Investigation of an Automatic Sleep Stage Classification by Means of Multiscorer Hypnogram

Helland, V. C. Figueroa; Gapelyuk, Andrej; Suhrbier, Alexander; Riedl, Maik; Penzel, Thomas; Kurths, Jürgen; Wessel, Niels

doi:10.3414/me09-02-0052

Cited by 33 publications

(13 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On our database, overall 76% AR is achieved for symbolic fusion, which is better in comparison to other decision support algorithms, as reported in [10,18,19]. It proved to be an effective method in comparison to decision tree method, which has AR up to 70% [10].…”

Section: Resultssupporting

confidence: 61%

See 1 more Smart Citation

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

Chen¹,

Xue²,

Ugon³

et al. 2015

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

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.

show abstract

Section: Resultssupporting

confidence: 61%

“…It proved to be an effective method in comparison to decision tree method, which has AR up to 70% [10]. In [18], authors reported 61% AR by using Linear Discriminant Analysis. In [19], authors reported AR of 55.88%, by using K-Nearest Neighbor method.…”

Section: Resultsmentioning

confidence: 99%

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

Chen¹,

Xue²,

Ugon³

et al. 2015

EAI Endorsed Trans Perv Health Tech

View full text Add to dashboard Cite

show abstract

“…The advent of computers in the second half of the twentieth century and the rapid increase in their capabilities led to the realization of numerous studies on methods of automatic analysis of sleep and its stages. The two main aspects of the implemented approaches are [23] : (a) most of the work performed signal characteristic extraction by frequency analysis and frequency over time using discrete wavelet transform (DWT), Huang Hilbert transform (HHT), and fast Fourier transform (FFT) [24][25][26][27] , and (b) different parametric and non-parametric methods have been applied in the classification of sleep events and stages, including random forest classifiers, artificial neural networks (ANN), fuzzy logic, nearest neighbor, linear discriminant analysis (LDA), support vector machines (SVM) and kernel logistic regression (KLR) [28][29][30][31][32][33][34][35][36] .…”

Section: Automatic Sleep Stagingmentioning

confidence: 99%

A knowledge model for the development of a framework for hypnogram construction

Fernández-Leal

Cabrero-Canosa

Mosqueira-Rey

et al. 2017

Knowledge-Based Systems

View full text Add to dashboard Cite

We describe a proposal of a knowledge model for the development of a framework for hypnogram construction from intelligent analysis of pulmonology and electrophysiological signals. Throughout the twentieth century, after the development of electroencephalography (EEG) by Hans Berger, there have been multiple studies on human sleep and its structure. Polysomnography (PSG), a sleep study from several biophysiological variables, gives us the hypnogram, a graphic representation of the stages of sleep as a function of time. This graph, when analyzed in conjunction with other physiological parameters, such as the heart rate or the amount of oxygen in arterial blood, has become a valuable diagnostic tool for different clinical problems that can occur during sleep and that often cause poor quality sleep. Currently, the gold standard for the detection of sleep events and for the correct classification of sleep stages are the rules published by the American Academy of Sleep Medicine (AASM), version 2.2. Based on the standards available to date, different studies on methods of automatic analysis of sleep and its stages have been developed but because of the different development and validation procedures used in existing methods, a rigorous and useful comparative analysis of results and their ability to correctly classify sleep stages is not possible. In this sense, we propose an approach that ensures that sleep stage classification task is not affected by the method for extracting PSG features and events. This approach is based on the development of a knowledge-intensive base system (KBS) for classifying sleep stages and building the corresponding hypnogram. For this development we used the CommonKADS methodology, that has become a de facto standard for the development of KBSs. As a result, we present a new knowledge model that can be used for the subsequent development of an intelligent system for hypnogram construction that allows us to isolate the process of signal processing to identify sleep stages so that the hypnograms obtained become comparable, independently of the signal analysis techniques.

show abstract

“…Scoring of S-W epochs into four or five categories has been used by various automated scoring systems (67,83) and in several other laboratories (12,63). Raw hypnograms were smoothed, i.e., every 32-s period was assigned to the dominant S-W stage (26). Analysis of rebound sleep.…”

Section: Treatmentsmentioning

confidence: 99%

Sleep loss and recovery after administration of drugs related to different arousal systems in rats

Hajnik¹,

Tóth²,

Szalontai³

et al. 2016

Physiology International

View full text Add to dashboard Cite

Sleep is homeostatically regulated suggesting a restorative function. Sleep deprivation is compensated by an increase in length and intensity of sleep. In this study, suppression of sleep was induced pharmacologically by drugs related to different arousal systems. All drugs caused non-rapid eye movement (NREM) sleep loss followed by different compensatory processes. Apomorphine caused a strong suppression of sleep followed by an intense recovery. In the case of fluoxetine and eserine, recovery of NREM sleep was completed by the end of the light phase due to the biphasic pattern demonstrated for these drugs first in the present experiments. Yohimbine caused a long-lasting suppression of NREM sleep, indicating that either the noradrenergic system has the utmost strength among the examined systems, or that restorative functions occurring normally during NREM sleep were not blocked. Arousal systems are involved in the regulation of various wakefulness-related functions, such as locomotion and food intake. Therefore, it can be hypothesized that activation of the different systems results in qualitatively different waking states which might affect subsequent sleep differently. These differences might give some insight into the homeostatic function of sleep in which the dopaminergic and noradrenergic systems may play a more important role than previously suggested.

show abstract

Investigation of an Automatic Sleep Stage Classification by Means of Multiscorer Hypnogram

Cited by 33 publications

References 20 publications

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

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

A knowledge model for the development of a framework for hypnogram construction

Sleep loss and recovery after administration of drugs related to different arousal systems in rats

Contact Info

Product

Resources

About