scholarly journals 0434 Clinical Application of Computer Aided Cloud Sleep Scoring System

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A166-A167
Author(s):  
W Lin ◽  
P Kuo ◽  
M Liu ◽  
C Li ◽  
C Lin ◽  
...  
Keyword(s):  
Scoring System ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Onset Time ◽  
Fine Tuning ◽  
Physiological Signals ◽  
Sleep Stages ◽  
Sleep Scoring ◽  
Computer Aided ◽  
Sleep Centers

Abstract Introduction According to a survey by World Sleep Society, 45% of the population suffered from sleep disorders. The best way to diagnose these patients is to use Polysomnography (PSG), recording their physiological signals throughout the night. Mostly, sleep technologists manually score sleep stages. Manual scoring is quite subjective and time-consuming. Although the technologist’s judgments are based on scoring standards of the American Academy of Sleep Medicine, fine-tuning scoring results because of different considerations in different sleep centers may be happened. In order to assess the consistency of scoring standards in sleep technologists, we tried to establish a cloud sleep scoring system and evaluate its feasibility in 4 sleep centers in southern Taiwan. Methods We constructed a computer-aided cloud sleep scoring system. Each sleep technologist could score the same test data of PSG online without being restricted by places and hardware equipment. After comparing scoring results of all participants, the scoring system could provide the following reports, including an overall agreement, agreement of each sleep stage and each sleep index. Besides, multi-person scoring results of each epoch with displaying physiological signals were analyzed. Results Seven sleep technologists from 4 hospitals in Tainan, Taiwan joined this study. Standard deviations (SDs) of each sleep stage included 2.64 in Wake stage, 6.90 in N1, 8.31 in N2, 6.87 in N3, 1.38 in REM, respectively. SDs of sleep indexes were 2.64 in sleep efficiency, 2.14 in sleep onset time, 8.35 in wake after sleep onset time, 10.03 in total sleep time, individually. The overall agreement was 89.6%. The satisfaction of this scoring system operation was 85.7%. Conclusion With the cloud sleep scoring system assistance, it was feasible to evaluate the scoring consistency among sleep technologists in different sleep centers. Support This work is supported by the Ministry of Science and Technology, Taiwan. (MOST 108-2634-F-006-012)

scholarly journals 0441 An Automatic Sleep Scoring System Based on Ensemble Convolutional Neural Network and Spectrogram of Sleep Physiological Signal

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A169-A169
Author(s):  
C Kuo ◽  
G Chen
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Scoring System ◽  
Sleep Stage ◽  
Sleep Stages ◽  
Neural Network Ensemble ◽  
Sleep Scoring ◽  
Physiological Signal ◽  
Time Required ◽  
Sleep Stage Scoring

Abstract Introduction Manual sleep stage scoring is time consuming and subjective. Therefore, several studies focused on developing automated sleep scoring algorithms. The previously reported the automatic sleep scoring have been develop usually using small dataset, which less than 100 subjects. In this study, an automatic sleep scoring system based on ensemble convolutional neural network (ensemble-CNN) and spectrogram of sleep physiological signal was proposed and evaluated using a large dataset with sleep disorder. Methods The spectrograms were computed from each 30-s EEG and EOG of 994 subjects from PhysioNet 2018 challenge dataset, using the continuous wavelet transform, which were fed into an ensemble-CNN classification for training. The ensemble-CNN contained five pretrained models, ResNet-101, Inception-v4, DenseNet-201, Xception, and NASNet models, because these models’ architectures are different which can learn different features from the spectrograms to obtain high accuracy. The probabilities of five models were averaged to decide the sleep stage for each spectrogram. After classifying sleep stage, a smoothing process was used for sleep continuity. Moreover, the total 80% data from PhysioNet dataset were randomly assigned to the training set, and the remaining data were assigned to the testing set. Results To validate the robustness of the proposed system, the validation procedure was repeated five times. The performance measures were averaged over the five runs. The overall agreement and kappa coefficient of the proposed method are 82% and 0.73, respectively. The sensitivity of the sleep stages of Wake, N1, N2, N3, and REM are 90.0%, 48.6%, 84.9%, 84.2%, and 81.9%, respectively. Conclusion The performance of the proposed method was achieved expert level, and it was noted that the ensemble-CNN is a promising solution for automatic sleep stage scoring. This method can assist clinical staff in reducing the time required for sleep stage scoring in the future. Support This work was supported by the Ministry of Science and Technology, Taiwan. (MOST 106-2218-E-035-013-MY2, 108-2221-E-035-064, and 108-2634-F-006-012).

Sleep Stage Assessment Using Power Spectral Indices of Heart Rate Variability With a Simple Algorithm

2012 ◽  
Vol 15 (3) ◽  
pp. 264-272 ◽  
Author(s):  
Keiko Tanida ◽  
Masashi Shibata ◽  
Margaret M. Heitkemper
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Low Frequency ◽  
Simple Algorithm ◽  
Sleep Stages ◽  
Spectral Indices ◽  
Current Form ◽  
Power Spectral

Clinical researchers do not typically assess sleep with polysomnography (PSG) but rather with observation. However, methods relying on observation have limited reliability and are not suitable for assessing sleep depth and cycles. The purpose of this methodological study was to compare a sleep analysis method based on power spectral indices of heart rate variability (HRV) data to PSG. PSG and electrocardiography data were collected synchronously from 10 healthy women (ages 20–61 years) over 23 nights in a laboratory setting. HRV was analyzed for each 60-s epoch and calculated at 3 frequency band powers (very low frequency [VLF]-hi: 0.016–0.04 Hz; low frequency [LF]: 0.04–0.15 Hz; and high frequency [HF]: 0.15–0.4 Hz). Using HF/(VLF-hi + LF + HF) value, VLF-hi, and heart rate (HR) as indices, an algorithm to categorize sleep into 3 states (shallow sleep corresponding to Stages 1 & 2, deep sleep corresponding to Stages 3 & 4, and rapid eye movement [REM] sleep) was created. Movement epochs and time of sleep onset and wake-up were determined using VLF-hi and HR. The minute-by-minute agreement rate with the sleep stages as identified by PSG and HRV data ranged from 32 to 72% with an average of 56%. Longer wake after sleep onset (WASO) resulted in lower agreement rates. The mean differences between the 2 methods were 2 min for the time of sleep onset and 6 min for the time of wake-up. These results indicate that distinguishing WASO from shallow sleep segments is difficult using this HRV method. The algorithm's usefulness is thus limited in its current form, and it requires additional modification.

Utility of Activity Monitors and Thermometry in Assessing Sleep Stages and Sleep Quality

2018 ◽  
Vol 1 (3) ◽  
pp. 108-121
Author(s):  
Natashia Swalve ◽  
Brianna Harfmann ◽  
John Mitrzyk ◽  
Alexander H. K. Montoye
Keyword(s):  
Sleep Quality ◽  
Skin Temperature ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Sleep Efficiency ◽  
Sleep Stages ◽  
Sleep Onset Latency ◽  
Onset Latency ◽  
Activity Monitors ◽  
Research Grade

Activity monitors provide an inexpensive and convenient way to measure sleep, yet relatively few studies have been conducted to validate the use of these devices in examining measures of sleep quality or sleep stages and if other measures, such as thermometry, could inform their accuracy. The purpose of this study was to compare one research-grade and four consumer-grade activity monitors on measures of sleep quality (sleep efficiency, sleep onset latency, and wake after sleep onset) and sleep stages (awake, sleep, light, deep, REM) against an electroencephalography criterion. The use of a skin temperature device was also explored to ascertain whether skin temperature monitoring may provide additional data to increase the accuracy of sleep determination. Twenty adults stayed overnight in a sleep laboratory during which sleep was assessed using electroencephalography and compared to data concurrently collected by five activity monitors (research-grade: ActiGraph GT9X Link; consumer-grade: Fitbit Charge HR, Fitbit Flex, Jawbone UP4, Misfit Flash) and a skin temperature sensor (iButton). The majority of the consumer-grade devices overestimated total sleep time and sleep efficiency while underestimating sleep onset latency, wake after sleep onset, and number of awakenings during the night, with similar results being seen in the research-grade device. The Jawbone UP4 performed better than both the consumer- and research-grade devices, having high levels of agreement overall and in epoch-by-epoch sleep stage data. Changes in temperature were moderately correlated with sleep stages, suggesting that addition of skin temperature could increase the validity of activity monitors in sleep measurement.

scholarly journals 1205 Activity Trackers As A Tool In Sleep Research: Determining Discrepancies In Trackers Vs. PSG

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A460-A461
Author(s):  
E P Pollet ◽  
D P Pollet ◽  
B Long ◽  
A A Qutub
Keyword(s):  
Sleep Disorders ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Sleep Efficiency ◽  
Sleep Stages ◽  
Sleep Staging ◽  
Sleep Study ◽  
Activity Tracker ◽  
Activity Trackers ◽  
Large Populations

Abstract Introduction Fitness-based wearables and other emerging sensor technologies have the potential to track sleep across large populations longitudinally in at-home environments. To understand how these devices can inform research studies, limitations of available trackers need to be compared to traditional polysomnography (PSG). Here we assessed discrepancies in sleep staging in activity trackers vs. PSG in subjects with various sleep disorders. Methods Twelve subjects (age 41-78, 7f, 5m) wore a Fitbit Charge 3 while undergoing a scheduled sleep study. Six subjects had been previously diagnosed with a sleep disorder (5 OSA, 1 CSA). 4 subjects used CPAP throughout the night, 2 had a split night (CPAP 2nd half of the night), and 6 had a PSG only. Activity tracker staging was compared to 2 RPSGTs staging. Results Of the 12 subjects, eight subjects’ sleep was detected in the activity tracker, and compared across sleep stages to the PSG (7 female, 1 male, ages 41-78, AHI 0.3-87, RDI 0.5-94.4, sleep efficiency 74%+/-18, 4 PSG, 1 split, 3 CPAP). The activity tracker matched either tech 52% (+/- 13). The average difference in score tech and activity tracker staging for sleep onset (SO) was 16 +/- 15 minutes and wake after sleep onset was 43.5 +/- 44 minutes. Sensitivity, specificity, and balanced accuracy were found for each sleep stage. Respectively, Wake: 0.45+/-0.27, 0.97+/-0.03, 0.71+/-0.12, REM: 0.41+/-0.30, 0.90+/-0.06, 0.60+/-0.28, Light: 0.71+/-0.09, 0.58+/-0.19, 0.65+/-0.10, Deep: 0.63+/-0.52, 0.88+/-0.05, 0.59+/-0.49. Conclusion From this study of 12 subjects seen at a sleep clinic for suspected sleep disorders, activity trackers performed best in wake, REM and deep sleep specificity (>=88%), while they lacked sensitivity to REM and wake (<=45%) stages. The tracker did not detect sleep in 4 subjects who had elevated AHI or low sleep efficiency. Further analysis can identify whether discrepancies between the Fitbit and PSG can be predicted by distinct patterns in sleep staging and/or identify subject exclusion criteria for activity tracking studies. Support This project in on-going with the support of Academy Diagnostics Sleep and EEG Center and staff.

scholarly journals 0746 Dynamics of Sleep Stage Transitions in Patients with Narcolepsy and Other Hypersomnias

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A283-A284
Author(s):  
A Kishi ◽  
T Kitajima ◽  
R Kawai ◽  
M Hirose ◽  
N Iwata ◽  
...  
Keyword(s):  
Rem Sleep ◽  
Transition Probabilities ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Sleep Stages ◽  
Subsequent Stage ◽  
Dynamic Features ◽  
Survival Curves ◽  
Transition Analysis ◽  
Sleep Transition

Abstract Introduction Narcolepsy is a chronic sleep disorder characterized by excessive daytime sleepiness and abnormal REM sleep phenomena. Narcolepsy can be distinguished into type 1 (NT1; with cataplexy) and type 2 (NT2; without cataplexy). It has been reported that sleep stage sequences at sleep-onset as well as sleep-wake dynamics across the night may be useful in the differential diagnosis of hypersomnia. Here we studied dynamic features of sleep stage transitions during whole night sleep in patients with NT1, NT2, and other types of hypersomnia (o-HS). Methods Twenty patients with NT1, 14 patients with NT2, and 35 patients with o-HS underwent overnight PSG. Transition probabilities between sleep stages (wake, N1, N2, N3, and REM) and survival curves of continuous runs of each sleep stage were compared between groups. Transition-specific survival curves of continuous runs of each sleep stage, dependent on the subsequent stage of the transition, were also compared. Results The probability of transitions from N1-to-wake was significantly greater in NT1 than in NT2 and o-HS while that from N1-to-N2 was significantly smaller in NT1 than in NT2 and o-HS. The probability of transitions from N2-to-REM was significantly smaller in NT1 than in o-HS. Wake and N1 were significantly more continuous in NT1 than in NT2; specifically, N1 followed by N2 was significantly more continuous in NT1 than in NT2 and o-HS. N2 was significantly less continuous in NT1 and NT2 than in o-HS; this was specifically confirmed for N2 followed by N1/wake. REM sleep was significantly less continuous in NT1 than in NT2 and o-HS; specifically, REM sleep followed by wake was significantly less continuous in NT1 than in o-HS. Continuity of N3 did not differ significantly between groups. Conclusion Dynamics of sleep stage transitions differed between NT1, NT2, and o-HS. Dynamic features of sleep such as sleep instability, persistency of wake/N1, and REM fragmentation may differentiate NT1 from NT2, while N2 continuity may differentiate narcolepsy from o-HS. The results suggest that sleep transition analysis may be of clinical utility and provide insights into the underlying pathophysiology of hypersomnia and narcolepsy. Support JSPS KAKENHI (18K17891 to AK).

scholarly journals Effect of a Recliner Chair with Rocking Motions on Sleep Efficiency

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8214
Author(s):  
Suwhan Baek ◽  
Hyunsoo Yu ◽  
Jongryun Roh ◽  
Jungnyun Lee ◽  
Illsoo Sohn ◽  
...  
Keyword(s):  
Sleep Quality ◽  
Quantitative Evaluation ◽  
Sleep Stage ◽  
Qualitative Evaluation ◽  
Parameter Analysis ◽  
Sleep Stages ◽  
Deep Sleep ◽  
Quality Of Sleep ◽  
Sleep Scoring

In this study, we analyze the effect of a recliner chair with rocking motions on sleep quality of naps using automated sleep scoring and spindle detection models. The quality of sleep corresponding to the two rocking motions was measured quantitatively and qualitatively. For the quantitative evaluation, we conducted a sleep parameter analysis based on the results of the estimated sleep stages obtained on the brainwave and spindle estimation, and a sleep survey assessment from the participants was analyzed for the qualitative evaluation. The analysis showed that sleep in the recliner chair with rocking motions positively increased the duration of the spindles and deep sleep stage, resulting in improved sleep quality.

scholarly journals Semi-Automated Sleep EEG Scoring with Active Learning and HMM-Based Deletion of Ambiguous Instances

Proceedings ◽  
2019 ◽  
Vol 31 (1) ◽  
pp. 46 ◽  
Author(s):  
Martin Macaš ◽  
Nela Grimová ◽  
Václav Gerla ◽  
Lenka Lhotská
Keyword(s):  
Active Learning ◽  
Sleep Stage ◽  
Decision Support Tool ◽  
Sleep Eeg ◽  
Sleep Stages ◽  
Biomedical Signal ◽  
Support Tool ◽  
Sleep Scoring ◽  
Eeg Recordings ◽  
Ambiguous Data

Sleep scoring is an important tool for physicians. Assigning of segments of long biomedical signal into sleep stages is, however, a very time consuming, tedious and expensive task which is performed by an expert. Automatic sleep scoring is not well accepted in clinical practice because of low interactivity and unacceptable error, which is often caused by inter-patient variability. This is solved by proposing a semi-automatic approach, where parts of the signal are selected for manual labeling by active learning and the resulting classifier is used for automatic labeling of the remaining signal. The active learning is disturbed by noisy ambiguous data instances caused by continuous character of the sleep stage transitions and a removal of such transitional instances from the training set prior to active learning can improve the efficiency of the method. This paper proposes to use the hidden Markov model for the detection of the transitional instances. It shows experimentally on 35 sleep EEG recordings that such a method significantly improves the semi-automatic method. A complete methodology for semi-automatic sleep scoring is proposed and evaluated, which can be better accepted as a decision support tool for sleep scoring experts.

scholarly journals 0147 Dynamic Alterations in Functional Connectivity Between Sleep- and Wake-Promoting Regions of the Human Brain at the Sleep Onset Period

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A58-A58
Author(s):  
T Ishii ◽  
T Koike ◽  
E Nakagawa ◽  
M Sumiya ◽  
N Sadato
Keyword(s):  
Functional Connectivity ◽  
Human Brain ◽  
Transition Period ◽  
Sleep Stage ◽  
Sleep Onset ◽  
Sleep Stages ◽  
Alpha Power ◽  
Onset Period ◽  
The Brain

Abstract Introduction The sleep onset period, involving so-called stage N1 sleep largely, is characterized by a reduction in the amount of alpha activity compared to wakefulness. Various kinds of physiological and psychological changes are also apparent, such as slow eye movements, changes in muscle tonus, and the hypnagogic dream-like mentation. These phenomena are thought to be the reflection of dynamic alterations in the brain during the transition period, however, details of these changes have still been uncovered. Methods We aimed to investigate a dynamic shift in the brain connectivity at sleep onset using the method of EEG-fMRI simultaneous recording. Twenty-three healthy subjects participated. EEG/fMRI were recorded simultaneously during an hour’s nap in a 3T-MRI scanner and real-time monitoring of EEG was performed. To record the transition period between multiple times, an experimenter inside a scanner room touched a subject’s foot for inducing arousal when a shift to NREM sleep stage 1 was observed. EEG data were scored according to the AASM criteria. Based on sleep stages defined by polysomnographic findings, we investigated alterations in functional connectivity of sleep- and wake- promoting regions within the hypothalamus and other areas including the thalamus. Results Posterior alpha power showed significant positive correlation with BOLD signals in the anterior and medial dorsal thalamus. Connectivity between the thalamus and cortical regions reduced sharply in the descent to sleep stage. Meanwhile, BOLD signals of the sleep- and wake- promoting regions within the hypothalamus fluctuated with certain temporal lags from fluctuations of alpha rhythm at sleep onset. Conclusion Present findings provide preliminary evidence of dynamics of wake- and sleep- promoting regions in the human brain in vivo. Our data also support the hypothesis that reduced thalamocortical connectivity which limits the capacity to integrate information is associated with the transition of consciousness at sleep onset. Support None

scholarly journals Improved sleep scoring in mice reveals human-like stages

2018 ◽  
Author(s):  
Marie Masako Lacroix ◽  
Gaetan de Lavilléon ◽  
Julie Lefort ◽  
Karim El Kanbi ◽  
Sophie Bagur ◽  
...  
Keyword(s):  
Sleep Onset ◽  
Nrem Sleep ◽  
Oscillatory Activity ◽  
Sleep Stages ◽  
New Approach ◽  
Firing Rates ◽  
Sleep Scoring ◽  
Delta Waves ◽  
Night Terrors

AbstractRodents are the main animal model to study sleep. Yet, in spite of a large consensus on the distinction between rapid-eye-movements sleep (REM) and non-REM sleep (NREM) in both humans and rodent, there is still no equivalent in mice of the NREM subdivision classically described in humans.Here we propose a classification of sleep stages in mice, inspired by human sleep scoring. By using chronic recordings in medial prefrontal cortex (mPFC) and hippocampus we can classify three NREM stages with a stage N1 devoid of any low oscillatory activity and N3 with a high density of delta waves. These stages displayed the same evolution observed in human during the whole sleep or within sleep cycles. Importantly, as in human, N1 in mice is the first stage observed at sleep onset and is increased after sleep fragmentation in Orexin-/- mice, a mouse model of narcolepsy.We also show that these substages are associated to massive modification of neuronal activity. Moreover, considering these stages allows to predict mPFC neurons evolution of firing rates across sleep period. Notably, neurons preferentially active within N3 decreased their activity over sleep while the opposite is seen for those preferentially active in N1 and N2.Overall this new approach shows the feasibility of NREM sleep sub-classification in rodents, and, in regard to the similarity between sleep in both species, will pave the way for further studies in sleep pathologies given the perturbation of specific sleep substages in human pathologies such as insomnia, somnambulism, night terrors, or fibromyalgia.

scholarly journals Automatic Sleep Scoring Stages using Real-Time EMG Signals

2021 ◽  
Vol 4 (1) ◽  
pp. 56-59
Author(s):  
Hemu Farooq ◽  
Anuj Jain ◽  
V. K. Sharma
Keyword(s):  
Sleep Disorders ◽  
Real Time ◽  
Scoring System ◽  
Sleep Stage ◽  
Clinical Information ◽  
Well Being ◽  
Physical And Mental Health ◽  
Sleep Scoring ◽  
Sleep Stage Classification ◽  
Reliable Classification

Sleep is completely regarded as obligatory component for an individual’s prosperity and is an extremely important element for the overall mental and physical well-being of an individual. It is a condition in which physical and mental health of an individual are in condition of halt. The conception of sleep is considered extremely peculiar and is a topic of discussion and it has attracted the researchers all over the world. Proper analysis of sleep scoring system and its different stages gives clinical information when diagnosing on patients having sleep disorders. Since, manual sleep stage classification is a hectic process as it takes sufficient time for sleep experts to perform data analysis. Besides, mistakes and irregularities in between classification of same data can be recurrent. Therefore, there is a great use of automatic scoring system to support reliable classification. The proposed work provides an insight to use the automatic scheme which is based on real time EMG signals. EMG is an electro neurological diagnostic tool which evaluates and records the electrical activity generated by muscle cells. The sleep scoring analysis can be applied by recording Electroencephalogram (EEG), Electromyogram (EMG), and Electrooculogram (EOG) based on epoch which is defined as a period of 30 second length segments, and this method of sleep scoring system is also called polysomnography test or PSG test. The standard database of EMG signals was collected from different hospitals in sleep laboratory which gives the different stages of sleep. These are Waking, Non-REM1 (stage-1), Non-REM2 (stage-2), Non-REM3 (stage-3), REM. The main motive of the proposed work is the synchronization of EEG, EMG, EOG in order to understand different stages of sleep when they are simultaneously recorded. The procedure can be useful in clinics, particularly for scientists in studying the wakefulness and sleep stage correlation and thus helps in diagnosing some sleep disorders.

Sign in / Sign up

Export Citation Format

Share Document