![Sample our Bioscience journals, sign in here to start your access, Latest two full volumes FREE to you for 14 days]({"type":"image" , "src" : "/sda/5925/TOC-Subject-Sample-2021-Bioscience.jpg"})
ABSTRACT
Sleep efficiency is a commonly and widely used measure to objectively evaluate sleep quality. Monitoring sleep efficiency can provide significant information about health conditions. As an attempt to facilitate less cumbersome monitoring of sleep efficiency, our study aimed to suggest new predictors of sleep efficiency that enable reliable and unconstrained estimation of sleep efficiency during awake resting period. We hypothesized that the autonomic nervous system activity observed before falling asleep might be associated with sleep efficiency. To assess autonomic activity, heart rate variability and breathing parameters were analyzed for 5 min. Using the extracted parameters as explanatory variables, stepwise multiple linear regression analyses and k-fold cross-validation tests were performed with 240 electrocardiographic and thoracic volume change signal recordings to develop the sleep efficiency prediction model. The developed model’s sleep efficiency predictability was evaluated using 60 piezoelectric sensor signal recordings. The regression model, established using the ratio of the power of the low- and high-frequency bands of the heart rate variability signal and the average peak inspiratory flow value, provided an absolute error (mean ± SD) of 2.18% ± 1.61% and a Pearson’s correlation coefficient of 0.94 (p < 0.01) between the sleep efficiency predictive values and the reference values. Our study is the first to achieve reliable and unconstrained prediction of sleep efficiency without overnight recording. This method has the potential to be utilized for home-based, long-term monitoring of sleep efficiency and to support reasonable decision-making regarding the execution of sleep efficiency improvement strategies.
Declaration of interest
The authors declare no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Funding
This work was supported by the Technological Innovation R&D Program (S2274094) funded by the Small and Medium Business Administration (SMBA, Korea).