Polysomnography (PSG) is the gold-standard for sleep apnea and hypopnea syndrome (SAHS) diagnosis. Because the PSG system is not suitable for long-term continuous use owing to the high cost and discomfort caused by attached multi-channel sensors, alternative methods using a non-contact sensor have been investigated. However, the existing methods have limitations in that the radar-person distance is fixed, and the detected apnea hypopnea (AH) event cannot be provided in real-time. In this paper, therefore, we propose a novel approach for real-time AH event detection with impulse-radio ultra-wideband (IR-UWB) radar using a deep learning model. 36 PSG recordings and simultaneously measured IR-UWB radar data were used in the experiments. After the clutter was removed, IR-UWB radar images were segmented by sliding a 20-s window at 1-s shift, and categorized into two classes: AH and N. A hybrid model combining the convolutional neural networks and long short-term memory networks was trained with the data, which consisted of class-balanced segments. Time sequenced classified outputs were then fed to an event detector to identify valid AH events. Therefore, the proposed method showed a Cohen’s kappa coefficient of 0.728, sensitivity of 0.781, specificity of 0.956, and an accuracy of 0.930. According to the apnea-hypopnea index (AHI) estimation analysis, the Pearson’s correlation coefficient between the estimated AHI and reference AHI was 0.97. In addition, the average accuracy and kappa of SAHS diagnosis was 0.98 and 0.96, respectively, for AHI cutoffs of ≥ 5, 15, and 30 events/h. The proposed method achieved the state-of-the-art performance for classifying SAHS severity without any hand-engineered feature regardless of the user’s location. Our approach can be utilized for a cost-effective and reliable SAHS monitoring system in a home environment.

Vital signs provide important biometric information for managing health and disease, and it is important to monitor them for a long time in a daily home environment. To this end, we developed and evaluated a deep learning framework that estimates the respiration rate (RR) and heart rate (HR) in real time from long-term data measured during sleep using a contactless impulse radio ultrawide-band (IR-UWB) radar. The clutter is removed from the measured radar signal, and the position of the subject is detected using the standard deviation of each radar signal channel. The 1D signal of the selected UWB channel index and the 2D signal applied with the continuous wavelet transform are entered as inputs into the convolutional neural-network-based model that then estimates RR and HR. From 30 recordings measured during night-time sleep, 10 were used for training, 5 for validation, and 15 for testing. The average mean absolute errors for RR and HR were 2.67 and 4.78, respectively. The performance of the proposed model was confirmed for long-term data, including static and dynamic conditions, and it is expected to be used for health management through vital-sign monitoring in the home environment.

Sleep stage scoring is the first step towards quantitative analysis of sleep using polysomnography (PSG) recordings. However, although PSG is a gold standard method for assessing sleep, it is obtrusive and difficult to apply for long-term sleep monitoring. Further, because human experts manually classify sleep stages, it is time-consuming and exhibits inter-rater variability. Therefore, this article proposes a long short-term memory (LSTM) model for automatic sleep stage scoring using a polyvinylidene fluoride (PVDF) film sensor that can provide unconstrained long-term physiological monitoring. Signals were recorded using a PVDF sensor during PSG. From 60 recordings, 30 were used for training, 10 for validation, and 20 for testing. Sixteen parameters, including movement, respiration-related, and heart rate variability, were extracted from the recorded signals and then normalized. From the selected LSTM architecture, four sleep stage classification performances were evaluated for a test dataset and the results were compared with those of conventional machine learning methods. According to epoch-by-epoch (30 s) analysis, the classification performance for the four sleep stages had an average accuracy of 73.9% and a Cohen's kappa coefficient of 0.55. When compared with other machine learning methods, the proposed method achieved the highest classification performance. The use of LSTM networks with the PVDF film sensor has potential for facilitating automatic sleep scoring, and it can be applied for long-term sleep monitoring at home.

This study investigated alterations in resting-state functional connectivity (RSFC) and hyperarousal biomarkers in patients with chronic insomnia disorder (CID), compared with good sleepers (GS). We also examined the relationships between altered RSFC and hyperarousal biomarkers. Fifty patients with CID and fifty-two GS completed self-reporting questionnaires, and then underwent polysomnography and resting-state functional magnetic resonance imaging. We analyzed RSFC in the amygdala (AMG) and anterior insula (aINS), which are core regions of the salience network that are likely to be involved in hyperarousal. We also analyzed electroencephalography (EEG) relative beta power and heart rate variability (HRV) parameters (e.g., low and high frequency) during sleep. We then tested between-group differences in the RSFC and hyperarousal biomarkers; we examined correlations of RSFC with EEG beta power and HRV. Compared with GS, patients with CID showed more negative RSFC between the right AMG and left supramarginal gyrus (SMG), but less positive RSFC between the left aINS and bilateral lateral prefrontal cortex. The AMG-SMG RSFC was negatively correlated with EEG beta power in central regions (C3: r = −0.336, P = 0.012; C4: r = −0.314, P = 0.024). Decreased RSFC between the AMG and SMG in patients with insomnia may reflect difficulty in cortical top-down regulation of the AMG, indicating daytime hyperarousal. Individuals who experience hyperarousal during the daytime may also exhibit cortical hyperarousal during sleep, as indicated by increased EEG beta power.