Presenting efficient features for automatic CAP detection in sleep EEG signals (original) (raw)
Related papers
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 F 1 -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 F 1 -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.
Automatic detection of a phases of the cyclic alternating pattern during sleep
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference, 2010
This study aimed to develop an automatic algorithm to detect the activation phases (A phases) of the Cyclic Alternating Pattern. The sleep EEG microstructure of 4 adult, healthy subjects was scored by a sleep medicine expert. Features were calculated from each of the six EEG bands (low delta, high delta, theta, alpha, sigma and beta), and three additional characteristics were computed: the Hjorth activity in the low delta and high delta bands, and the differential variance of the raw EEG signal. The correlation between couples of features was analyzed to find redundancies for the automatic analysis. The features were used to train an Artificial Neural Network to automatically find the A phases of CAP. The data were divided into training, validation and testing set, and the visual scoring provided by the clinician was used as the desired output. The statistics on the second by second classification show an average sensitivity equal to 76%, specificity equal to 83% and accuracy equal ...
EEG signal features for computer-aided sleep stage detection
… , 2009. NER'09. 4th …, 2009
Abstract 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 ...
Feature Extraction and Selection for Automatic Sleep Staging using EEG
2010
Sleep disorders affect a great percentage of the population. The diagnostic of these disorders is usually made by a polysomnography, requiring patient's hospitalization. Low cost ambulatory diagnostic devices can in certain cases be used, especially when there is no need of a full or rigorous sleep staging. In this paper, several methods to extract features from 6 EEG channels are described in order to evaluate their performance. The features are selected using the R-square Pearson correlation coefficient , providing this way a Bayesian classifier with the most discriminative features. The results demonstrate the effectiveness of the methods to discriminate several sleep stages, and ranks the several feature extraction methods. The best discrimination was achieved for relative spectral power, slow wave index, harmonic parameters and Hjorth parameters.
EEG feature extraction for classification of sleep stages
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2004
Automated sleep staging based on EEG signal analysis provides an important quantitative tool to assist neurologists and sleep specialists in the diagnosis and monitoring of sleep disorders as well as evaluation of treatment efficacy. A complete visual inspection of the EEG recordings acquired during nocturnal polysomnography is time consuming, expensive, and often subjective. Therefore, feature extraction is implemented as an essential preprocessing step to achieve significant data reduction and to determine informative measures for automatic sleep staging. However, the analysis of the EEG signal and extraction of sensitive measures from it has been a challenging task due to the complexity and variability of this signal. We present three different schemes to extract features from the EEG signal: relative spectral band energy, harmonic parameters, and Itakura distance. Spectral estimation is performed by using autoregressive (AR) modeling. We then compare the performance of these sch...
Clinical Neurophysiology, 2008
Automatic methods developed to detect transient EEG events during sleep may present a degree of arbitrariness in the choice of appropriate channels or amplitude thresholds for the analysis. To overcome these limitations, we propose a multi-channel and temporal coincidences approach. A two-step automatic detection (AD) of peculiar transient synchronized EEG events (TE) was performed in stage 2 and stage 3 sleep periods obtained from 10 normal sleep recordings and included: (a) detection of candidate TE from all the EEG traces and averaged signals, based on amplitude thresholds selections in both the time and frequency domains; (b) cross-checking of TE by evaluation of the coincidences in different EEG traces. TE found by AD but not confirmed by visual analysis (false positives, FP) and TE evidenced by visual analysis and missed by AD (false negatives, FN) were then counted. AD performed in averaged signals significantly reduced the number of FP but slightly increased FN, compared to single-channel analysis. However, when TE were confirmed by inter-channel temporal coincidences, a significant reduction of total errors (FN+FP) was achieved. The minimum error was obtained after C3-A2 and C4-A1 averaging and signal cross-checking with at least three channels (C3-A2 or C4-A1, plus both O1-A2 and O2-A1). This study describes a novel method for automatic detection of transient EEG events occurring during sleep that takes into account all the available channels. This approach reduces the need of human supervision and may overcome most of the difficulties encountered by automatic methods based on single-channel analysis.
Analysis and Detection of EEG Transient Waves During Sleep
ARS Medica Tomitana
Electroencephalogram (EEG) analysis consists of locating signal structtures in time and frequency. A detection method based on the Matching Pursuit Algorithms finds the suboptimal solution of the function optimal linear expansion over a redundant waveform dictionary. This paper has put forth a method for the automatic detection and analysis of transient waves during sleep based on the matching pursuit method with a real dictionary og Gabor functions. Each wave peak is described in terms of natural parameters. In this context, there have been confirmed several literature hypotheses regarding the spatial, temporal, and frequency distribution of transient waves during sleep, and their relationships with slow wave brain activity. Mastery and expertise in clinical EEG interpretation is one of the most desirable disgnostic clinical skills in interpreting seizures, epilepsy, sleep disorder, biomarkers for early disgnosis of Parkinson’s and Alzheimer’s disease, and other neurocognitive stud...
2021
A better consciousness depends on how well your sleep is. Study shows that, sleep disorder become a crucial problem day by day due to work pressure and other different causes. This continuous lack of sleep or uneven sleep pattern can cause to develop different major health issues in humans. These sleep patterns are difficult to detect, analyze, and experience as they exhibit at the time when people are in their deep sleep phase. This research work is focused on studying, methods for analyzing and identifying different sleep patterns based on EEG patterns. Every stage of sleep shows a different electroencephalogram pattern. These EEG patterns show that sleep can be observed as a combination of different cyclic sleep stages. This work shows different sleep stage patterns analysis found in different sleep disorders. Based on these patterns, monitoring of quality sleep can be performed. In this paper, authors have discussed 10-20 electrodes systems to capture brain signals, electroencephalogram signals, and its categorization. This study also represent the detailed description of several methods identified for monitoring sleep behavioural patterns in order to understand the experimental basis and forming a strong theoretical background towards analyzing these EEG signals.