenty five patients (21 males and 4 females) suffering from sleep apnea (age: 50 ± 10 years, range 28-68 years). Sleep data were available online from the Physionet database. Time and frequency domain algorithms were applied to 3 biopotentials to extract features as follows: EEG (Hjorth Parameters, Harmonic Hjorth Parameters, Itakura Distance, Detrended Fluctuation Analysis, Relative Energy Band Percent, and Correlation Dimension), EMG (Energy Content), and EOG (Energy Content Band). Heart Rate Variability (HRV) signals were then derived from ECG signals using an Enhanced Hilbert Transform algorithm. Features extracted from the HRV signals were: R-R statistics (mean, standard deviation, maximum and minimum R-R values), detrended fluctuation analysis parameters, frequency components (LF, HF and LF/HF ratio) and approximate entropy. Results show that trends detected by these features could distinguish between different sleep stages at a highly significant level (p<0.01). These features could prove very helpful in computer-aided detection of sleep apnea.