Dataset Information

An unbiased, efficient sleep-wake detection algorithm for a population with sleep disorders: change point decoder.

ABSTRACT:

Study objectives

The usage of wrist-worn wearables to detect sleep-wake states remains a formidable challenge, particularly among individuals with disordered sleep. We developed a novel and unbiased data-driven method for the detection of sleep-wake and compared its performance with the well-established Oakley algorithm (OA) relative to polysomnography (PSG) in elderly men with disordered sleep.

Methods

Overnight in-lab PSG from 102 participants was compared with accelerometry and photoplethysmography simultaneously collected with a wearable device (Empatica E4). A binary segmentation algorithm was used to detect change points in these signals. A model that estimates sleep or wake states given the changes in these signals was established (change point decoder, CPD). The CPD's performance was compared with the performance of the OA in relation to PSG.

Results

On the testing set, OA provided sleep accuracy of 0.85, wake accuracy of 0.54, AUC of 0.67, and Kappa of 0.39. Comparable values for CPD were 0.70, 0.74, 0.78, and 0.40. The CPD method had sleep onset latency error of -22.9 min, sleep efficiency error of 2.09%, and underestimated the number of sleep-wake transitions with an error of 64.4. The OA method's performance was 28.6 min, -0.03%, and -17.2, respectively.

Conclusions

The CPD aggregates information from both cardiac and motion signals for state determination as well as the cross-dimensional influences from these domains. Therefore, CPD classification achieved balanced performance and higher AUC, despite underestimating sleep-wake transitions. The CPD could be used as an alternate framework to investigate sleep-wake dynamics within the conventional time frame of 30-s epochs.

SUBMITTER: Cakmak AS

PROVIDER: S-EPMC7420526 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An unbiased, efficient sleep-wake detection algorithm for a population with sleep disorders: change point decoder.

Cakmak Ayse S AS Da Poian Giulia G Willats Adam A Haffar Ammer A Abdulbaki Rami R Ko Yi-An YA Shah Amit J AJ Vaccarino Viola V Bliwise Donald L DL Rozell Christopher C Clifford Gari D GD

Sleep 20200801 8

<h4>Study objectives</h4>The usage of wrist-worn wearables to detect sleep-wake states remains a formidable challenge, particularly among individuals with disordered sleep. We developed a novel and unbiased data-driven method for the detection of sleep-wake and compared its performance with the well-established Oakley algorithm (OA) relative to polysomnography (PSG) in elderly men with disordered sleep.<h4>Methods</h4>Overnight in-lab PSG from 102 participants was compared with accelerometry and ...[more]

PMID: 32006429

Similar Datasets

Project description:BackgroundIndividuals with typical circadian rhythm sleep-wake disorders (CRSWDs) have a habitual sleep timing that is desynchronized from social time schedules. However, it is possible to willfully force synchronisation against circadian-driven sleepiness, which causes other sleep problems. This pathology is distinguishable from typical CRSWDs and is referred to here as latent CRSWD (LCRSWD). Conventional diagnostic methods for typical CRSWDs are insufficient for detecting LCRSWD because sufferers have an apparently normal habitual sleep timing.MethodsWe first evaluated the reliability of circadian phase estimation based on clock gene expression using hair follicles collected at three time points without sleep interruption. Next, to identify detection criteria for LCRSWD, we compared circadian and sleep parameters according to estimated circadian phases, at the group and individual level, between subjects with low and high Pittsburgh Sleep Quality Index (PSQI) scores. To validate the reliability of identified detection criteria, we investigated whether the same subjects could be reproducibly identified at a later date and whether circadian amelioration resulted in sleep improvement.FindingsWe successfully validated the reliability of circadian phase estimation at three time points and identified potential detection criteria for individuals with LCRSWD attributed to delayed circadian-driven sleepiness. In particular, a criterion based on the interval between the times of the estimated circadian phase of clock gene expression and getting out of bed on work or school days was promising. We also successfully confirmed the reproducibility of candidate screening and sleep improvement by circadian amelioration, supporting the reliability of the detection criteria.InterpretationAlthough several limitations remain, our present study demonstrates a promising prototype of a detection method for LCRSWD attributed to delayed circadian-driven sleepiness. More extensive trials are needed to further validate this method.FundingThis study was supported mainly by JSPS, Japan.

Project description:BackgroundTo detect changes in biological processes, samples are often studied at several time points. We examined expression data measured at different developmental stages, or more broadly, historical data. Hence, the main assumption of our proposed methodology was the independence between the examined samples over time. In addition, however, the examinations were clustered at each time point by measuring littermates from relatively few mother mice at each developmental stage. As each examination was lethal, we had an independent data structure over the entire history, but a dependent data structure at a particular time point. Over the course of these historical data, we wanted to identify abrupt changes in the parameter of interest - change points.ResultsIn this study, we demonstrated the application of generalized hypothesis testing using a linear mixed effects model as a possible method to detect change points. The coefficients from the linear mixed model were used in multiple contrast tests and the effect estimates were visualized with their respective simultaneous confidence intervals. The latter were used to determine the change point(s). In small simulation studies, we modelled different courses with abrupt changes and compared the influence of different contrast matrices. We found two contrasts, both capable of answering different research questions in change point detection: The Sequen contrast to detect individual change points and the McDermott contrast to find change points due to overall progression. We provide the R code for direct use with provided examples. The applicability of those tests for real experimental data was shown with in-vivo data from a preclinical study.ConclusionSimultaneous confidence intervals estimated by multiple contrast tests using the model fit from a linear mixed model were capable to determine change points in clustered expression data. The confidence intervals directly delivered interpretable effect estimates representing the strength of the potential change point. Hence, scientists can define biologically relevant threshold of effect strength depending on their research question. We found two rarely used contrasts best fitted for detection of a possible change point: the Sequen and McDermott contrasts.

Dataset Information

An unbiased, efficient sleep-wake detection algorithm for a population with sleep disorders: change point decoder.

Study objectives

Methods

Results

Conclusions

Publications

An unbiased, efficient sleep-wake detection algorithm for a population with sleep disorders: change point decoder.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure