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

Study Objectives Accurate identification of sleep stages is essential in the diagnosis of sleep disorders (e.g. obstructive sleep apnea [OSA]) but relies on labor-intensive electroencephalogram (EEG)-based manual scoring. Furthermore, long-term assessment of sleep relies on actigraphy differentiating only between wake and sleep periods without identifying specific sleep stages and having low reliability in identifying wake periods after sleep onset. To address these issues, we aimed to develop an automatic method for identifying the sleep stages from the photoplethysmogram (PPG) signal obtained with a simple finger pulse oximeter. Methods PPG signals from the diagnostic polysomnographies of susptected OSA patients (n = 894) were utilized to develop a combined convolutional and recurrent neural network. The deep learning model was trained individually for three-stage (wake/NREM/REM), four-stage (wake/N1+N2/N3/REM), and five-stage (wake/N1/N2/N3/REM) classification of sleep. Results The three-stage model achieved an epoch-by-epoch accuracy of 80.1% with Cohen’s κ of 0.65. The four- and five-stage models achieved 68.5% (κ = 0.54), and 64.1% (κ = 0.51) accuracies, respectively. With the five-stage model, the total sleep time was underestimated with a mean bias error (SD) of of 7.5 (55.2) minutes. Conclusion The PPG-based deep learning model enabled accurate estimation of sleep time and differentiation between sleep stages with a moderate agreement to manual EEG-based scoring. As PPG is already included in ambulatory polygraphic recordings, applying the PPG-based sleep staging could improve their diagnostic value by enabling simple, low-cost, and reliable monitoring of sleep and help assess otherwise overlooked conditions such as REM-related OSA.

Low long-term heart rate variability (HRV), often observed in obstructive sleep apnea (OSA) patients, is a known risk factor for cardiovascular diseases. However, it is unclear how the type or duration of individual respiratory events modulate ultra-short-term HRV and beat-to-beat intervals (RR intervals). We aimed to examine the sex-specific changes in RR interval and ultra-short-term HRV during and after apneas and hypopneas of various durations. Electrocardiography signals, recorded as a part of clinical polysomnography, of 758 patients (396 men) with suspected OSA were analysed retrospectively. Average RR intervals and time-domain HRV parameters were determined during the respiratory event and the 15-s period immediately after the event. Parameters were analysed in three pooled sex-specific subgroups based on the respiratory event duration (10–20 s, 20–30 s, and > 30 s) separately for apneas and hypopneas. We observed that RR intervals shortened after the respiratory events and the magnitude of these changes increased in both sexes as the respiratory event duration increased. Furthermore, ultra-short-term HRV generally increased as the respiratory event duration increased. Apneas caused higher ultra-short-term HRV and a stronger decrease in RR interval compared to hypopneas. In conclusion, the respiratory event type and duration modulate ultra-short-term HRV and RR intervals. Considering HRV and the respiratory event characteristics in the diagnosis of OSA could be useful when assessing the cardiac consequences of OSA in a more detailed manner.

The severity of obstructive sleep apnea (OSA) is classified using apnea-hypopnea index (AHI). Accurate determination of AHI currently requires manual analysis and complicated registration setup making it expensive and labor intensive. Partially for these reasons, OSA is a heavily underdiagnosed disease as only 7% of women and 18% of men suffering from OSA have diagnosis. To resolve these issues, we introduce an artificial neural network (ANN) that estimates AHI and oxygen desaturation index (ODI) using only the blood oxygen saturation signal (SpO2), recorded during ambulatory polygraphy, as an input. Therefore, hypopneas associated only with an arousal were not considered in this study. SpO2 signals from 1692 patients were used for training and 99 for validation. Two test sets were used consisting of 198 and 1959 patients. In the primary test set, the median absolute errors of ANN estimated AHI and ODI were 0.78 events/hour and 0.68 events/hour respectively. Based on the ANN estimated AHI and ODI, 90.9% and 94.4% of the test patients were classified into the correct OSA severity category. In conclusion, AHI and ODI can be reliably determined using neural network analysis of SpO2 signal. The developed method may enable a more affordable screening of OSA.

Summary The severity of obstructive sleep apnea is clinically assessed mainly using the apnea–hypopnea index. Based on the apnea–hypopnea index, patients are classified into four severity groups: non‐obstructive sleep apnea (apnea–hypopnea index < 5); mild (5 ≤ apnea–hypopnea index < 15); moderate (15 ≤ apnea–hypopnea index < 30); and severe obstructive sleep apnea (apnea–hypopnea index ≥ 30). However, these thresholds lack solid clinical and scientific evidence. We hypothesize that the current apnea–hypopnea index thresholds are not optimal despite their global use, and aim to assess this clinical shortcoming by optimizing the thresholds with respect to the risk of all‐cause mortality. We analysed ambulatory polygraphic recordings of 1,783 patients with suspected obstructive sleep apnea (mean follow‐up 18.3 years). We simulated 79,079 different threshold combinations in 100 randomized subgroups of the population and studied the relative risk of all‐cause mortality corresponding to each combination and randomization. The optimal thresholds were chosen according to three criteria: (a) the hazard ratios increase linearly between severity groups towards more severe obstructive sleep apnea; (b) each group includes at least 15% of the study population; (c) group sizes decrease with increasing obstructive sleep apnea severity. The risk of all‐cause mortality varied greatly across simulations; the threshold defining non‐obstructive sleep apnea group having the largest effect on the hazard ratios. The apnea–hypopnea index threshold combination of 3‐9‐24 was optimal in most of the subgroups. In conclusion, the assessment of obstructive sleep apnea severity based on the current apnea–hypopnea index thresholds is not optimal. Our novel approach provides methods for optimizing apnea–hypopnea index‐based severity classification, and the revised thresholds better differentiate patients into severity groups, ensuring that an increase in the severity corresponds to an increase in the risk of all‐cause mortality.

Obstructive sleep apnea (OSA)-related intermittent hypoxaemia is a potential risk factor for different OSA comorbidities, for example cardiovascular disease. However, conflicting results are found as to whether intermittent hypoxaemia is associated with impaired vigilance. Therefore, we aimed to investigate how desaturation characteris-

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, thermistorairflow, 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.

Study ObjectivesObesity, older age, and male sex are recognized risk factors for sleep apnea. However, it is unclear whether the severity of hypoxic burden, an essential feature of sleep apnea, is associated with the risk of sleep apnea worsening. Thus, we investigated our hypothesis that the worsening of sleep apnea is expedited in individuals with more severe desaturations.MethodsThe blood oxygen saturation (SpO2) signals of 805 Sleep Heart Health Study participants with mild sleep apnea [5 ≤ oxygen desaturation index (ODI) &lt; 15] were analyzed at baseline and after a mean follow-up time of 5.2 years. Linear regression analysis, adjusted for relevant covariates, was utilized to study the association between baseline SpO2-derived parameters and change in sleep apnea severity, determined by a change in ODI. SpO2-derived parameters, consisting of ODI, desaturation severity (DesSev), desaturation duration (DesDur), average desaturation area (avg. DesArea), and average desaturation duration (avg. DesDur), were standardized to enable comparisons between the parameters.ResultsIn the group consisting of both men and women, avg. DesDur (β = 1.594, p = 0.001), avg. DesArea (β = 1.316, p = 0.004), DesDur (β = 0.998, p = 0.028), and DesSev (β = 0.928, p = 0.040) were significantly associated with sleep apnea worsening, whereas ODI was not (β = −0.029, p = 0.950). In sex-stratified analysis, avg. DesDur (β = 1.987, p = 0.003), avg. DesArea (β = 1.502, p = 0.024), and DesDur (β = 1.374, p = 0.033) were significantly associated with sleep apnea worsening in men.ConclusionLonger and deeper desaturations are more likely to expose a patient to the worsening of sleep apnea. This information could be useful in the planning of follow-up monitoring or lifestyle counseling in the early stage of the disease.