From Scalp to Ear-EEG: A Generalizable Transfer Learning Model for Automatic Sleep Scoring in Older People.

OBJECTIVE: Sleep monitoring has extensively utilized electroencephalogram (EEG) data collected from the scalp, yielding very large data repositories and well-trained analysis models. Yet, this wealth of data is lacking for emerging, less intrusive modalities, such as ear-EEG. METHODS AND PROCEDURES: The current study seeks to harness the abundance of open-source scalp EEG datasets by applying models pre-trained on data, either directly or with minimal fine-tuning; this is achieved in the context of effective sleep analysis from ear-EEG data that was recorded using a single in-ear electrode, referenced to the ipsilateral mastoid, and developed in-house as described in our previous work. Unlike previous studies, our research uniquely focuses on an older cohort (17 subjects aged 65-83, mean age 71.8 years, some with health conditions), and employs LightGBM for transfer learning, diverging from previous deep learning approaches. RESULTS: Results show that the initial accuracy of the pre-trained model on ear-EEG was 70.1%, but fine-tuning the model with ear-EEG data improved its classification accuracy to 73.7%. The fine-tuned model exhibited a statistically significant improvement (p < 0.05, dependent t-test) for 10 out of the 13 participants, as reflected by an enhanced average Cohen's kappa score (a statistical measure of inter-rater agreement for categorical items) of 0.639, indicating a stronger agreement between automated and expert classifications of sleep stages. Comparative SHAP value analysis revealed a shift in feature importance for the N3 sleep stage, underscoring the effectiveness of the fine-tuning process. CONCLUSION: Our findings underscore the potential of fine-tuning pre-trained scalp EEG models on ear-EEG data to enhance classification accuracy, particularly within an older population and using feature-based methods for transfer learning. This approach presents a promising avenue for ear-EEG analysis in sleep studies, offering new insights into the applicability of transfer learning across different populations and computational techniques. CLINICAL IMPACT: An enhanced ear-EEG method could be pivotal in remote monitoring settings, allowing for continuous, non-invasive sleep quality assessment in elderly patients with conditions like dementia or sleep apnea.

Sleep Delta power, age, and sex effects in treatment-resistant depression.

Electroencephalographic (EEG) deficits in slow wave activity or Delta power (0.5-4 Hz) indicate disturbed sleep homeostasis and are hallmarks of depression. Sleep homeostasis is linked to restorative sleep and potential antidepressant response via non-rapid eye movement (NREM) slow wave sleep (SWS) during which neurons undergo essential repair and rejuvenation. Decreased Low Delta power (0.5-2 Hz) was previously reported in individuals with depression. This study investigated power levels in the Low Delta (0.5-<2 Hz), High Delta (2-4 Hz), and Total Delta (0.5-4 Hz) bands and their association with age, sex, and disrupted sleep in treatment-resistant depression (TRD). Mann-Whitney U tests were used to compare the nightly progressions of Total Delta, Low Delta, and High Delta in 100 individuals with TRD and 24 healthy volunteers (HVs). Polysomnographic parameters were also examined, including Total Sleep Time (TST), Sleep Efficiency (SE), and Wake after Sleep Onset (WASO). Individuals with TRD had lower Delta power during the first NREM episode (NREM1) than HVs. The deficiency was observed in the Low Delta band versus High Delta. Females with TRD had higher Delta power than males during the first NREM1 episode, with the most noticeable sex difference observed in Low Delta. In individuals with TRD, Low Delta power correlated with WASO and SE, and High Delta correlated with WASO. Low Delta power deficits in NREM1 were observed in older males with TRD, but not females. These results provide compelling evidence for a link between age, sex, Low Delta power, sleep homeostasis, and non-restorative sleep in TRD.

Machine learning-empowered sleep staging classification using multi-modality signals.

The goal is to enhance an automated sleep staging system's performance by leveraging the diverse signals captured through multi-modal polysomnography recordings. Three modalities of PSG signals, namely electroencephalogram (EEG), electrooculogram (EOG), and electromyogram (EMG), were considered to obtain the optimal fusions of the PSG signals, where 63 features were extracted. These include frequency-based, time-based, statistical-based, entropy-based, and non-linear-based features. We adopted the ReliefF (ReF) feature selection algorithms to find the suitable parts for each signal and superposition of PSG signals. Twelve top features were selected while correlated with the extracted feature sets' sleep stages. The selected features were fed into the AdaBoost with Random Forest (ADB + RF) classifier to validate the chosen segments and classify the sleep stages. This study's experiments were investigated by obtaining two testing schemes: epoch-wise testing and subject-wise testing. The suggested research was conducted using three publicly available datasets: ISRUC-Sleep subgroup1 (ISRUC-SG1), sleep-EDF(S-EDF), Physio bank CAP sleep database (PB-CAPSDB), and S-EDF-78 respectively. This work demonstrated that the proposed fusion strategy overestimates the common individual usage of PSG signals.

In-Laboratory Polysomnography Worsens Obstructive Sleep Apnea by Changing Body Position Compared to Home Testing.

(1) Background: Home sleep apnea testing, known as polysomnography type 3 (PSG3), underestimates respiratory events in comparison with in-laboratory polysomnography type 1 (PSG1). Without head electrodes for scoring sleep and arousal, in a home environment, patients feel unfettered and move their bodies more naturally. Adopting a natural position may decrease obstructive sleep apnea (OSA) severity in PSG3, independently of missing hypopneas associated with arousals. (2) Methods: Patients with suspected OSA performed PSG1 and PSG3 in a randomized sequence. We performed an additional analysis, called reduced polysomnography, in which we blindly reassessed all PSG1 tests to remove electroencephalographic electrodes, electrooculogram, and surface electromyography data to estimate the impact of not scoring sleep and arousal-based hypopneas on the test results. A difference of 15 or more in the apnea-hypopnea index (AHI) between tests was deemed clinically relevant. We compared the group of patients with and without clinically relevant differences between lab and home tests (3) Results: As expected, by not scoring sleep, there was a decrease in OSA severity in the lab test, similar to the home test results. The group of patients with clinically relevant differences between lab and home tests presented more severe OSA in the lab compared to the other group (mean AHI, 42.5 vs. 20.2 events/h, p = 0.002), and this difference disappeared in the home test. There was no difference between groups in the shift of OSA severity by abolishing sleep scoring in the lab. However, by comparing lab and home tests, there were greater variations in supine AHI and time spent in the supine position in the group with a clinically relevant difference, either with or without scoring sleep, showing an impact of the site of the test on body position during sleep. These variations presented as a marked increase or decrease in supine outcomes according to the site of the test, with no particular trend. (4) Conclusions: In-lab polysomnography may artificially increase OSA severity in a subset of patients by inducing marked changes in body position compared to home tests. The location of the sleep test seems to interfere with the evaluation of patients with more severe OSA.

Association Between Sleep Quality and Cognitive Symptoms in Patients with Major Depressive Disorder.

Cognitive symptoms and sleep disturbance (SD) are common non-mood-related symptoms of major depressive disorder (MDD). In clinical practice, both cognitive symptoms and SD are related to MDD progression. However, there are only a few studies investigating the connection between cognitive symptoms and SD in patients with MDD, and only preliminary evidence suggests a significant association between cognitive symptoms and SD in patients with mood disorders. This study investigates the relationship between cognitive symptoms and sleep quality in patients with major depressive disorder. Patients (n = 20) with MDD were enrolled; their mean Hamilton Depression Scale-17 score was 21.95 (±2.76). Gold standard polysomnography (PSG) was used to assess sleep quality, and the validated THINC-integrated tool (the cognitive screening tool) was used to evaluate cognitive function in MDD patients. Overall, the results showed significant correlations between the cognitive screening tool's total score and sleep latency, wake-after-sleep onset, and sleep efficiency. These findings indicate that cognitive symptoms are associated with poor sleep quality among patients with MDD.

Sleep Disorders and Traffic Accidents: Unveiling the Hidden Risks.

BACKGROUND Numerous countries, Vietnam included, have persistently high annual rates of traffic accidents. Despite concerted government efforts to reduce the annual traffic accident rate, the toll of fatalities and consequential injuries from these accidents rises each year. Various factors contribute to these incidents, notably including alcohol consumption while driving, inadequate awareness of traffic regulations, and substandard traffic infrastructure. However, an under-recognized risk in developing nations such as Vietnam is the prevalence of sleep disorders. Conditions such as obstructive sleep apnea syndrome and obesity hypoventilation syndrome, while prevalent, remain inadequately assessed and treated. These disorders represent significant yet largely unaddressed contributors to the heightened risk of traffic accidents. CASE REPORT We describe the case of a 55-year-old Vietnamese man hospitalized due to long-standing respiratory complications and profound daytime sleepiness. Over the past 2 years, the patient gained 10 kg. Consequently, he frequently experienced drowsiness, leading to 4 traffic accidents. Despite previous hospitalizations, this sleep disorder had gone undiagnosed and untreated. Diagnostic assessments confirmed concurrent obstructive sleep apnea and obesity hypoventilation syndrome through polysomnography and blood gas analyses. Treatment involving non-invasive positive airway pressure therapy notably alleviated symptoms and substantially improved his quality of life within a concise 3-month period. CONCLUSIONS Obstructive sleep apnea and obesity hypoventilation syndrome are contributory factors to excessive daytime somnolence, significantly increasing vulnerability to traffic accidents. Regrettably, this critical intersection remains inadequately addressed. Addressing these concerns comprehensively through dedicated research initiatives should be imperative before considering the universal issuance of driver's licenses to all road users in Vietnam.

Assessing sleep-related breathing disorders among newly diagnosed rheumatoid and psoriatic arthritis patients: a cross-sectional study.

OBJECTIVES: This cross-sectional study aimed to determine the prevalence and risk factors for sleep-related breathing disorders (SRBD) in newly diagnosed, untreated rheumatoid arthritis (RA) and psoriatic arthritis (PsA) patients, and to develop a screening algorithm for early detection. METHODS: We evaluated newly diagnosed RA or PsA patients using the Epworth Sleepiness Scale (ESS) questionnaire, cardiorespiratory polygraphy (RPG), and clinical and laboratory assessments. Sleep apnea syndrome (SAS) was diagnosed based on pathological RPG findings excessive daytime sleepiness, defined as ESS score above 10. RESULTS: The study included 39 patients (22 RA, 17 PsA) and 23 controls. In RPG, SRBD was identified in 38.5% of arthritis patients compared to 39.1% of controls (p = 1.00), with male gender (p = .004) and age (p < .001) identified as risk factors. Excessive daytime sleepiness was noted in 36.4% of RA patients, 17.6% of PsA patients, and 21.7% of controls. Of the 24 patients diagnosed with SRBD, 41.6% met the criteria for SAS. SAS prevalence was 31.8% among RA patients, 0% in PsA patients, and 13% in controls. A significant association was observed between excessive daytime sleepiness and SRBD (p = .036). CONCLUSION: Our findings reveal a high prevalence of SRBD in newly diagnosed, untreated RA and PsA patients in ESS and RPG, with excessive daytime sleepiness being a reliable predictor of SRBD. Patients with RA exhibited a higher predisposition to SAS. We therefore suggest incorporating ESS and RPG as screening tools in RA or PsA for early detection and management of SRBD.

Independent relationship between sleep apnea-specific hypoxic burden and glucolipid metabolism disorder: a cross-sectional study.

OBJECTIVES: Obstructive sleep apnea (OSA) is associated with abnormal glucose and lipid metabolism. However, whether there is an independent association between Sleep Apnea-Specific Hypoxic Burden (SASHB) and glycolipid metabolism disorders in patients with OSA is unknown. METHODS: We enrolled 2,173 participants with suspected OSA from January 2019 to July 2023 in this study. Polysomnographic variables, biochemical indicators, and physical measurements were collected from each participant. Multiple linear regression analyses were used to evaluate independent associations between SASHB, AHI, CT90 and glucose as well as lipid profile. Furthermore, logistic regressions were used to determine the odds ratios (ORs) for abnormal glucose and lipid metabolism across various SASHB, AHI, CT90 quartiles. RESULTS: The SASHB was independently associated with fasting blood glucose (FBG) (ß = 0.058, P = 0.016), fasting insulin (FIN) (ß = 0.073, P < 0.001), homeostasis model assessment of insulin resistance (HOMA-IR) (ß = 0.058, P = 0.011), total cholesterol (TC) (ß = 0.100, P < 0.001), total triglycerides (TG) (ß = 0.063, P = 0.011), low-density lipoprotein cholesterol (LDL-C) (ß = 0.075, P = 0.003), apolipoprotein A-I (apoA-I) (ß = 0.051, P = 0.049), apolipoprotein B (apoB) (ß = 0.136, P < 0.001), apolipoprotein E (apoE) (ß = 0.088, P < 0.001) after adjustments for confounding factors. Furthermore, the ORs for hyperinsulinemia across the higher SASHB quartiles were 1.527, 1.545, and 2.024 respectively, compared with the lowest quartile (P < 0.001 for a linear trend); the ORs for hyper-total cholesterolemia across the higher SASHB quartiles were 1.762, 1.998, and 2.708, compared with the lowest quartile (P < 0.001 for a linear trend) and the ORs for hyper-LDL cholesterolemia across the higher SASHB quartiles were 1.663, 1.695, and 2.316, compared with the lowest quartile (P < 0.001 for a linear trend). Notably, the ORs for hyper-triglyceridemia{1.471, 1.773, 2.099} and abnormal HOMA-IR{1.510, 1.492, 1.937} maintained a consistent trend across the SASHB quartiles. CONCLUSIONS: We found SASHB was independently associated with hyperinsulinemia, abnormal HOMA-IR, hyper-total cholesterolemia, hyper-triglyceridemia and hyper-LDL cholesterolemia in Chinese Han population. Further prospective studies are needed to confirm that SASHB can be used as a predictor of abnormal glycolipid metabolism disorders in patients with OSA. TRIAL REGISTRATION: ChiCTR1900025714 { http://www.chictr.org.cn/ }; Prospectively registered on 6 September 2019; China.

Association Between Sleep Quality and Deep Learning-Based Sleep Onset Latency Distribution Using an Electroencephalogram.

To evaluate sleep quality, it is necessary to monitor overnight sleep duration. However, sleep monitoring typically requires more than 7 hours, which can be inefficient in termxs of data size and analysis. Therefore, we proposed to develop a deep learning-based model using a 30 sec sleep electroencephalogram (EEG) early in the sleep cycle to predict sleep onset latency (SOL) distribution and explore associations with sleep quality (SQ). We propose a deep learning model composed of a structure that decomposes and restores the signal in epoch units and a structure that predicts the SOL distribution. We used the Sleep Heart Health Study public dataset, which includes a large number of study subjects, to estimate and evaluate the proposed model. The proposed model estimated the SOL distribution and divided it into four clusters. The advantage of the proposed model is that it shows the process of falling asleep for individual participants as a probability graph over time. Furthermore, we compared the baseline of good SQ and SOL and showed that less than 10 minutes SOL correlated better with good SQ. Moreover, it was the most suitable sleep feature that could be predicted using early EEG, compared with the total sleep time, sleep efficiency, and actual sleep time. Our study showed the feasibility of estimating SOL distribution using deep learning with an early EEG and showed that SOL distribution within 10 minutes was associated with good SQ.

Multimodal data integration for enhanced longitudinal prediction for cardiac and cerebrovascular events following initial diagnosis of obstructive sleep apnea syndrome.

Background: Obstructive sleep apnea syndrome (OSAS), a prevalent condition, often coexists with intricate metabolic issues and is frequently associated with negative cardiovascular outcomes. We developed a longitudinal prediction model integrating multimodal data for cardiovascular risk stratification of patients with an initial diagnosis of OSAS. Methods: We reviewed the data of patients with new-onset OSAS who underwent diagnostic polysomnography between 2018-19. Patients were treated using standard treatment regimens according to clinical practice guidelines. Results: Over a median follow-up of 32 months, 98/729 participants (13.4%) experienced our composite outcome. At a ratio of 7:3, cases were randomly divided into development (n = 510) and validation (n = 219) cohorts. A prediction nomogram was created using six clinical factors - sex, age, diabetes mellitus, history of coronary artery disease, triglyceride-glucose index, and apnea-hypopnea index. The prediction nomogram showed excellent discriminatory power, based on Harrell's C-index values of 0.826 (95% confidence interval (CI) = 0.779-0.873) for the development cohort and 0.877 (95% CI = 0.824-0.93) for the validation cohort. Moreover, comparing the predicted and observed major adverse cardiac and cerebrovascular events in both development and validation cohorts indicated that the prediction nomogram was well-calibrated. Decision curve analysis demonstrated the good clinical applicability of the prediction nomogram. Conclusions: Our findings demonstrated the construction of an innovative visualisation tool that utilises various types of data to predict poor outcomes in Chinese patients diagnosed with OSAS, providing accurate and personalised therapy. Registration: Chinese Clinical Trial Registry ChiCTR2300075727.

Is sleep bruxism in obstructive sleep apnea only an oral health related problem?

BACKGROUND: The etiology of sleep bruxism in obstructive sleep apnea (OSA) patients is not yet fully clarified. This prospective clinical study aimed to investigate the connection between probable sleep bruxism, electromyographic muscle tone, and respiratory sleep patterns recorded during polysomnography. METHODS: 106 patients with OSA (74 males, 31 females, mean age: 56.1 ± 11.4 years) were divided into two groups (sleep bruxism: SB; no sleep bruxism: NSB). Probable SB were based on the AASM criteria: self-report of clenching/grinding, orofacial symptoms upon awakening, abnormal tooth wear and hypertrophy of the masseter muscle. Both groups underwent clinical examination for painful muscle symptoms aligned with Temporomandibular Disorders Diagnostic Criteria (DC/TMD), such as myalgia, myofascial pain, and headache attributed to temporomandibular disorder. Additionally, non-complaint positive muscle palpation and orofacial-related limitations (Jaw Functional Limited Scale-20: JFLS-20) were assessed. A one-night polysomnography with electromyographic masseter muscle tone (EMG) measurement was performed. Descriptive data, inter-group comparisons and multivariate logistic regression were calculated. RESULTS: OSA patients had a 37.1% prevalence of SB. EMG muscle tone (N1-N3, REM; P = 0.001) and the number of hypopneas (P = 0.042) were significantly higher in the sleep bruxism group. While measures like apnea-hypopnea-index (AHI), respiratory-disturbance-index (RDI), apnea index (AI), hypopnea-index (HI), number of arousals, and heart rate (1/min) were elevated in sleep bruxers, the differences were not statistically significant. There was no difference in sleep efficiency (SE; P = 0.403). Non-complaint masseter muscle palpation (61.5%; P = 0.015) and myalgia (41%; P = 0.010) were significant higher in SB patients. Multivariate logistic regression showed a significant contribution of EMG muscle tone and JFLS-20 to bruxism risk. CONCLUSION: Increased EMG muscle tone and orofacial limitations can predict sleep bruxism in OSA patients. Besides, SB patients suffer more from sleep disorder breathing. Thus, sleep bruxism seems to be not only an oral health related problem in obstructive apnea. Consequently, interdisciplinary interventions are crucial for effectively treating these patients. TRIAL REGISTRATION: The study was approved by the Ethics Committee of Philipps-University Marburg (reg. no. 13/22-2022) and registered at the "German Clinical Trial Register, DRKS" (DRKS0002959).

Older adults at greater risk for Alzheimer's disease show stronger associations between sleep apnea severity in REM sleep and verbal memory.

BACKGROUND: Obstructive sleep apnea (OSA) increases risk for cognitive decline and Alzheimer's disease (AD). While the underlying mechanisms remain unclear, hypoxemia during OSA has been implicated in cognitive impairment. OSA during rapid eye movement (REM) sleep is usually more severe than in non-rapid eye movement (NREM) sleep, but the relative effect of oxyhemoglobin desaturation during REM versus NREM sleep on memory is not completely characterized. Here, we examined the impact of OSA, as well as the moderating effects of AD risk factors, on verbal memory in a sample of middle-aged and older adults with heightened AD risk. METHODS: Eighty-one adults (mean age:61.7 ± 6.0 years, 62% females, 32% apolipoprotein E ε4 allele (APOE4) carriers, and 70% with parental history of AD) underwent clinical polysomnography including assessment of OSA. OSA features were derived in total, NREM, and REM sleep. REM-NREM ratios of OSA features were also calculated. Verbal memory was assessed with the Rey Auditory Verbal Learning Test (RAVLT). Multiple regression models evaluated the relationships between OSA features and RAVLT scores while adjusting for sex, age, time between assessments, education years, body mass index (BMI), and APOE4 status or parental history of AD. The significant main effects of OSA features on RAVLT performance and the moderating effects of AD risk factors (i.e., sex, age, APOE4 status, and parental history of AD) were examined. RESULTS: Apnea-hypopnea index (AHI), respiratory disturbance index (RDI), and oxyhemoglobin desaturation index (ODI) during REM sleep were negatively associated with RAVLT total learning and long-delay recall. Further, greater REM-NREM ratios of AHI, RDI, and ODI (i.e., more events in REM than NREM) were related to worse total learning and recall. We found specifically that the negative association between REM ODI and total learning was driven by adults 60 + years old. In addition, the negative relationships between REM-NREM ODI ratio and total learning, and REM-NREM RDI ratio and long-delay recall were driven by APOE4 carriers. CONCLUSION: Greater OSA severity, particularly during REM sleep, negatively affects verbal memory, especially for people with greater AD risk. These findings underscore the potential importance of proactive screening and treatment of REM OSA even if overall AHI appears low.

Artificial intelligence augmented home sleep apnea testing device study (AISAP study).

STUDY OBJECTIVE: This study aimed to prospectively validate the performance of an artificially augmented home sleep apnea testing device (WVU-device) and its patented technology. METHODOLOGY: The WVU-device, utilizing patent pending (US 20210001122A) technology and an algorithm derived from cardio-pulmonary physiological parameters, comorbidities, and anthropological information was prospectively compared with a commercially available and Center for Medicare and Medicaid Services (CMS) approved home sleep apnea testing (HSAT) device. The WVU-device and the HSAT device were applied on separate hands of the patient during a single night study. The oxygen desaturation index (ODI) obtained from the WVU-device was compared to the respiratory event index (REI) derived from the HSAT device. RESULTS: A total of 78 consecutive patients were included in the prospective study. Of the 78 patients, 38 (48%) were women and 9 (12%) had a Fitzpatrick score of 3 or higher. The ODI obtained from the WVU-device corelated well with the HSAT device, and no significant bias was observed in the Bland-Altman curve. The accuracy for ODI > = 5 and REI > = 5 was 87%, for ODI> = 15 and REI > = 15 was 89% and for ODI> = 30 and REI of > = 30 was 95%. The sensitivity and specificity for these ODI /REI cut-offs were 0.92 and 0.78, 0.91 and 0.86, and 0.94 and 0.95, respectively. CONCLUSION: The WVU-device demonstrated good accuracy in predicting REI when compared to an approved HSAT device, even in patients with darker skin tones.

Sleep disturbance in clinical and preclinical scrapie-infected sheep measured by polysomnography.

Neurodegenerative diseases are characterised by neuronal loss and abnormal deposition of pathological proteins in the nervous system. Among the most common neurodegenerative diseases are Alzheimer's disease (AD), Parkinson's disease (PD), Huntington's disease and transmissible spongiform encephalopathies (TSEs). Sleep and circadian rhythm disturbances are one of the most common symptoms in patients with neurodegenerative diseases. Currently, one of the main objectives in the study of TSEs is to try to establish an early diagnosis, as clinical signs do not appear until the damage to the central nervous system is very advanced, which prevents any therapeutic approach. In this paper, we provide the first description of sleep disturbance caused by classical scrapie in clinical and preclinical sheep using polysomnography compared to healthy controls. Fifteen sheep classified into three groups, clinical, preclinical and negative control, were analysed. The results show a decrease in total sleep time as the disease progresses, with significant changes between control, clinical and pre-clinical animals. The results also show an increase in sleep fragmentation in clinical animals compared to preclinical and control animals. In addition, sheep with clinical scrapie show a total loss of Rapid Eye Movement sleep (REM) and alterations in Non Rapid Eyes Movement sleep (NREM) compared to control sheep, demonstrating more shallow sleep. Although further research is needed, these results suggest that prion diseases also produce sleep disturbances in animals and that polysomnography could be a diagnostic tool of interest in clinical and preclinical cases of prion diseases.

A multi-task learning model using RR intervals and respiratory effort to assess sleep disordered breathing.

BACKGROUND: Sleep-disordered breathing (SDB) affects a significant portion of the population. As such, there is a need for accessible and affordable assessment methods for diagnosis but also case-finding and long-term follow-up. Research has focused on exploiting cardiac and respiratory signals to extract proxy measures for sleep combined with SDB event detection. We introduce a novel multi-task model combining cardiac activity and respiratory effort to perform sleep-wake classification and SDB event detection in order to automatically estimate the apnea-hypopnea index (AHI) as severity indicator. METHODS: The proposed multi-task model utilized both convolutional and recurrent neural networks and was formed by a shared part for common feature extraction, a task-specific part for sleep-wake classification, and a task-specific part for SDB event detection. The model was trained with RR intervals derived from electrocardiogram and respiratory effort signals. To assess performance, overnight polysomnography (PSG) recordings from 198 patients with varying degree of SDB were included, with manually annotated sleep stages and SDB events. RESULTS: We achieved a Cohen's kappa of 0.70 in the sleep-wake classification task, corresponding to a Spearman's correlation coefficient (R) of 0.830 between the estimated total sleep time (TST) and the TST obtained from PSG-based sleep scoring. Combining the sleep-wake classification and SDB detection results of the multi-task model, we obtained an R of 0.891 between the estimated and the reference AHI. For severity classification of SBD groups based on AHI, a Cohen's kappa of 0.58 was achieved. The multi-task model performed better than a single-task model proposed in a previous study for AHI estimation, in particular for patients with a lower sleep efficiency (R of 0.861 with the multi-task model and R of 0.746 with single-task model with subjects having sleep efficiency < 60%). CONCLUSION: Assisted with automatic sleep-wake classification, our multi-task model demonstrated proficiency in estimating AHI and assessing SDB severity based on AHI in a fully automatic manner using RR intervals and respiratory effort. This shows the potential for improving SDB screening with unobtrusive sensors also for subjects with low sleep efficiency without adding additional sensors for sleep-wake detection.

Predictors of moderate to severe obstructive sleep apnea in patients with lung cancer.

BACKGROUND AND OBJECTIVES: OSA is a known medical condition that is associated with several comorbidities and affect patients' quality of life. The association between OSA and lung cancer remains debated. Some studies reported increased prevalence of OSA in patients with lung cancer. We aimed to assess predictors of moderate-to-severe OSA in patients with lung cancer. METHODS: We enrolled 153 adult patients who were newly diagnosed with lung cancer. Cardiorespiratory monitoring was performed using home sleep apnea device. We carried out Univariate and multivariate logistic regression analysis on multiple parameters including age, gender, smoking status, neck circumference, waist circumference, BMI, stage and histopathology of lung cancer, presence of superior vena cava obstruction, and performance status to find out the factors that are independently associated with a diagnosis of moderate-to-severe OSA. RESULTS: Our results suggest that poor performance status is the most significant predictor of moderate to severe OSA in patients with lung cancer after controlling for important confounders. CONCLUSION: Performance status is a predictor of moderate to severe OSA in patients with lung cancer in our population of middle eastern ethnicity.

Alpha anteriorization and theta posteriorization during deep sleep.

Brain states (wake, sleep, general anesthesia, etc.) are profoundly associated with the spatiotemporal dynamics of brain oscillations. Previous studies showed that the EEG alpha power shifted from the occipital cortex to the frontal cortex (alpha anteriorization) after being induced into a state of general anesthesia via propofol. The sleep research literature suggests that slow waves and sleep spindles are generated locally and propagated gradually to different brain regions. Since sleep and general anesthesia are conceptualized under the same framework of consciousness, the present study examines whether alpha anteriorization similarly occurs during sleep and how the EEG power in other frequency bands changes during different sleep stages. The results from the analysis of three polysomnography datasets of 234 participants show consistent alpha anteriorization during the sleep stages N2 and N3, beta anteriorization during stage REM, and theta posteriorization during stages N2 and N3. Although it is known that the neural circuits responsible for sleep are not exactly the same for general anesthesia, the findings of alpha anteriorization in this study suggest that, at macro level, the circuits for alpha oscillations are organized in the similar cortical areas. The spatial shifts of EEG power in different frequency bands during sleep may offer meaningful neurophysiological markers for the level of consciousness.

[Techniques for quantifying endotypes of obstructive sleep apnea].

Obstructive sleep apnea (OSA) is the frequent occurrence of apnea and/or hypopnea during sleep, leading to intermittent hypoxia, hypercapnia, and disruption of sleep architecture, further resulting in multisystem damage. The pathophysiological mechanisms include abnormal anatomical structure, low arousal threshold, high loop gain, and poor muscle reactivity, etc. As there are individual differences in the underlying mechanisms of OSA (i.e. endotypes), the effectiveness of treatment and prognosis may also vary according to these characteristics. Understanding the endotype of OSA is critical to understanding which patients are most likely to benefit from non-invasive ventilation therapy. Quantification of endotypes is central to the precision treatment of OSA and may provide the basis for accurate clinical treatment of OSA based on endotypes.

Interhemispheric differences of electroencephalography signal characteristics in different sleep stages.

OBJECTIVE: The current electroencephalography (EEG) measurement setup is complex, laborious to set up, and uncomfortable for patients. We hypothesize that differences in EEG signal characteristics for sleep staging between the left and right hemispheres are negligible; therefore, there is potential to simplify the current measurement setup. We aimed to investigate the technical hemispheric differences in EEG signal characteristics along with electrooculography (EOG) signals during different sleep stages. METHODS: Type II portable polysomnography (PSG) recordings of 50 patients were studied. Amplitudes and power spectral densities (PSDs) of the EEG and EOG signals were compared between the left (C3-M2, F3-M2, O1-M2, and E1-M2) and the right (C4-M1, F4-M1, O2-M1, and E2-M2) hemispheres. Regression analysis was performed to investigate the potential influence of sleep stages on the hemispheric differences in PSDs. Wilcoxon signed-rank tests were also employed to calculate the effect size of hemispheres across different frequency bands and sleep stages. RESULTS: The results showed statistically significant differences in signal characteristics between hemispheres, but the absolute differences were minor. The median hemispheric differences in amplitudes were smaller than 3 µv with large interquartile ranges during all sleep stages. The absolute and relative PSD characteristics were highly similar between hemispheres in different sleep stages. Additionally, there were negligible differences in the effect size between hemispheres across all sleep stages. CONCLUSIONS: Technical signal differences between hemispheres were minor across all sleep stages, indicating that both hemispheres contain similar information needed for sleep staging. A reduced measurement setup could be suitable for sleep staging without the loss of relevant information.