Obstructive sleep apnea (OSA) is a prevalent disorder affecting approximately a billion people globally. Traditional diagnostic metrics from polysomnography (PSG) such as the apnea hypopnea index (AHI) are limited in predicting OSA-related impacts. This study aims to leverage machine learning (ML) methods to enhance PSG prediction of three outcomes: daytime sleepiness (defined as Epworth Sleepiness Scale >10), insomnia (Insomnia Severity Index >15) and cognitive impairment (Montreal Cognitive Assessment < 25) in patients with moderate to severe OSA. This pilot study utilized a subset of Canadian Sleep and Circadian Network participants (patients with suspected OSA recruited from academic sleep centres). Advanced signal processing was used to derive 790 features from PSG European Data Format (edf) files including: respiratory events, heart rate variations, limb movements, and EEG based metrics from leads C3/C4 (e.g., sleep stages, spindle metrics, power frequencies, sleep depth, arousal intensity). 541 participants with moderate to severe OSA (AHI>15/hr) were included. Python 3.11.6 was used for analysis. For each outcome, dimensionality reduction was done using Lasso Regression, Principal Component Analysis (PCA), and Recursive Feature Elimination (RFE). Binary classification models with Logistic Regression (LR), Support Vector Classification (SVC), Random Forest (RF), Multi-Layer Perceptron (MLP), Gaussian Naïve bayes, and XGBoost were then used (18 models tested). Model accuracy was assessed using 5-fold cross validation. Models that employed RFE for feature selection and LR for classification (based on 50-70 features depending on outcome) yielded the best performance. The average accuracy/F1 values across all target outcomes were 0.71/0.71 for sleepiness, 0.68/0.61 for insomnia, and 0.62/0.62 for cognitive impairment. However, accuracy of all the ML models surpassed the predictive accuracy of AHI alone (accuracy of 0.55, 0.60, 0.53 using logistic regression). This preliminary study supports the concept of applying advanced signal processing and ML techniques to PSG to help predict OSA-related outcomes. Future research with larger sample sizes, more diverse patients, more refined ML methodologies, and better feature engineering should further improve accuracy of these models. CIHR, BC Lung Association

Obstructive sleep apnea is an independent risk factor for stroke, potentially due to intermittent hypoxia (IH)-induced impairment of cerebral autoregulation. Human cerebral autoregulation during sleep is poorly characterized, and whether IH exposure during sleep alters cerebral autoregulation during sleep is unknown. In a secondary, exploratory analysis of previously collected cerebral blood flow (transcranial Doppler ultrasound measurement of peak blood velocity through the middle cerebral artery; [Formula: see text]), mean arterial pressure (MAP; finger photoplethysmography), and end-tidal partial pressure of CO2 ([Formula: see text]) data, dynamic cerebral autoregulation (dCA) was quantified using transfer function analysis gain, phase, and coherence in healthy males (n = 10; age: 26 ± 6 yr; body mass index: 24.5 ± 1.7 kg/m2; MAP: 87.5 ± 8.0 mmHg) during wakefulness and during nonrapid eye movement (NREM) sleep in normoxia or accompanied by IH. Compared with wakefulness, [Formula: see text] variability was lower during both sleep in normoxia and sleep accompanied by IH in the very low frequency (0.02-0.07 Hz) and low frequency (LF: 0.07-0.2 Hz) ranges (both comparisons, P ≤ 0.02) with MAP variability being lower in the LF range (P = 0.045); gain, phase, and coherence were similar between wakefulness and sleep (all comparisons, P ≥ 0.062). dCA measures during normoxic and IH-sleep were similar (all comparisons, P ≥ 0.09). Moreover, dCA gain and phase, and multiple and partial coherences during IH-sleep were not different between acute (<1 h) and prolonged (∼2 h) exposure (all comparisons, P ≥ 0.055) even though [Formula: see text] was lower following prolonged IH exposure (P = 0.002). These findings indicate dCA is effective during stage 2/3 NREM sleep and is not impacted by ∼2 h of sleep accompanied by IH.NEW & NOTEWORTHY This study found that dynamic cerebral autoregulation (dCA) is not different between wakefulness and stages 2/3 nonrapid eye movement (NREM) sleep in young healthy males and that ∼2 h of intermittent hypoxia exposure during sleep mimicking that experienced by patients with moderate-to-severe obstructive sleep apnea does not alter NREM stage 2/3 sleep dCA. This maintained dCA during sleep may result from the reduced cerebral blood flow and blood pressure variability observed during sleep.

Standard metrics of obstructive sleep apnea (OSA) severity, such as apnea-hypopnea index (AHI), do not correlate well with daytime sleepiness. In OSA patients, there is considerable variability in the severity of hypoxemia and the electroencephalographic (EEG) response associated with respiratory events. We hypothesized that nocturnal hypoxemia and EEG responses would be associated with subjective daytime sleepiness in patients with moderate-to-severe OSA. We used cross-sectional data from participants enrolled in a Canadian Sleep and Circadian Network’s clinical cohort of patients with suspected OSA who had moderate-to-severe OSA (AHI>15/hr). Event-related hypoxemia was quantified as the mean event-related hypoxic burden (HBev): mean area under the oxygen desaturation curve. EEG responses to respiratory events were quantified by calculating the power ratio (log(mean absolute power 6s after / mean absolute power 6s before the event)) across EEG frequency bands; subject-specific responses were defined as the mean EEG response across all events. We calculated an overall Brain Response to Events (BReTE) metric by summing power ratios across all frequency bands. Subjective daytime sleepiness was assessed by the Epworth Sleep Scale (ESS) with an ESS>10 considered indicative of daytime sleepiness). Logistic regression, controlling for age, body mass index, race, sex, AHI and comorbidities was employed to investigate hypothesized associations. We studied 468 patients (40%female) with a median [IQR] age=56 years [46,63], AHI=43events/hr [23,87], HBev=1.87%min [1.24,2.69]. More severe hypoxemia and a lower EEG response were independently associated with higher odds of daytime sleepiness. One standard deviation (SD) increase in HBev was associated with 41% higher odds of daytime sleepiness (95% CI: 1.14-1.75,p< 0.01), while a one SD increase in BReTE was associated with 27% lower odds of daytime sleepiness (95%CI: 0.58-0.91,p< 0.01). Blunted EEG responses were more prevalent across beta and gamma EEG frequencies. AHI was not associated with daytime sleepiness. Greater event-related hypoxemia and blunted EEG responses were independently associated with subjective daytime sleepiness in moderate-to-severe OSA, emphasizing the pivotal roles of hypoxemia and EEG in evaluating daytime sleepiness in OSA. EEG findings could be the result of adaptations to chronic OSA exposure, resulting in reduced arousal responses. Future prospective studies should explore these intricate associations further.

Obstructive sleep apnea-related hypoxemia, measured by hypoxic burden (HB), is associated with chronic kidney disease (CKD). Obstructive sleep apnea-related autonomic response may also be associated with CKD. This study examined whether individuals with high HB and varying autonomic responses to obstructive sleep apnea have a different risk of CKD progression compared to those with low HB. Polysomnography data from the multicenter Canadian Sleep and Circadian Network cohort were analyzed. HB was defined as the area under event-related oxygen desaturation curves during sleep. Autonomic responses were assessed using “vasoconstriction burden” (area under photoplethysmography declines, reflecting vascular reactivity) and heart rate response to events (reflecting cardiac autonomic response). Estimated glomerular filtration rate and urine albumin:creatinine ratio were used to identify participants at risk of CKD progression. This risk was compared across individuals with high HB (≥ median) and varying levels of autonomic responses relative to those with low HB. Data from 421 participants were analyzed. The odds ratio of CKD progression was higher in those with high vs low HB. Compared to the low HB group, individuals with high HB and low vasoconstriction burden (lowest quartile) were at increased risk of CKD progression (odds ratio [95

BACKGROUND:Individuals with obstructive sleep apnoea (OSA) are at increased risk of cognitive impairment. However, the physiological mechanisms that link OSA to this impairment are unclear. We assessed the association between novel physiological biomarkers (i.e. respiratory event-related electroencephalography (EEG) activity and autonomic responses) and the risk of cognitive impairment. METHODS:Participants with OSA (apnoea-hypopnoea index ≥5 events·h-1) from the Canadian Sleep and Circadian Network observational cohort were studied. Brain Response to Event (BReTE) was derived from EEG power (defined as mean (median post-event power/median pre-event power) (frequency range: 0.5-50 Hz)) for each individual. Event-related autonomic responses were measured by heart rate response to events (ΔHR: the difference between maximum post-event heart rate and minimum heart rate during event) and photoplethysmography (PPG)-derived vasoconstriction activity (event-related area and depth of PPG decline). Cognitive performance was assessed using the Montreal Cognitive Assessment (MoCA), Wechsler Digit Symbol Coding (DSC) and Rey Auditory Verbal Learning Test-Delayed Recall (RAVLT-DR). Multiple logistic regression examined the independent associations between biomarkers and outcomes. RESULTS:We studied 537 individuals (42% female) with a median age of 55 years. In fully adjusted models, each 1sd decrease in BReTE was associated with higher odds of poor cognitive performance indicated by MoCA <26 (OR 1.42, 95% CI 1.13-1.79; p=0.003), DSC <25th percentile (OR 1.35, 95% CI 1.02-1.84; p=0.04) and RAVLT-DR <25th percentile (OR 1.50, 95% CI 1.13-2.02; p=0.007). Additionally, those with low ΔHR compared to the mid-range group were at increased risk of poor cognitive performance. Vasoconstriction indices were not associated with cognitive performance. CONCLUSION:Blunted EEG and heart rate responses to respiratory events are linked to poorer cognitive performance in OSA, highlighting the value of EEG in identifying individuals at risk for cognitive impairment.

Study Objectives Obstructive sleep apnea (OSA) increases the risk of cognitive impairment. Measures of sleep microarchitecture from EEG may help identify patients at risk of this complication.Methods Participants with suspected OSA (n = 1142) underwent in-laboratory polysomnography and completed sleep and medical history questionnaires, and tests of global cognition (Montreal Cognitive Assessment, MoCA), memory (Rey Auditory Verbal Learning Test, RAVLT) and information processing speed (Digit-Symbol Coding, DSC). Associations between cognitive scores and stage 2 non-rapid eye movement (NREM) sleep spindle density, power, frequency and %-fast (12-16Hz), odds-ratio product (ORP), normalized EEG power (EEGNP), and the delta:alpha ratio were assessed using multivariable linear regression (MLR) adjusted for age, sex, education, and total sleep time. Mediation analyses were performed to determine if sleep microarchitecture indices mediate the negative effect of OSA on cognition.Results All spindle characteristics were lower in participants with moderate and severe OSA (p <= .001, vs. no/mild OSA) and positively associated with MoCA, RAVLT, and DSC scores (false discovery rate corrected p-value, q <= 0.026), except spindle power which was not associated with RAVLT (q = 0.185). ORP during NREM sleep (ORPNREM) was highest in severe OSA participants (p <= .001) but neither ORPNREM (q >= 0.230) nor the delta:alpha ratio were associated with cognitive scores in MLR analyses (q >= 0.166). In mediation analyses, spindle density and EEGNP (p >= .048) mediated moderate-to-severe OSA's negative effect on MoCA scores while ORPNREM, spindle power, and %-fast spindles mediated OSA's negative effect on DSC scores (p <= .018).Conclusions Altered spindle activity, ORP and normalized EEG power may be important contributors to cognitive deficits in patients with OSA. Graphical Abstract

Rationale: Obstructive sleep apnea (OSA) severity is typically assessed by the apnea-hypopnea index (AHI), a frequency-based metric that allocates equal weight to all respiratory events. However, more severe events may have a greater physiologic impact. Objectives: The purpose of this study was to determine whether the degree of event-related hypoxemia would be associated with the postevent physiologic response. Methods: Patients with OSA (AHI, ⩾5/h) from the multicenter Canadian Sleep and Circadian Network cohort were studied. Using mixed-effect linear regression, we examined associations between event-related hypoxic burden (HBev) assessed by the area under the event-related oxygen saturation recording with heart rate changes (ΔHRev), vasoconstriction (vasoconstriction burden [VCBev] assessed with photoplethysmography), and electroencephalographic responses (power ratio before and after events). Results: Polysomnographic recordings from 658 patients (median [interquartile range] age, 55.00 [45.00, 64.00] yr; AHI, 27.15 [14.90, 64.05] events/h; 42% female) were included in the analyses. HBev was associated with an increase in all physiologic responses after controlling for age, sex, body mass index, sleep stage, total sleep time, and study centers; for example, 1 standard deviation increase in HBev was associated with 0.21 [95% confidence interval, 0.2, 0.22], 0.08 [0.08, 0.09], and 0.22 [0.21, 0.23] standard deviation increases in ΔHRev, VCBev, and β-power ratio, respectively. Conclusions: Increased event-related hypoxic burden was associated with greater responses across a broad range of physiologic signals. Future metrics that incorporate information about the variability of these physiologic responses may have promise in providing a more nuanced assessment of OSA severity.

Respiratory and nonrespiratory sleep disorders are common and underrecognized in patients with both non–dialysis-dependent chronic kidney disease (CKD) and end-stage kidney disease (ESKD). The relationship between sleep apnea and kidney disease is bidirectional and thought to contribute to morbidity and mortality. Treatment of sleep apnea is aimed at improving kidney function as well as upper airway and ventilatory stability. Restless legs syndrome, periodic limb movement disorder, insomnia, and hypersomnia have a higher prevalence in patients with CKD and ESKD than in the general population. Management of these disorders includes both conventional therapy and specific interventions to address reduced kidney function.

Abstract Background Previous research has suggested that alternative (respiratory) care providers (ACP) may provide affordable, accessible care for sleep-disordered breathing (SDB) that decreases wait-times and improves clinical outcomes. The objective of this study was to compare ACP-led and sleep physician-led care for SDB on patient reported outcome and experiences, with a focus on general and health-related quality of life, sleepiness, and patient satisfaction. Methods We conducted a secondary analysis of a randomized trial in which participants with severe SDB were assigned to either ACP-led or physician-led management. We created longitudinal linear mixed models to assess the impacts of treatment arm and timepoint on total and domain-level scores of multiple patient-reported outcome measures and patient-reported experience measures. Results Patients in both treatment arms (ACP-led n = 81; sleep-physician = 75) reported improved outcomes on the Sleep Apnea Quality of Life Index, Health Utilities Index, and Epworth Sleepiness Scale. Patients in each group had similar and clinically meaningful improvements on domains assessing cognition, emotion, and social functioning. The linear mixed models suggested no significant difference between treatment arms on the patient-reported outcomes. However, scores significantly improved over time. Conclusions Management of SDB using ACPs was comparable to physician-led care, as measured bypatient-reported outcome and experience measures. While loss to follow-up limits our findings, these results provide some support for the use of this novel health service delivery model to improve access to high quality SDB care. Clinical trial registration This is analysis of data from the study registered Clinicaltrials.gov (NCT02191085).

Study objectives Although the importance of upper airway assessment in the consideration of obstructive sleep apnea (OSA) is recognized, there are current limitations in our approach to assessment. Methods We convened a group of experts in upper airway neuromuscular physiology and anatomy, sleep apnea endophenotypes, novel therapeutics and sleep epidemiology to summarize existing literature and delineate future opportunities to utilize and incorporate innovative and less invasive techniques focused on upper airway neuromuscular physiology to assess and manage OSA. Results In OSA, genioglossus electromyogram (EMG) activity is reduced during sleep onset with higher levels observed during wakefulness compared to controls. Surface EMG recordings are limited due to distance from the actual muscle and while needle EMG offers more direct assessment, this approach is more invasive. Novel alternatives overcoming these limitations to assess upper airway neuromuscular physiology in OSA may therefore prove beneficial. Specifically, such an approach would facilitate identification of upstream prognostic biomarkers of OSA clinical trajectory and offer more informative mechanistic data. Novel approaches to neuromuscular assessment in OSA would enhance phenotyping to predict better tolerance to positive airway pressure therapy and set the stage to target neuromuscular function and upper airway anatomy. A quantifiable and repeatable neuromuscular physiologic metric has potential to facilitate a precision medicine strategy and personalize treatment, including measuring treatment response to neurophysiologic-focused interventions including hypoglossal nerve stimulation (HGNS), myofunctional therapy and neuromuscular electrical stimulation. A key area for future investigation is whether observed neuromuscular changes can identify patients at future risk of OSA, facilitating early intervention or prevention strategies. Conclusions Overall, recognizing the critical contributions of abnormalities of upper airway neuromuscular function to the pathophysiology of OSA, it may be important to find accurate and reproducible neurophysiological assessments to address existing knowledge gaps in OSA assessment and management.

Recent studies have found associations between obstructive sleep apnea and cognitive decline. The underlying mechanisms are still unclear. Here, we investigate the associations between changes in micro-architecture, specifically sleep spindles, and cognitive function in community-dwelling middle-aged and older adults, some with obstructive sleep apnea, with a focus on sex differences. A total of 125 voluntary participants (mean age 66.0 ± 6.4 years, 64 females) from a larger cohort (participants of the Brain in Motion Studies I and II) underwent 1 night of in-home polysomnography and a neuropsychological battery (sleep and cognitive testing were conducted within 2 weeks of each other). A semi-automatic computerized algorithm was used to score polysomnography data and detect spindle characteristics in non-rapid eye movement Stages 2 and 3 in both frontal and central electrodes. Based on their apnea-hypopnea index, participants were divided into those with no obstructive sleep apnea (apnea-hypopnea index < 5 per hr, n = 21), mild obstructive sleep apnea (5 ≥ apnea-hypopnea index < 15, n = 47), moderate obstructive sleep apnea (15 ≥ apnea-hypopnea index < 30, n = 34) and severe obstructive sleep apnea (apnea-hypopnea index ≥ 30, n = 23). There were no significant differences in spindle characteristics between the four obstructive sleep apnea severity groups. Spindle density and percentage of fast spindles were positively associated with some verbal fluency measures on the cognitive testing. Sex might be linked with these associations. Biological sex could play a role in the associations between spindle characteristics and some verbal fluency measures. Obstructive sleep apnea severity was not found to be a contributing factor in this non-clinical community-dwelling cohort.

Study Objectives The response of sleep depth to CPAP in patients with OSA is unpredictable. The odds-ratio-product (ORP) is a continuous index of sleep depth and wake propensity that distinguishes different sleep depths within sleep stages, and different levels of vigilance during stage wake. When expressed as fractions of time spent in different ORP deciles, nine distinctive patterns are found. Only three of these are associated with OSA. We sought to determine whether sleep depth improves on CPAP exclusively in patients with these three ORP patterns. Methods ORP was measured during the diagnostic and therapeutic components of 576 split-night polysomnographic (PSG) studies. ORP architecture in the diagnostic section was classified into one of the nine possible ORP patterns and the changes in sleep architecture were determined on CPAP for each of these patterns. ORP architecture was similarly determined in the first half of 760 full-night diagnostic PSG studies and the changes in the second half were measured to control for differences in sleep architecture between the early and late portions of sleep time in the absence of CPAP. Results Frequency of the three ORP patterns increased progressively with the apnea-hypopnea index. Sleep depth improved significantly on CPAP only in the three ORP patterns associated with OSA. Changes in CPAP in the other six patterns, or in full diagnostic PSG studies, were insignificant or paradoxical. Conclusions ORP architecture types can identify patients in whom OSA adversely affects sleep and whose sleep is expected to improve on CPAP therapy.