Search

Wearable electroencephalography devices emerge as a cost-effective and ergonomic alternative to gold-standard polysomnography, paving the way for better health monitoring and sleep disorder screening. Machine learning allows to automate sleep stage classification, but trust and reliability issues have hampered its adoption in clinical applications. Estimating uncertainty is a crucial factor in enhancing reliability by identifying regions of heightened and diminished confidence. In this study, we used an uncertainty-centred machine learning pipeline, U-PASS, to automate sleep staging in a challenging real-world dataset of single-channel electroencephalography and accelerometry collected with a wearable device from an elderly population. We were able to effectively limit the uncertainty of our machine learning model and to reliably inform clinical experts of which predictions were uncertain to improve the machine learning model's reliability. This increased the five-stage sleep-scoring accuracy of a state-of-the-art machine learning model from 63.9% to 71.2% on our dataset. Remarkably, the machine learning approach outperformed the human expert in interpreting these wearable data. Manual review by sleep specialists, without specific training for sleep staging on wearable electroencephalography, proved ineffective. The clinical utility of this automated remote monitoring system was also demonstrated, establishing a strong correlation between the predicted sleep parameters and the reference polysomnography parameters, and reproducing known correlations with the apnea-hypopnea index. In essence, this work presents a promising avenue to revolutionize remote patient care through the power of machine learning by the use of an automated data-processing pipeline enhanced with uncertainty estimation., (© 2024 European Sleep Research Society.)

Obstructive sleep apnea increases morbidity and mortality risks. The most common treatment is continuous positive airway pressure, with nasal mask usage being important, but not always optimal. While most research on treatment adherence focuses on the patient, the bed partner's involvement may be detrimental. Our study aim is to obtain a European-wide picture of the bed partner's attitude and support towards continuous positive airway pressure therapy, including effects on relationship satisfaction and intimacy. The English translation of a German bed partner questionnaire, assessing relationship satisfaction and three major components (general attitude, perceived mask looks, intimacy effects) was distributed within the European Sleep Apnea Database Network and translated in participating countries' local language. Data were collected for 2 years. In total, 10 European countries (13 sleep centres) participated with 1546 questionnaires. Overall, 91% of bed partners had a positive attitude towards continuous positive airway pressure therapy, 86% perceived mask looks not negative, 64% stated no negative intimacy effects. More specifically, 71% mentioned improved sleep quality, 68% supported nightly device usage. For 41% of bed partners, relationship satisfaction increased (no change for 47%). These results were significantly more pronounced in Eastern/Southern Europe compared with Middle Europe, especially regarding intimacy effects. However, increased continuous positive airway pressure therapy length affected attitude negatively. These results provide necessary information to improve treatment strategies by including educational couple-focused approaches. Among others, we revealed that negative intimacy effects are not considered a barrier to continuous positive airway pressure adherence. These results may inspire more research identifying regional gaps with need for treatment adjustments., (© 2023 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.)

Periodic limb movements during sleep and obstructive sleep apnea are both associated with increased sympathetic tone, and have been proposed as risk factors for heart diseases and, in particular, cardiovascular disease. As sympathetic system activation may lead to dyslipidaemia, periodic limb movements during sleep could be an additional risk factor for cardiovascular disease in patients with obstructive sleep apnea. The aim of the study was to determine whether the presence of periodic limb movements during sleep affects serum lipid levels in obstructive sleep apnea. Total cholesterol, low-density lipoprotein cholesterol, high-density lipoprotein cholesterol, non- high-density lipoprotein cholesterol and triglyceride levels were investigated in 4138 patients with obstructive sleep apnea in the European Sleep Apnea Database (ESADA) cohort, divided into those with periodic limb movements during sleep index ≥ 15 per hr (n = 628) and controls (n = 3510). ANCOVA adjusted for age, sex, body mass index, apnea-hypopnea index, alcohol intake, smoking status, diabetes, insomnia and study site was used to assess differences in lipids between periodic limb movements during sleep and controls. Patients with periodic limb movements during sleep (24% female, 54.4 ± 12.1 years, body mass index 31.9 ± 5.8 kg m -2 , apnea-hypopnea index 36.7 ± 25.4 per hr) had higher triglyceride (1.81 ± 1.04 versus 1.69 ± 0.90 mmol L -1 , p = 0.002) and lower high-density lipoprotein cholesterol (1.19 ± 0.34 versus 1.24 ± 0.37 mmol L -1 , p = 0.002) levels, whilst there was no difference in either total cholesterol (4.98 ± 1.10 versus 4.94 ± 1.07 mmol L -1 ), low-density lipoprotein cholesterol (3.04 ± 0.96 versus 2.98 ± 0.98 mmol L -1 ) or non- high-density lipoprotein cholesterol (3.78 ± 1.10 versus 3.70 ± 1.05 mmol L -1 ) concentrations (all p > 0.05). The results remained unchanged after most sensitivity analyses. Patients with obstructive sleep apnea with periodic limb movements during sleep had more prevalent cardiovascular disease (11% versus 6%, p < 0.01). Periodic limb movements during sleep in obstructive sleep apnea is associated with dyslipidaemia independently of important confounders. Our results highlight periodic limb movements during sleep as an additional risk factor for cardiovascular disease in obstructive sleep apnea., (© 2023 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.)

The present study aimed to evaluate whether titration of fixed continuous positive airway pressure at home using telemonitoring produces patient outcomes equal to auto-adjusting positive airway pressure titration at home for patients with moderate obstructive sleep apnea. Patients were randomized with a 1:1 allocation ratio to receive either auto-adjusting positive airway pressure titration based on the median of the 95th percentile pressure across seven nights or fixed continuous positive airway pressure titration based on a fixed calculated pressure and specific adaptations after telemonitoring of device data after 3 and 7 nights. The results of the ambulatory titration were evaluated with in-laboratory polysomnography after 2 weeks. We hypothesized that fixed continuous positive airway pressure titration would be non-inferior to auto-adjusting positive airway pressure titration in respect to continuous positive airway pressure adherence at a 3-month follow-up. A non-inferiority margin of -0.75 hr was prespecified. One-hundred and four patients were randomly allocated to fixed continuous positive airway pressure (n = 52) and auto-adjusting positive airway pressure (n = 52) titration. The mean difference and the 95% confidence intervals in continuous positive airway pressure adherence after 3 months between the two arms were 0.80 (-0.08, 1.69) hr. The non-inferiority hypothesis was confirmed as the lower one-sided 97.5% confidence interval for the mean difference was above the prespecified margin. Patients in the fixed continuous positive airway pressure titration arm were titrated at significantly lower pressure level and had a significantly lower amount of average leaks compared with auto-adjusting positive airway pressure-titrated patients, while there was no difference in residual obstructive apnea-hypopnea index on polysomnography. Telemonitoring enables ambulatory continuous positive airway pressure titration with fixed pressure that is non-inferior to ambulatory titration with auto-adjusting pressure in patients with moderate obstructive sleep apnea., (© 2023 European Sleep Research Society.)

The American Academy of Sleep Medicine (AASM) uses similar apnea-hypopnea index (AHI) cut-off values to diagnose and define severity of sleep apnea independent of the technique used: in-hospital polysomnography (PSG) or type 3 portable monitoring (PM). Taking into account that PM theoretically might underestimate the AHI, we explored whether a lower cut-off would be more appropriate. We performed mathematical re-calculations on the diagnostic PSG-AHI (scored using AASM 1999 rules) of 865 consecutive patients with an AHI of ≥20 events/h who started continuous positive airway pressure (CPAP). For a PSG-AHI of ≥15 events/h re-scored using AASM 2012 rules (PSG-AHI AASM2012 ), a PM-respiratory event index (REI) AASM2012 cut-off point of ≥15 events/h resulted in a post-test probability of 100% of having the disease, but with negative tests in 57.1%. A PM-REI AASM2012 cut-off of 8 events/h, still resulted in a positive post-test probability of 100% but with negative tests in only 34.3%. Combination of the cut-off values with clinical estimation of being 'at high risk' based on Epworth Sleepiness Scale (ESS) and Berlin Questionnaire scores only resulted in a small reduction in the percentage of negative tests (respectively 52.7% and 32.7%). After 6 months, CPAP adherence was not lower using the PM-REI AASM 2012 cut-off ≥8 events/h in comparison to ≥15 events/h (median 5.7 vs. 5.8 h/night, p = 0.368) and the reduction in ESS was similar too (median -4 and -5 points, p = 0.083). Consequently, using a lower PM-REI AASM2012 cut-off could result in cost savings because of less negative studies and lesser need for a confirmatory PSG or a performance of a CPAP trial., (© 2022 European Sleep Research Society.)

It is known that adenosine excess due to monophosphate deaminase deficiency (AMPD1) can be linked to muscle problems. Recently, Perumal et al., 2014 reported a first case of possible impact of AMPD1 on sleep, REM sleep and cholinergic neurotransmission. We report a second patient with similar sleep complaints: long sleep duration with residual daytime sleepiness and a need to sleep after exercise. On polysomnography we observed a long sleep duration, with high sleep efficiency and a SOREMP; on MSLT a shortened sleep latency and 4 SOREMPS were observed. Frequency power spectral heart rate analysis during slow wave sleep, REM sleep and wakefulness revealed an increased parasympathetic tone. In conclusion, AMPD1 could have a profound influence on cholinergic neurotransmission and sleep; further studies are mandatory., (© 2015 The Authors. Journal of Sleep Research published by John Wiley & Sons Ltd on behalf of European Sleep Research Society.)