Sleep quality assessment by parameter optimization

Sleep quality measurement is a complex process requires large number of parameters to monitor sleep and sleep cycles. The Gold Standard Polysomnography (PSG) parameters are considered as standard parameters for sleep quality measurement. In the PSG process, number of monitoring parameters are involved for that large number of sensors are used which makes this process complex, expensive and obtrusive. There is need to find optimize parameters which are directly involve in providing accurate information about sleep and reduce the process complexity. Our Parameter Optimization method is based on parameter reduction by finding key parameters and their inter dependent parameters. Sleep monitoring by these optimize parameter is different from both, clinical complex (PSG) used in hospitals and commercially available devices which work on dependent and dynamic parameter sensing. Optimized parameters obtained from PSG parameters are Electrocardiogram (ECG), Electrooculogram (EOG), Electroencephalography (EEG) and Cerebral blood flow (CBF). These key parameters show close correlation with sleep and hence reduce complexity in sleep monitoring by providing simultaneous measurement of appropriate signals for sleep analysis.

A Novel Sleep Staging Network Based on Data Adaptation and Multimodal Fusion

Sleep staging is one of the important methods to diagnosis and treatment of sleep diseases. However, it is laborious and time-consuming, therefore, computer assisted sleep staging is necessary. Most of the existing sleep staging researches using hand-engineered features rely on prior knowledges of sleep analysis, and usually single channel electroencephalogram (EEG) is used for sleep staging task. Prior knowledge is not always available, and single channel EEG signal cannot fully represent the patient’s sleeping physiological states. To tackle the above two problems, we propose an automatic sleep staging network model based on data adaptation and multimodal feature fusion using EEG and electrooculogram (EOG) signals. 3D-CNN is used to extract the time-frequency features of EEG at different time scales, and LSTM is used to learn the frequency evolution of EOG. The nonlinear relationship between the High-layer features of EEG and EOG is fitted by deep probabilistic network. Experiments on SLEEP-EDF and a private dataset show that the proposed model achieves state-of-the-art performance. Moreover, the prediction result is in accordance with that from the expert diagnosis.

Cardiopulmonary coupling analysis using smart wearables and mobile computing

Cardiopulmonary coupling (CPC) analysis links heart and respiration rates to assess sleep-related parameters. Typically, the CPC is measured using multi-lead electrocardiography (ECG) and ECG-derived respiration (EDR). Novel textile shirts with embedded ECG sensors offer convenient and continuously monitored sleep at home. We investigate the feasibility of a shirt with textile sensors (Pro- Kit, Hexoskin, Quebec, Canada) for CPC analysis by mobile computing. ECG data is continuously transmitted from the shirt to a smartphone via Bluetooth Low Energy (BLE). We customize a CPC algorithm and use twelve whole-night recordings from four volunteers to perform qualitative and quantitative analysis. We compare EDR with respiratory inductive plethysmography (RIP). In average, EDR and RIP differ 17.22%. After one night, the batteries are reduced to approx. 70% (shirt) and 90% (smartphone). The run time for CPC processing is approx. 3 min. Hence, smart wearables in combination with mobile computing show technical feasibility for CPC analysis. Eventually, this could yield a useful solution for sleep analysis of non-expert users in a private environment.

O035 Automated vs. expert manual analysis of the Multiple Sleep Latency Test

Purpose To compare Compumedics Profusion PSG™ automated sleep analysis of Multiple Sleep Latency Tests (MSLTs) with expert consensus manual analysis. Methods Consecutive PSG with MSLTs were analysed using automated software (Compumedics Ltd (Abbottsford, Victoria, Australia) Profusion PSG™ V4.5 Build 531) (‘Auto’) and by two of nine experienced scientists. Discrepancies between scientists were discussed to establish expert consensus (‘Final’). Results Fifty consecutive patients referred for investigation of Narcolepsy were included. Two were excluded due to poor signal quality (1) and early test termination (1). The remaining 48 (37 M, 10 F, 1) had a median (range) age of 37 (17–63) years, BMI 28.0 (19.9–66.1) kg/m2, and mean sleep latency (MSL) 14.0 (1.5–20.0) minutes. Of five MSLTs with MSL <=8 min, Auto-MSL was also <=8 min. Of 43 MSLTs with MSL >=8 min, Auto-MSL was <=8 min in 12. MSL sensitivity was 100% and specificity 72%. For the one MSLT with >=2 SOREMs, Auto identified 1 SOREM. Nap-wise, Auto-SOREM sensitivity was 17% and specificity 98%; one of six REM-positive naps was detected by auto-analysis and there were seven false positive and five false negative SOREM results. Conclusions (1) Automated analysis poorly detected short MSL and SOREM occurrence but was able to rule out all true-negative MSLT results, in this MSLT dataset. (2) This comparison methodology and dataset facilitates robust prospective testing of other current and future algorithms.

Sleep in Intensive Care Unit Patients

Sleep disturbances are common among patients admitted to the intensive care unit (ICU); however, these issues tend to receive less attention because critical care is prioritized in seriously ill patients. Recent studies have reported that sleep disturbances in patients admitted to the ICU are associated with delirium, weakened immunity, long-term cognitive decline, and persistent sleep disorders. Sleep disturbances in the ICU are attributable to the disease per se and also to the ICU environment that is not conducive to good sleep. Continuous exposure to light and noise are major environmental risk factors that disrupt the circadian rhythm and interfere with deep sleep. Sleep analysis using polysomnography in patients admitted to the ICU typically reveals increase in sleep latency, sleep fragmentation, and decreased stage N3 and rapid eye movement sleep, which are associated with poor prognosis even in patients with severe neurological conditions, including traumatic brain injury and intracranial hemorrhage. Polysomnography is the gold standard for objective evaluation of sleep; however, its applicability is limited in ICU settings, and novel methods such as continuous electroencephalographic spectral analysis and actigraphy have recently been proposed in clinical practice. Efforts to reduce nighttime light and noise (which are modifiable environmental factors) can improve sleep quality. In this article, the author reviews the studies that discuss characteristics of sleep disturbances, the associated risk factors and their correlation with prognosis among patients admitted to the ICU, as well as possible strategies to improve sleep quality in this patient population.

Multitaper Time-frequency Peak-based Longitudinal Sleep Analysis in 5XFAD Mouse Model

Background: Sleep disturbance is common in Alzheimer’s disease (AD), but the characteristics of sleep disturbance remain unclear. Multitaper spectral analysis (MSA) is a novel method for investigating sleep. However, MSA-based sleep research in AD is lacking; hence we applied MSA to examine the sleep of AD.Methods: Electroencephalograms were recorded on 3-, 6-, and 10-month-old 5XFAD mice, and the time-frequency (TF) peaks were detected using MSA. We comparatively analyzed the TF peaks between genotypes and age groups.Results: The sigma TF peaks (~80%) were sleep spindles. MSA-based TF plot showed distinct patterns, agreeing with manual scoring. With AD progression, the characteristics of TF peaks coherently changed; shorter sigma TF peaks outnumbered longer ones; dark-period fast spindle TF peak density decreased significantly at both 6 and 10 months.Conclusions: Multitaper TF peaks might provide biomarkers for the progression of AD. Further investigations are warranted.