Automatic sleep classification using a data-driven topic model reveals latent sleep states

Koch, H; Christensen, J. H.; Frandsen, Rune; Zoetmulder, Marielle; Arvastson, Lars; Christensen, Søren Rahn; Jennum, Poul; Sørensen, Helge Bjarup Dissing

doi:10.1016/j.jneumeth.2014.07.002

Cited by 47 publications

(37 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Surveying these measures simultaneously in three-second intervals with a step size of one second, the approach identifies patterns indicative of the various sleep stages. The method produces a mixture of probabilities for the different sleep stages, and final identification of NREM, REM and W is based on the highest probability when combining probabilities of individual sleep stages (Koch et al, 2014). A clear advantage of this approach is that it takes distributions of microsleep characteristics into account, and each sleep epoch is labeled individually and independently of adjacent epochs.…”

Section: Automatic Staging Of Sleepmentioning

confidence: 99%

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson’s disease

Christensen

Jennum

Koch

et al. 2016

Clinical Neurophysiology

Self Cite

View full text Add to dashboard Cite

Section: Automatic Staging Of Sleepmentioning

confidence: 99%

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson’s disease

Christensen

Jennum

Koch

et al. 2016

Clinical Neurophysiology

Self Cite

View full text Add to dashboard Cite

“…To overcome this, an automatic sleep detector was used to identify REM, NREM and W for each subject and analyses were performed using automatically scored sleep stage data. The automatic sleep scoring technique used in this study has been validated on the same PD, iRBD, PLMD and control PSG data set as used in this study, and the methods are described in detail by Koch et al (2014). Specifically, the method is optimized on nocturnal PSG of 50 subjects, and validated on an additional 76 subjects (a mixture of the same controls and patients included in this study).…”

Section: Automatic Staging Of Sleepmentioning

confidence: 99%

“…Therefore, this study analyzed wake-sleep and REM-NREM transitions as well as W, REM and NREM stability measures based on automatically identified as well as manually scored REM, NREM and W stages. The automatic method used has been validated by (Koch et al, 2014) using the same PSG data as analyzed in this study.…”

Section: Introductionmentioning

confidence: 99%

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson's disease

et al. 2015

View full text Add to dashboard Cite

“…[7][8][9] A home sleep monitoring device with the accuracy of PSG would be an ideal solution to enable a combination of cost-effectiveness and ease of use along with reliability and accuracy. Among the available alternatives, actigraphy has the disadvantage of requiring body contact.…”

Section: Introductionmentioning

confidence: 99%

Validation of Contact-Free Sleep Monitoring Device with Comparison to Polysomnography

Tal

Shinar

Shaki

et al. 2017

Journal of Clinical Sleep Medicine

121

View full text Add to dashboard Cite

Study Objectives: To validate a contact-free system designed to achieve maximal comfort during long-term sleep monitoring, together with high monitoring accuracy. Methods: We used a contact-free monitoring system (EarlySense, Ltd., Israel), comprising an under-the-mattress piezoelectric sensor and a smartphone application, to collect vital signs and analyze sleep. Heart rate (HR), respiratory rate (RR), body movement, and calculated sleep-related parameters from the EarlySense (ES) sensor were compared to data simultaneously generated by the gold standard, polysomnography (PSG). Subjects in the sleep laboratory underwent overnight technician-attended full PSG, whereas subjects at home were recorded for 1 to 3 nights with portable partial PSG devices. Data were compared epoch by epoch. Results: A total of 63 subjects (85 nights) were recorded under a variety of sleep conditions. Compared to PSG, the contact-free system showed similar values for average total sleep time (TST), % wake, % rapid eye movement, and % non-rapid eye movement sleep, with 96.1% and 93.3% accuracy of continuous measurement of HR and RR, respectively. We found a linear correlation between TST measured by the sensor and TST determined by PSG, with a coefficient of 0.98 (R = 0.87). Epoch-by-epoch comparison with PSG in the sleep laboratory setting revealed that the system showed sleep detection sensitivity, specificity, and accuracy of 92.5%, 80.4%, and 90.5%, respectively. Conclusions: TST estimates with the contact-free sleep monitoring system were closely correlated with the gold-standard reference. This system shows good sleep staging capability with improved performance over accelerometer-based apps, and collects additional physiological information on heart rate and respiratory rate.

show abstract

Automatic sleep classification using a data-driven topic model reveals latent sleep states

Cited by 47 publications

References 8 publications

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson’s disease

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson’s disease

Sleep stability and transitions in patients with idiopathic REM sleep behavior disorder and patients with Parkinson's disease

Validation of Contact-Free Sleep Monitoring Device with Comparison to Polysomnography

Contact Info

Product

Resources

About