Search

Objective: The aim of this study was to assess how the photoplethysmogram frequency and amplitude responses to arousals from sleep differ between arousals caused by apneas and hypopneas with and without blood oxygen desaturations, and spontaneous arousals. Stronger arousal causes were hypothesized to lead to larger and faster responses., Methods and Procedures: Photoplethysmogram signal segments during and around respiratory and spontaneous arousals of 876 suspected obstructive sleep apnea patients were analyzed. Logistic functions were fit to the mean instantaneous frequency and instantaneous amplitude of the signal to detect the responses. Response intensities and timings were compared between arousals of different causes., Results: The majority of the studied arousals induced photoplethysmogram responses. The frequency response was more intense ([Formula: see text]) after respiratory than spontaneous arousals, and after arousals caused by apneas compared to those caused by hypopneas. The amplitude response was stronger ([Formula: see text]) following hypopneas associated with blood oxygen desaturations compared to those that were not. The delays of these responses relative to the electroencephalogram arousal start times were the longest ([Formula: see text]) after arousals caused by apneas and the shortest after spontaneous arousals and arousals caused by hypopneas without blood oxygen desaturations., Conclusion: The presence and type of an airway obstruction and the presence of a blood oxygen desaturation affect the intensity and the timing of photoplethysmogram responses to arousals from sleep., Clinical Impact: The photoplethysmogram responses could be used for detecting arousals and assessing their intensity, and the individual variation in the response intensity and timing may hold diagnostically significant information., (© 2024 The Authors.)

Objective: Hypoxic load is one of the main characteristics of obstructive sleep apnea (OSA) contributing to sympathetic overdrive and weakened cardiorespiratory coupling (CRC). Whether this association changes with increasing hypoxic load has remained obscure. Therefore, we aimed to study our hypothesis that increasing hypoxic load acutely decreases the CRC., Methods: We retrospectively analyzed the electrocardiography and nasal pressure signals in 5-min segment pairs (n = 36 926) recorded during clinical polysomnographies of 603 patients with suspected OSA. The segment pairs were pooled into five groups based on the hypoxic load severity described with the the total integrated area under the blood oxygen saturation curve during desaturations. In these severity groups, we determined the frequency-domain heart rate variability (HRV) parameters, the HRV and respiratory high-frequency (HF, 0.15-0.4 Hz) peaks, and the difference between those peaks. We also computed the spectral HF coherence between HRV and respiration in the HF band., Results: The ratio of low-frequency (LF, 0.04-0.15 Hz) to HF power increased from 1.047 to 1.805 (p < 0.001); the difference between the HRV and respiratory HF peaks increased from 0.001 Hz to 0.039 Hz (p < 0.001); and the spectral coherence between HRV and respiration in the HF band decreased from 0.813 to 0.689 (p < 0.001) as the hypoxic load increased., Conclusion and Significance: The vagal modulation decreases and CRC weakens significantly with increasing hypoxic load. Thus, the hypoxic load could be utilized more thoroughly in contemporary OSA diagnostics to better assess the severity of OSA-related cardiac stress.

Objective: We aimed to investigate how acute and long-term effects of atrial arrhythmias affect the desaturation severity and characteristics determined from the oxygen saturation signal in obstructive sleep apnea (OSA) patients., Methods: 520 suspected OSA patients were included in retrospective analyses. Eight desaturation area and slope parameters were calculated from blood oxygen saturation signals recorded during polysomnographic recordings. Patients were grouped based on whether they had previously diagnosed atrial arrhythmia (i.e., atrial fibrillation (AFib) or atrial flutter) or not. Furthermore, patients with a previous atrial arrhythmia diagnosis were sub-grouped based on whether they had continuous AFib or sinus rhythm during the polysomnographic recordings. Empirical cumulative distribution functions and linear mixed models were utilized to investigate the connection between diagnosed atrial arrhythmia and the desaturation characteristics., Results: Patients with previous atrial arrhythmia diagnosis had greater desaturation recovery area when the 100% oxygen saturation baseline reference was considered (β = 0.150--0.127, p ≤ 0.039) and more gradual recovery slopes (β = -0.181 to -0.199, p < 0.004) than patients without a previous atrial arrhythmia diagnosis. Furthermore, patients with AFib had more gradual oxygen saturation fall and recovery slopes than patients with sinus rhythm., Conclusion: Desaturation recovery characteristics in the oxygen saturation signal contains essential information about the cardiovascular response to hypoxemic periods., Significance: More comprehensive consideration of the desaturation recovery section could provide more detailed information about OSA severity, for example when developing new diagnostic parameters.

Obstructive sleep apnea is a disorder characterized by partial or complete airway obstructions during sleep. Our previously published algorithms use the minimally invasive nasal pressure signal routinely collected during diagnostic polysomnography (PSG) to segment breaths and estimate airflow limitation (using flow:drive) and minute ventilation for each breath. The first aim of this study was to investigate the effect of airflow signal quality on these algorithms, which can be influenced by oronasal breathing and signal-to-noise ratio (SNR). It was hypothesized that these algorithms would make inaccurate estimates when the expiratory portion of breaths is attenuated to simulate oronasal breathing, and pink noise is added to the airflow signal to reduce SNR. At maximum SNR and 0% expiratory amplitude, the average error was 2.7% for flow:drive, -0.5% eupnea for ventilation, and 19.7 milliseconds for breath duration (n = 257,131 breaths). At 20 dB and 0% expiratory amplitude, the average error was -15.1% for flow:drive, 0.1% eupnea for ventilation, and 28.4 milliseconds for breath duration (n = 247,160 breaths). Unexpectedly, simulated oronasal breathing had a negligible effect on flow:drive, ventilation, and breath segmentation algorithms across all SNRs. Airflow SNR ≥ 20 dB had a negligible effect on ventilation and breath segmentation, whereas airflow SNR ≥ 30 dB had a negligible effect on flow:drive. The second aim of this study was to explore the possibility of correcting these algorithms to compensate for airflow signal asymmetry and low SNR. An offset based on estimated SNR applied to individual breath flow:drive estimates reduced the average error to ≤ 1.3% across all SNRs at patient and breath levels, thereby facilitating for flow:drive to be more accurately estimated from PSGs with low airflow SNR.Clinical Relevance- This study demonstrates that our airflow limitation, ventilation, and breath segmentation algorithms are robust to reduced airflow signal quality.

Objective: Obstructive sleep apnea (OSA) is diagnosed using the apnea-hypopnea index (AHI), which is the average number of respiratory events per hour of sleep. Recently, machine learning algorithms for automatic AHI assessment have been developed, but many of them do not consider the individual sleep stages or events. In this study, we aimed to develop a deep learning model to simultaneously score both sleep stages and respiratory events. The hypothesis was that the scoring and subsequent AHI calculation could be performed utilizing pulse oximetry data only., Methods: Polysomnography recordings of 877 individuals with suspected OSA were used to train the deep learning models. The same architecture was trained with three different input signal combinations (model 1: photoplethysmogram (PPG) and oxygen saturation (SpO 2 ); model 2: PPG, SpO 2 , and nasal pressure; model 3: SpO 2 , nasal pressure, electroencephalogram (EEG), oronasal thermocouple, and respiratory belts)., Results: Model 1 reached comparative performance with models 2 and 3 for estimating the AHI (model 1 intraclass correlation coefficient (ICC) = 0.946; model 2 ICC = 0.931; model 3 ICC = 0.945), and REM-AHI (model 1 ICC = 0.912; model 2 ICC = 0.921; model 3 ICC = 0.883). The automatic sleep staging accuracies (wake/N1/N2/N3/REM) were 69%, 70%, and 79% with models 1, 2, and 3, respectively., Conclusion: AHI can be estimated using pulse oximetry-based automatic scoring. Explicit scoring of sleep stages and respiratory events allows visual validation of the automatic analysis, and provides information on OSA phenotypes., Significance: Automatic scoring of sleep stages and respiratory events with a simple pulse oximetry setup could allow cost-effective, large-scale screening of OSA.

Reliable, automated, and user-friendly solutions for the identification of sleep stages in home environment are needed in various clinical and scientific research settings. Previously we have shown that signals recorded with an easily applicable textile electrode headband (FocusBand, T 2 Green Pty Ltd) contain characteristics similar to the standard electrooculography (EOG, E1-M2). We hypothesize that the electroencephalographic (EEG) signals recorded using the textile electrode headband are similar enough with standard EOG in order to develop an automatic neural network-based sleep staging method that generalizes from diagnostic polysomnographic (PSG) data to ambulatory sleep recordings of textile electrode-based forehead EEG. Standard EOG signals together with manually annotated sleep stages from clinical PSG dataset (n = 876) were used to train, validate, and test a fully convolutional neural network (CNN). Furthermore, ambulatory sleep recordings including a standard set of gel-based electrodes and the textile electrode headband were conducted for 10 healthy volunteers at their homes to test the generalizability of the model. In the test set (n = 88) of the clinical dataset, the model's accuracy for 5-stage sleep stage classification was 80% (κ = 0.73) using only the single-channel EOG. The model generalized well for the headband-data, reaching 82% (κ = 0.75) overall sleep staging accuracy. In comparison, accuracy of the model was 87% (κ = 0.82) in home recordings using the standard EOG. In conclusion, the CNN model shows potential on automatic sleep staging of healthy individuals using a reusable electrode headband in a home environment.

Objective: We aimed to investigate the differences in electroencephalogram (EEG) gamma power (30-40 Hz) of respiratory arousals between varying types and severities of respiratory events, and in different sleep stages., Methods: Power spectral densities of EEG signals from diagnostic Type I polysomnograms of 869 patients with clinically suspected obstructive sleep apnea were investigated. Arousal gamma powers were compared between sleep stages, and between the type (obstructive apnea and hypopnea) and duration (10-20 s, 20-30 s, and >30 s) of the related respiratory event. Moreover, we investigated whether the presence of a ≥3% blood oxygen desaturation influenced the arousal gamma power., Results: Gamma power of respiratory arousals was the lowest in Stage R sleep and increased from Stage N1 towards Stage N3. Gamma power was higher when the arousals were caused by obstructive apneas compared to hypopneas. Moreover, arousal gamma power increased when the duration of the related apnea increased, whereas an increase in the hypopnea duration did not have a similar effect. Furthermore, respiratory events associated with desaturations increased the arousal gamma power more than respiratory events not associated with desaturations., Conclusion: Gamma power of respiratory arousals increased towards deeper sleep and as the severity of the related respiratory event increased in terms of type and duration of obstruction, and presence of desaturation., Significance: As increased gamma power might indicate a greater shift towards wakefulness, the present findings demonstrate that the respiratory arousal intensity and the magnitude of sleep disruption may vary depending on the event type and severity.

The diagnosis of obstructive sleep apnea is based on daytime symptoms and the frequency of respiratory events during the night. The respiratory events are scored manually from polysomnographic recordings, which is time-consuming and expensive. Therefore, automatic scoring methods could considerably improve the efficiency of sleep apnea diagnostics and release the resources currently needed for manual scoring to other areas of sleep medicine. In this study, we trained a long short-term memory neural network for automatic scoring of respiratory events using input signals from peripheral blood oxygen saturation, thermistor-airflow, nasal pressure -airflow, and thorax respiratory effort. The signals were extracted from 887 in-lab polysomnography recordings. 787 patients with suspected sleep apnea were used to train the neural network and 100 patients were used as an independent test set. The epoch-wise agreement between manual and automatic neural network scoring was high (88.9%, κ = 0.728). In addition, the apnea-hypopnea index (AHI) calculated from the automated scoring was close to the manually determined AHI with a mean absolute error of 3.0 events/hour and an intraclass correlation coefficient of 0.985. The neural network approach for automatic scoring of respiratory events achieved high accuracy and good agreement with manual scoring. The presented neural network could be used for analysis of large research datasets that are unfeasible to score manually, and has potential for clinical use in the future In addition, since the neural network scores individual respiratory events, the automatic scoring can be easily reviewed manually if desired.

Traditional sleep staging with non-overlapping 30-second epochs overlooks multiple sleep-wake transitions. We aimed to overcome this by analyzing the sleep architecture in more detail with deep learning methods and hypothesized that the traditional sleep staging underestimates the sleep fragmentation of obstructive sleep apnea (OSA) patients. To test this hypothesis, we applied deep learning-based sleep staging to identify sleep stages with the traditional approach and by using overlapping 30-second epochs with 15-, 5-, 1-, or 0.5-second epoch-to-epoch duration. A dataset of 446 patients referred for polysomnography due to OSA suspicion was used to assess differences in the sleep architecture between OSA severity groups. The amount of wakefulness increased while REM and N3 decreased in severe OSA with shorter epoch-to-epoch duration. In other OSA severity groups, the amount of wake and N1 decreased while N3 increased. With the traditional 30-second epoch-to-epoch duration, only small differences in sleep continuity were observed between the OSA severity groups. With 1-second epoch-to-epoch duration, the hazard ratio illustrating the risk of fragmented sleep was 1.14 (p = 0.39) for mild OSA, 1.59 (p < 0.01) for moderate OSA, and 4.13 (p < 0.01) for severe OSA. With shorter epoch-to-epoch durations, total sleep time and sleep efficiency increased in the non-OSA group and decreased in severe OSA. In conclusion, more detailed sleep analysis emphasizes the highly fragmented sleep architecture in severe OSA patients which can be underestimated with traditional sleep staging. The results highlight the need for a more detailed analysis of sleep architecture when assessing sleep disorders.

The identification of sleep stages is essential in the diagnostics of sleep disorders, among which obstructive sleep apnea (OSA) is one of the most prevalent. However, manual scoring of sleep stages is time-consuming, subjective, and costly. To overcome this shortcoming, we aimed to develop an accurate deep learning approach for automatic classification of sleep stages and to study the effect of OSA severity on the classification accuracy. Overnight polysomnographic recordings from a public dataset of healthy individuals (Sleep-EDF, n = 153) and from a clinical dataset (n = 891) of patients with suspected OSA were used to develop a combined convolutional and long short-term memory neural network. On the public dataset, the model achieved sleep staging accuracy of 83.7% (κ = 0.77) with a single frontal EEG channel and 83.9% (κ = 0.78) when supplemented with EOG. For the clinical dataset, the model achieved accuracies of 82.9% (κ = 0.77) and 83.8% (κ = 0.78) with a single EEG channel and two channels (EEG+EOG), respectively. The sleep staging accuracy decreased with increasing OSA severity. The single-channel accuracy ranged from 84.5% (κ = 0.79) for individuals without OSA diagnosis to 76.5% (κ = 0.68) for patients with severe OSA. In conclusion, deep learning enables automatic sleep staging for suspected OSA patients with high accuracy and expectedly, the accuracy decreased with increasing OSA severity. Furthermore, the accuracies achieved in the public dataset were superior to previously published state-of-the-art methods. Adding an EOG channel did not significantly increase the accuracy. The automatic, single-channel-based sleep staging could enable easy, accurate, and cost-efficient integration of EEG recording into diagnostic ambulatory recordings.

This article combines Rorschach Comprehensive System (CS; Exner, 1990, 1993) data from four projects conducted in Finland between 1990 and 1995. The projects studied a stratified random sample of Finnish nonpatients, a cohort of twins, a group of elderly men, and a random sample collected to investigate sleep difficulties. The 343 records from these four studies provide a representative survey of Rorschach responding throughout the Finnish population.