Detection of Arousals in Patients with Respiratory Sleep Disorders Using a Single Channel EEG

Cho, S.P.; Lee, J.; Park, H.D.; Lee, K.J.

doi:10.1109/iembs.2005.1617036

Cited by 32 publications

(27 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensitivity and precision values vary on these studies (0.42-1.00 and 0.57-1.00, respectively) as well as it does the number of PSGs involved (from 2 to 8). Is to be remarked that, at least for the approximations of Zamora and Tarassenko [5], Pacheco and Vaz [3], and Cho et al [6], the validation was limited to partial preselected periods out of the total recording time. In the work of De Carli et al [4] the standard reference was obtained from the consensus of two human scorers and their own proposed method, which might bias the result.…”

Section: Inter-scorer Variability Reported In the Literaturementioning

confidence: 99%

Large-scale validation of an automatic EEG arousal detection algorithm using different heterogeneous databases

Álvarez-Estévez

Fernández-Varela

2019

Sleep Medicine

View full text Add to dashboard Cite

Objective: To assess the validity of an automatic EEG arousal detection algorithm using large patient samples and different heterogeneous databases Methods: Automatic scorings were confronted with results from human expert scorers on a total of 2768 full-night PSG recordings obtained from two different databases. Of them, 472 recordings were obtained during clinical routine at our sleep center, and were subdivided into two subgroups of 220 (HMC-S) and 252 (HMC-M) recordings each, attending to the procedure followed by the clinical expert during the visual review (semi-automatic or purely manual, respectively). In addition, 2296 recordings from the public SHHS-2 database were evaluated against the respective manual expert scorings. Results: Event-by-event epoch-based validation resulted in an overall Cohen's kappa agreement κ = 0.600 (HMC-S), 0.559 (HMC-M), and 0.573 (SHHS2). Estimated inter-scorer variability on the datasets was, respectively, κ = 0.594, 0.561 and 0.543. Analyses of the corresponding Arousal Index scores showed associated automatic-human repeatability indices ranging in 0.693-0.771 (HMC-S), 0.646-0.791 (HMC-M), and 0.759-0.791 (SHHS2).Conclusions: Large-scale validation of our automatic EEG arousal detector on different databases has shown robust performance and good generalization results comparable to the expected levels of human agreement. Special emphasis has been put on allowing reproducibility of the results and implementation of our method has been made accessible online as open source code.

show abstract

Section: Inter-scorer Variability Reported In the Literaturementioning

confidence: 99%

Large-scale validation of an automatic EEG arousal detection algorithm using different heterogeneous databases

Álvarez-Estévez

Fernández-Varela

2019

Sleep Medicine

View full text Add to dashboard Cite

show abstract

“…The classification was done using ANN,with weights updated using gradient descent rule. S. P. Cho et al [7] used single EEG channel time frequency features with SVM classifier and reported a sensitivity of 87.92% and specificity of 95.56 % for the training sets, and sensitivity of 75.26 % and specificity of 93.08 % for the testing sets but the results do not seem to be consistent across recordings and there is a large difference between recorded detection of positive and negative arousals. Not only this but the single channel approach is not useful for REM arousal detection as per AASM manual.…”

Section: Classification and Resultsmentioning

confidence: 99%

“…This task of visual recognition of Arousal events has some subjectivity embedded within it [5] and also a huge manual work associated which necessitates the need for objective automation. Some of the early works in this area [6] and [7] have used single channel EEGs to track the arousal events in sleep. But there is a simultaneous changes in all the channels during the time of arousal identification and when we consider only a single channel for the analysis, we miss out information from the signals of other channels.…”

Section: Introductionmentioning

confidence: 99%

Artificial neural network based arousal detection from sleep electroencephalogram data

Behera

Reddy

Behera

et al. 2014

2014 International Conference on Computer, Communications, and Control Technology (I4CT)

View full text Add to dashboard Cite

Electroencephalographic arousals are characterized by a sudden shift in electroencephalogram (EEG) frequency during sleep. Occurrence of arousals causes improper sleep which is the main reason of day-time sleepiness. The arousal during the sleep is detected by analyzing a multimodal multichannel Polysomnographic (PSG) recordings. It is a time consuming task to analyze the recording manually and requires a lot of patience. Hence automation of the process is required. This task becomes difficult because of the presence of a lot of events in time in relation to various bio-medical signals available through Polysomnographic (PSG) recordings. In this paper we present a method to detect the arousals in sleep automatically. Firstly two sets of electroencephalogram (EEG) channels C4/M1 and C3/M2 and an electromyogram (EMG) channel are chosen for preprocessing. Then the electroencephalogram (EEG) signals are passed through a bandpass filter of 8-30 Hz in order to extract the signal containing only the alpha and beta frequency components. The events are detected when the Power spectral density of this filtered signal crosses a threshold of zero. When an event is detected the relevant features from Alpha, Beta, Theta, Delta, and sigma waves are extracted. Similarly when electromyogram (EMG) signal crosses a threshold of zero events are detected and relevant features are extracted for the corresponding events. Now all these features are grouped together along with the corresponding labels and used as inputs to the Artificial Neural Network (ANN) Classifier to detect the presence of arousals. The novelty of this work relies on using both Hjorth and Power Spectral density difference spectrum features leading to improved accuracy than either of them alone. Considering 10 overnight sleep recordings We recorded an average sensitivity of 0.93262, average specificity of 0.91387, average precision of 0.91693 and average Area under Region of Convergence curve (AUC) of 0.92328 (showing a good measure of overall performance).

show abstract

“…Therefore, the 2018 PhysioNet/ Computing in Cardiology Challenge (henceforth referred to as "Challenge") seeks to detect non-apnea arousals during sleep using a variety of physiological signals collected during polysomnographic sleep studies [3]. A limited number of approaches for detecting sleep arousal using mainly electroencephalography (EEG), electrooculography (EOG), electromyography (EMG) and electrocardiology (EKG) already exists, such as applying wavelet analysis [4], time-frequency analysis and the support vector machine (SVM) classifier [5,6] for the automatic detection of arousals during sleep.…”

Section: Introductionmentioning

confidence: 99%

Effectiveness of a Convolutional Neural Network in Sleep Arousal Classification Using Multiple Physiological Signals

Shen¹

2018

2018 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

The 2018 PhysioNet Challenge utilizes 13 physiological signals collected during polysomnographic sleep studies to classify explicitly-defined arousal regions. The goal is to assign a probability of arousal at each sample for each test subject. Automatic detection of non-apnea arousals may help us better understand various causes of sleep disturbance and advance sleep arousal analysis. Neural networks possess powerful feature-learning abilities to gain insights from complex datasets. Our approach is based on a deep convolutional neural network (CNN), which we trained with normalization, pooling, activation and dropout techniques in Python using Keras on top of Tensorflow. The CNN was trained on 737 patients' sleep data and validated on 185 patients' sleep data. Our model obtained AUROC performance score of 0.514293+/-0.054509 and AUPRC performance score of 0.501947+/-0.063199. In this paper, we discuss the strengths and limitations of our CNN in sleep arousal classification using a variety of physiological signals. We also present some possible directions for future work.

show abstract

Detection of Arousals in Patients with Respiratory Sleep Disorders Using a Single Channel EEG

Cited by 32 publications

References 4 publications

Large-scale validation of an automatic EEG arousal detection algorithm using different heterogeneous databases

Large-scale validation of an automatic EEG arousal detection algorithm using different heterogeneous databases

Artificial neural network based arousal detection from sleep electroencephalogram data

Effectiveness of a Convolutional Neural Network in Sleep Arousal Classification Using Multiple Physiological Signals

Contact Info

Product

Resources

About