JOIN US AT WORLD SLEEP 2022 CONGRESS

Advancing Sleep Science
Promoting impactful research to improve sleep quality
Sleep Number is showcasing new studies using its smart bed at World Sleep 2022 Congress, the 16th international meeting of the World Sleep Society. Sleep Number® data being presented at the congress includes results of a prediction model for influenza-like illnesses, a study of sleep disorders and analysis of real-time sleep staging to potentially detect and guide intervention for sleep disorders. These further demonstrate the research capabilities of the smart bed to accurately assess and track sleep in a non-invasive way, while also offering a longitudinal data collection platform and delivering effortless, proven quality sleep. Sleep Number is also hosting a symposium with world-leading sleep experts to evaluate how external factors like temperature, light and noise can be optimized to improve sleep quality.
APPROXIMATION OF INFLUENZA-LIKE ILLNESS RATES USING SLEEP AND CARDIORESPIRATORY DATA FROM SMART BED
1. OBJECTIVE
Pathophysiologic responses to viral infections affect sleep duration, quality and concomitant cardiorespiratory function. Real-world, longitudinal monitoring of sleep metrics using a smart bed could prove to be invaluable for infectious disease detection. Previously we leveraged sleep metrics from a smart bed to build a COVID-19 symptom detection model. Analysis of pre-pandemic data with this model indicated that our results may generalize to detecting symptoms of other influenza-like illnesses (ILI). Here we investigated whether seasonal ILI trends reported by US Centers for Disease Control and Prevention (CDC) can be approximated from aggregation of individual ILI symptom predictions.
2. HIGH LEVEL STUDY SETUP
Sleep data from January 2020 to December 2020 from 122 positive and 1,603 negative respondents were used to develop an individual-level COVID-19 symptom detection model. The model produces a probability of experiencing COVID-19 symptoms for each sleep session. Pre-pandemic sleep data from January 2017 to December 2019 from 4,187 responders (1,820 sleep sessions per night on average) were used to assess ability of the developed model to generalize to ILI symptom detection. Weekly rates of high-scoring sleep sessions between January 2017 and June 2018 were fitted to the weekly ILI rates as reported by the CDC using a negative binomial model. Subsequently, Pearson correlation coefficients were calculated for the predicted and reported rates between July 2018 and December 2019.
3. RESULTS
Correlation between the predicted and CDC reference was 0.91 (+0.04 compared to the baseline model). Correlation restricted to the influenza season (week 40 of 2018 to week 20 of 2019) was 0.87 (+0.13 compared to the baseline model). The sleep metrics measured with a smart bed platform are a unique source of longitudinal data, collected in a real-world, unobtrusive manner. This system may serve as a valuable asset in predicting and tracking the development of symptoms associated with a wide variety of respiratory illnesses, including influenza and COVID-19.
EEG SPECTRAL PROPERTIES AND ASSOCIATED ECG-BASED HEART RATE VARIABILITY IN PEOPLE WITH INSOMNIA VERSUS HEALTHY SLEEPERS
1. OBJECTIVE
Sleep disorders may disrupt normal central and autonomic nervous system function, as measured by electroencephalogram (EEG)/electrocardiogram (ECG) coupling. We compared the sleep architecture, central and autonomic nervous system functions, and EEG/ECG coupling of healthy sleepers versus people with insomnia using polysomnography.
2. HIGH LEVEL STUDY SETUP
Utilized publicly available polysomnography data from 9 people with insomnia and polysomnography data from 12 age-matched healthy sleepers obtained from an IRB-approved sleep study conducted by Sleep Number Corporation. A generalized linear model approach was used to assess the degree of coupling between EEG power and ECG-derived metrics in rapid eye movement (REM) and non-REM (NREM) sleep for all participants.
3. RESULTS
People with insomnia have elements of increased EEG power during REM sleep, as well as a pattern of power characteristics during NREM sleep as compared with healthy sleepers. Changes are also seen in ECG-based heart rate variability (HRV) during NREM and REM sleep in people with insomnia, who have significantly lower HRV compared with healthy sleepers.
InterBeat Interval (IBI) based sleep staging: towards real-time implementation
1. OBJECTIVE
Using the IBI signal for automatic sleep staging enables the development of algorithms that are agnostic of the cardiac monitoring technology. We developed a deep neural network (DNN) algorithm that detects sleep stages using IBIs and perform real-time sleep staging, and potentially direct intervention strategies.
2. HIGH LEVEL STUDY SETUP
This study describes a sleep-staging algorithm that processes sequential 150-second IBI temporal windows, with a shift of 30 seconds between adjacent windows. IBIs were used because they can be measured using unobtrusive, noninvasive sensing technology, such as ballistocardiography (BCG) or indirect contact ECG.
3. RESULTS
This DNN algorithm is three orders of magnitude smaller compared with state-of-the-art DNN algorithms and was developed to perform real-time, IBI-based sleep staging. Kappa values on healthy subject data show moderate agreement with manual scoring. Lower performance on data from 36 sleep disorders can be improved using optimized thresholds.
Results from this study was accepted for publication in the journal Physiological Measurement.
Join Our Symposium
Can the Sleeping Environment Be Optimized to Improve Sleep Quality?
During this event convened by sleep health leader Sleep Number, we will evaluate temperature modulation, light and noise exposure, and sleeping position within the sleeping environment to determine if they can be manipulated to improve sleep quality.
Meet Our Speakers