Search Results (263)

Sleep is a vital physiological process for recovery and health. In people with knee osteoarthritis (OA), disrupted sleep is common and linked to worse clinical outcomes. Commercial sleep trackers provide an accessible option to monitor sleep in this population, but their accuracy for detecting sleep, wake, and sleep stages remains uncertain. This study compared nighttime sleep data from polysomnography (PSG) and Fitbit Sense in individuals with knee OA and insomnia. Data were collected from 53 participants (60.4% women, mean age 51 ± 8.2 years) over 62 nights using simultaneous PSG and Fitbit recording. Fitbit Sense showed high accuracy (85.76%) and sensitivity (95.95%) for detecting sleep but lower specificity (50.96%), indicating difficulty separating quiet wakefulness from sleep. Agreement with PSG was higher on nights with longer total sleep time, higher sleep efficiency, shorter sleep onset, and fewer awakenings, suggesting better performance when sleep is less fragmented. The device showed limited precision in classifying sleep stages, often misclassifying deep and REM sleep as light sleep. Despite these issues, Fitbit Sense may serve as a useful complementary tool for monitoring sleep duration, timing, and regularity in this population. However, sleep stage and fragmentation data should be interpreted cautiously in both clinical and research settings. Full article

Accurate sleep staging and sleep-disordered breathing (SDB) severity prediction are critical for the early diagnosis and management of sleep disorders. However, real-world polysomnography (PSG) data often suffer from modality heterogeneity, label scarcity, and non-independent and identically distributed (non-IID) characteristics across institutions, posing significant challenges for model generalization and clinical deployment. To address these issues, we propose a federated multi-task learning (FMTL) framework that simultaneously performs sleep staging and SDB severity classification from seven multimodal physiological signals, including EEG, ECG, respiration, etc. The proposed framework is built upon a hybrid deep neural architecture that integrates convolutional layers (CNN) for spatial representation, bidirectional GRUs for temporal modeling, and multi-head self-attention for long-range dependency learning. A shared feature extractor is combined with task-specific heads to enable joint diagnosis, while the FedAvg algorithm is employed to facilitate decentralized training across multiple institutions without sharing raw data, thereby preserving privacy and addressing non-IID challenges. We evaluate the proposed method across three public datasets (APPLES, SHHS, and HMC) treated as independent clients. For sleep staging, the model achieves accuracies of 85.3% (APPLES), 87.1% (SHHS_rest), and 79.3% (HMC), with Cohen’s Kappa scores exceeding 0.71. For SDB severity classification, it obtains macro-F1 scores of 77.6%, 76.4%, and 79.1% on APPLES, SHHS_rest, and HMC, respectively. These results demonstrate that our unified FMTL framework effectively leverages multimodal PSG signals and federated training to deliver accurate and scalable sleep disorder assessment, paving the way for the development of a privacy-preserving, generalizable, and clinically applicable digital sleep monitoring system. Full article

Background/Objectives: Childhood obesity represents a growing public health concern. It is closely associated with obstructive sleep apnoea (OSA), which impairs nocturnal breathing and significantly affects neurocognitive and cardiovascular health. This review aims to analyse differences in fat distribution, anthropometric parameters, and instrumental assessments of paediatric OSA compared to adult OSA to improve the diagnostic characterisation of obese children. Methods: narrative review. Results: While adenotonsillar hypertrophy (ATH) remains a primary cause of paediatric OSA, the increasing prevalence of obesity has introduced distinct pathophysiological mechanisms, including fat accumulation around the pharynx, reduced respiratory muscle tone, and systemic inflammation. Children exhibit different fat distribution patterns compared to adults, with a greater proportion of subcutaneous fat relative to visceral fat. Nevertheless, cervical and abdominal adiposity are crucial in increasing upper airway collapsibility. Recent evidence highlights the predictive value of anthropometric and body composition indicators such as neck circumference (NC), neck-to-height ratio (NHR), neck-to-waist ratio (NWR), fat-to-muscle ratio (FMR), and the neck-to-abdominal-fat percentage ratio (NAF%). In addition, ultrasound assessment of lateral pharyngeal wall (LPW) thickness and abdominal fat distribution provides clinically relevant information regarding anatomical contributions to OSA severity. Among imaging modalities, dual-energy X-ray absorptiometry (DXA), bioelectrical impedance analysis (BIA), and air displacement plethysmography (ADP) have proven valuable tools for evaluating body fat distribution. Conclusions: Despite advances in the topic, a validated predictive model that integrates these parameters is still lacking in clinical practice. Polysomnography (PSG) remains the gold standard for diagnosis; however, its limited accessibility underscores the need for complementary tools to prioritise the identification of children at high risk. A multimodal approach integrating clinical, anthropometric, and imaging data could support the early identification and personalised management of paediatric OSA in obesity. Full article

Background: Obstructive Sleep Apnea (OSA) is a common occurrence in the perioperative patient population but is often undiagnosed. Point-of-Care Ultrasound (POCUS) has emerged as a promising tool for perioperative assessment; however, its effectiveness in detecting the presence or severity of OSA needs to be evaluated. Objective: We assessed the ability of airway POCUS as a screening and severity evaluation tool for OSA by examining its correlation with STOP-BANG scores and the Apnea–Hypopnea Index (AHI). Design: Cross-sectional observational study. Setting: A single-center study in a tertiary care hospital between June 2020 to May 2021. Patients: Adult patients aged 18–65 with prior Polysomnography (PSG) for OSA workup were screened. Interventions: The participants completed the STOP-BANG questionnaire and subsequently underwent POCUS examinations, either pre- or post-surgery. Ten different POCUS views previously used for evaluating OSA were acquired in a predefined sequence, with subsequent measurements of airway parameters. Outcome measures: Generalized linear modeling was used to explore and assess the relationships between the measured parameters, STOP-BANG, and AHI scores (modeled continuously and categorized into risk levels of STOP-BANG and AHI). Results: A total of 260 patients were screened, of which 142 were enrolled and 127 completed the scanning studies. The median AHI was 16.71, while the STOP-BANG scores were mostly between 5 and 6, indicating a moderate-to-high OSA risk in the study population. Notably, only neck circumference was significantly associated with AHI severity (p = 0.012), whereas none of the other POCUS measures were. Among the POCUS measures, significant associations with STOP-BANG scores were observed for the Tongue Cross-Sectional Area (T-CSA) (p = 0.002), Retro-Palatal Diameter (RPD) (p = 0.034), Distance Between Lingual Arteries (DLA) (p = 0.034), and Geniohyoid Muscle Thickness (GMT) (p = 0.040). Conclusions: Neck circumference is a more reliable predictor of OSA severity (AHI) compared to other POCUS measurements. Many of the POCUS measures had a good correlation with the STOP-BANG scores, highlighting the utility of POCUS as a screening tool for OSA rather than as a severity evaluation tool. Full article

Automated sleep stage classification is essential for objective sleep evaluation and clinical diagnosis. While numerous algorithms have been developed, the predominant existing methods utilize single-channel electroencephalogram (EEG) signals, neglecting the complementary physiological information available from other channels. Standard polysomnography (PSG) recordings capture multiple concurrent biosignals, where sophisticated integration of these multi-channel data represents a critical factor for enhanced classification accuracy. Conventional multi-channel fusion techniques typically employ elementary concatenation approaches that insufficiently model the intricate cross-channel correlations, consequently limiting classification performance. To overcome these shortcomings, we present MCAF-Net, a novel network architecture that employs temporal convolution modules to extract channel-specific features from each input signal and introduces a dynamic gated multi-head cross-channel attention mechanism (MCAF) to effectively model the interdependencies between different physiological channels. Experimental results show that our proposed method successfully integrates information from multiple channels, achieving significant improvements in sleep stage classification compared to the vast majority of existing methods. Full article

Background/Objectives: The relationship between OSA and adult hypertension has been extensively studied; however, it remains understudied in pediatric patients without OSA. The aim of this study is to identify factors associated with pediatric hypertension without OSA, through an IRB-approved retrospective chart review of patients who underwent polysomnography at Nemours Children’s Hospital, DE/NJ between January 2020 and July 2023. Methods: Eligibility criteria included children 8–17 years, completed PSG, and clinic visit blood pressure (BP). Anthropometrics, demographics, social determinants, and medical history were obtained from electronic medical records. Hypertension was defined as the average systolic and/or diastolic BP that is ≥95th percentile for gender, age, and height based on AAP Clinical Practice Guidelines. All variables were checked for normality. Chi-square tests for categorical data and Wilcoxon rank sum tests for continuous data were used to test significance between non-OSA non-hypertensives (NH) and hypertensives (H). p < 0.05 is considered significant. Results: Of 285 charts evaluated, 137 were classified as non-OSA. Patient information, including parents in household, smoking exposure, and food allergies, were statistically significant (p < 0.05) in hypertensive pediatric patients without OSA. Hypertension was significantly correlated (p < 0.05) with birth weight, BMI, daytime heart rate, systolic BP, and diastolic BP. Statistically significant differences (p < 0.05) were found in mental illnesses, neurological disease, and respiratory disease. Among polysomnography parameters, only nighttime heart rate was found to be statistically significant. Conclusions: The data suggests that in pediatric patients without OSA, there are multiple factors and co-morbidities associated with hypertension. These factors and co-morbidities warrant additional follow up in clinical practice to mitigate the risks of hypertension in pediatric patients. Full article

Background/Objectives: There is limited data on well-documented comorbidities with polysomnography (PSG)/multiple sleep latency test (MSLT) findings in idiopathic hypersomnia (IH). We aimed to characterize the clinical, PSG/MSLT characteristics of IH patients in our health network. Methods: We reviewed charts of all IH cases between 2000 and 2023, extracting clinical features, comorbidities, and PSG/MSLT findings. Results: One hundred forty-two patients (83.80% female) with IH were included. Compared to those without mood disorders, both major depressive disorder (MDD) and anxiety patients were older at onset (27.10 ± 8.32 and 26.76 ± 8.40 versus 23.23 ± 6.94 and 24.05 ± 7.31 years; p = 0.003 and p = 0.042) and had lower ESS (15 versus 19; 15.67 versus 17.75; p < 0.0001), more disrupted sleep (28 (36.36%) versus 8 (12.31%); p = 0.001; 24 (35.82%) versus 12 (16%); p = 0.007), and less sleep inertia (30 (38.96%) versus 38 (58.46%); p = 0.021; 26 (38.81%) versus 42 (56%); p = 0.04). Fifteen patients with dysautonomia disorders presented at an earlier age (21.80 ± 6.60 versus 25.75 ± 8, p = 0.0682). On MSLT, MDD, anxiety, and dysautonomia patients had longer sleep latencies than the non-affected counterparts (6.40 (5.40–7.60) minutes versus 3.60 (2.60–5.40) min., <0.0001; 6.20 (5.20–7.40) versus 4 (2.60–6.40) minutes; p < 0.0001; 7.40 (6–7.80) versus 5.40 (3–7); p = 0.008). MDD and anxiety cases had fewer sleep onset REM periods (7 (9.09%) versus 16 (24.62%), p = 0.0124 and 6 (8.96%) versus 17 (22.67%), p = 0.0388) compared to those not affected by these disorders. Conclusions: Our study highlights the importance of recognizing mood disorders and dysautonomia in patients diagnosed with IH. Further research may elucidate management strategies for these patients. Full article

Health and well-being, both mental and physical, depend largely on adequate sleep. Many conditions arise from a disrupted sleep cycle, significantly deteriorating the quality of life of those affected. The analysis of the sleep cycle provide valuable information about sleep stages, which are employed in sleep medicine for the diagnosis of numerous diseases. The clinical standard for sleep data recording is polysomnography (PSG), which records electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), and other signals during sleep activity. Recently, machine learning approaches have exhibited high accuracy in applications such as the classification and prediction of biomedical signals. This study presents a hybrid neural network architecture composed of convolutional neural network (CNN) layers, bidirectional long short-term memory (BiLSTM) layers, and attention mechanism layers in order to process large volumes of EEG data in PSG files. The objective is to design a framework for automated feature extraction. To address class imbalance, an epoch-level random undersampling (E-LRUS) method is proposed, discarding full epochs from majority classes while preserving the temporal structure, unlike traditional methods that remove individual samples. This method has been tested on EEG recordings acquired from the public Sleep EDF Expanded database, achieving an overall accuracy rate of 78.67% along with an F1-score of 72.10%. The findings show that this method proves to be effective for sleep stage classification in patients. Full article

Introduction: Older people with sleep disturbances also have other chronic pathologies that may interfere with these disturbances. One of the comorbidities that is frequently present is type 2 diabetes. Objective: This research aims to find out whether type 2 diabetes mellitus present in elderly people affects the level of severity of obstructive sleep apnoea syndrome (OSAS). Methodology: A cross-sectional descriptive study was carried out on a sample of 134 elderly people who attended the Sleep Unit of Andalusia’s Door Hospital in Jaen, who were diagnosed with OSAS and classified according to severity. A total of 34 participants had a diagnosis of diabetes mellitus at the time of the study. Results: There were significant differences in the severity of obstructive sleep apnoea syndrome between participants with and without type 2 diabetes mellitus, with the former having higher scores (p < 0.01). Participants with a BMI that classified them as obese had more severe apnoea than those with a normal weight at the time of the study (p = 0.043). Discussion: This study, focused exclusively on older adults, demonstrates an association between type 2 diabetes mellitus and a greater severity of OSAS. Using polysomnography (PSG) as the gold standard, we identified a significant relationship between obesity and severe OSAS. Furthermore, the connection between OSAS, type 2 diabetes mellitus, and CPAP use highlights the importance of a comprehensive approach in this population. Full article

This study evaluated the agreement between MotionWatch8 actigraphy and polysomnography (PSG) in measuring sleep parameters among menopausal women under controlled 30 °C laboratory conditions. Sixteen peri- and post-menopausal women (age: 51.4 ± 4.2 years, BMI: 26.0 ± 3.1 kg/m²) contributed 59 nights of simultaneous recordings, with parameters analyzed using Bland–Altman plots, linear mixed model analysis, and epoch-by-epoch comparisons. Results showed MotionWatch8 significantly overestimated total sleep time by 18.6 min and sleep efficiency by 3.5%, while underestimating sleep onset latency by 11.2 min and wake after sleep onset by 9.1 min compared to PSG. Significant proportional errors were observed, particularly for participants with prolonged sleep onset latency, high wake after sleep onset, and lower sleep efficiency. Epoch-by-epoch analysis revealed high sensitivity for sleep detection (94.8%) but low specificity for wake detection (33.1%), with 87.3% overall accuracy. These findings demonstrate that MotionWatch8 may be less reliable for individuals with more extreme sleep characteristics, such as insomnia, as measurement accuracy declines with increasing severity of sleep disturbances, highlighting the need for caution when using this device for detailed sleep assessments in clinical populations with sleep disturbances. Full article

Sleep occupies about one-third of human life and is crucial for health, but traditional sleep staging relies on experts manually performing polysomnography (PSG), a process that is time-consuming, labor-intensive, and susceptible to subjective differences between evaluators. With the development of deep learning technologies, particularly the application of convolutional neural networks and recurrent neural networks, significant progress has been made in automatic sleep staging. However, existing methods still face challenges in feature extraction and cross-modal data fusion. This paper introduces an innovative deep learning architecture, MultiSEss, aimed at solving key issues in automatic sleep stage classification. The MultiSEss architecture utilizes a multi-scale convolution module to capture signal features from different frequency bands and incorporates a Squeeze-and-Excitation attention mechanism to enhance the learning of channel feature weights. Furthermore, the architecture discards complex attention mechanisms or encoder–decoder structures in favor of a state–space sequence coupling module, which more accurately captures and integrates correlations between multi-modal data. Experiments show that MultiSEss achieved accuracy results of 83.84% and 82.30% in five-fold cross-subject testing on the Sleep-EDF-20 and Sleep-EDF-78 datasets. MultiSEss demonstrates its potential in improving sleep stage accuracy, which is significant for enhancing the diagnosis and treatment of sleep disorders. Full article

Background/Objectives: The purpose of this research is to compare and contrast the application of machine learning and deep learning methodologies such as a dual-branch convolutional neural network (CNN) model for detecting obstructive sleep apnea (OSA) from electrocardiogram (ECG) data. Methods: This approach solves the limitations of conventional polysomnography (PSG) and presents a non-invasive method for detecting OSA in its early stages with the help of AI. Results: The research shows that both CNN and dual-branch CNN models can identify OSA from ECG signals. The CNN model achieves validation and test accuracy of about 93% and 94%, respectively, whereas the dual-branch CNN model achieves 93% validation and 94% test accuracy. Furthermore, the dual-branch CNN obtains a ROC AUC score of 0.99, meaning that it is better at distinguishing between apnea and non-apnea cases. Conclusions: The results show that CNN models, especially the dual-branch CNN, are effective in apnea classification and better than traditional methods. In addition, our proposed model has the potential to be used as a reliable, non-invasive method for accurate OSA detection that is even better than the current state-of-the-art advanced methods. Full article

Background and Objectives: Sleep disorders are highly prevalent in society and require focused attention within healthcare systems. While patient history, reported complaints, and subjective sleep questionnaires can provide initial insights into potential sleep issues, polysomnography (PSG) remains the gold standard for diagnosing various sleep disorders. However, long waiting times for PSG appointments in many healthcare facilities pose challenges for timely diagnosis and treatment. This study aimed to evaluate the diagnostic value of subjective measures, including patient-reported parameters, in comparison to the objective findings of PSG. Materials and Methods: In this study, we retrospectively analysed the data from 562 patients who underwent clinical evaluation and PSG testing at the Hospital of Lithuanian University of Health Sciences Kaunas Clinics between 2018 and 2024. We report the diagnostic accuracy of different sleep questionnaires to detect various sleep disorders in our population. Results: We report the corresponding sensitivity and specificity values: the Epworth Sleepiness Scale (ESS)—73.2% and 44.1% for detecting severe obstructive sleep apnoea and 87.1% and 76.8% for detecting hypersomnia; the Insomnia Severity Index (ISI)—77.2% and 63.3% for detecting insomnia; the Berlin Questionnaire (BQ)—67.8% and 68.8% for detecting obstructive sleep apnoea; the Ullanlina Narcolepsy Scale (UNS)—84.4% and 58.9% for detecting hypersomnia; the Innsbruck REM Sleep Behaviour Disorder Inventory (RBD-I)—93.3% and 52.5% for detecting RBD; the REM Sleep Behaviour Disorder Single-Question Screen (RBD1Q)—73.3% and 81.0% for detecting RBD; and the Paris Arousal Disorder Severity Scale (PADSS)—57.5% and 90.5% for detecting parasomnia. Conclusions: When comparing our findings with the previous literature, we found that the screening tools generally demonstrated a slightly poorer performance in our population. However, our results suggest that certain individual questions from the comprehensive questionnaires may provide comparable diagnostic values, while reducing the patient burden. We propose a targeted screening approach that integrates fundamental clinical parameters, key screening questions, and selected validated questionnaires, enabling primary care and outpatient clinicians to more efficiently identify patients who may require referral for specialised sleep evaluation and treatment. Full article

Objective: Attention-Deficit/Hyperactivity Disorder (ADHD) is a common neurodevelopmental disorder in children, characterized by inattention, hyperactivity, and impulsive behavior. In recent years, studies have shown that patients with ADHD often experience sleep problems, raising clinical interest in the potential role of polysomnography (PSG) in the diagnosis and management of ADHD. This study examines polysomnographic findings in children with ADHD who present with diverse sleep complaints. Methods: A cohort of children aged younger than 18 years, diagnosed with ADHD based on DSM-5 criteria, underwent overnight polysomnography. The study assessed various sleep parameters, including sleep latency, sleep efficiency, total sleep time, and the presence of sleep-disordered breathing. Results: A retrospective analysis was conducted on 36 children (29 boys and 7 girls) aged 6 to 14 years, diagnosed with ADHD, who underwent polysomnography between 2021 and 2024. Polysomnographic findings revealed that 77.78% of the children demonstrated significant snoring. Furthermore, 50.0% were diagnosed with obstructive sleep apnea syndrome (OSAS). In addition, eight children exhibited parasomnias. Among them, six had bruxism, three were diagnosed with periodic limb movement disorder (PLMD), and two experienced sleep talking. Other notable sleep-related conditions included two cases of narcolepsy, one case of prolonged sleep onset latency, and one case of central apnea syndrome. Total sleep time (TST) was significantly longer in females compared to males (400.71 ± 32.68 min vs. 361.24 ± 41.20 min, p = 0.0215), whereas rapid eye movement (REM) latency was longer in males compared to females (118.62 ± 55.60 min vs. 78.57 ± 27.82 min, p = 0.0194). These findings highlight the high prevalence of sleep-disordered breathing (SDB) in children with ADHD who present with sleep disturbances. Furthermore, sleep quality, as indicated by longer TST and shorter REM latency, appears to be better in females with ADHD. Conclusions: The findings of this study underscore the critical role of polysomnography (PSG) in the assessment of children with ADHD. PSG provides an objective evaluation of sleep abnormalities commonly associated with ADHD, which may influence symptom manifestation and treatment outcomes. Notably, the results suggest that females with ADHD exhibit better sleep quality, as indicated by longer total sleep time (TST) and shorter rapid eye movement (REM) latency compared to males. We recommend incorporating polysomnography (PSG) into the comprehensive assessment of children with ADHD who present with significant sleep disturbances. Further research is warranted to investigate the impact of targeted interventions for sleep abnormalities on ADHD symptoms, prognosis, and potential sex-specific differences. Full article

Sleep apnea, characterized by its high prevalence and serious health consequences, faces a critical bottleneck in diagnosis. Polysomnography (PSG), the gold standard, is costly and cumbersome, while wearable devices struggle with quality control and patient compliance, rendering them as unsuitable for both large-scale screening and continuous monitoring. To address these challenges, this research introduces a contactless, low-cost, and accurate event-level sleep apnea detection method leveraging frequency-modulated continuous-wave (FMCW) radar technology. The core of our approach is a novel deep-learning model, built upon the U-Net architecture and augmented with self-attention mechanisms and squeeze-and-excitation (SE) modules, meticulously designed for the precise event-level segmentation of sleep apnea from FMCW radar signals. Crucially, we integrate blood oxygen saturation (SpO₂) prediction as an auxiliary task within a multitask-learning framework to enhance the model’s feature extraction capabilities and clinical utility by capturing physiological correlations between apnea events and oxygen levels. Rigorous evaluation in a clinical dataset, comprising data from 35 participants, with synchronized PSG and radar data demonstrated a performance exceeding that of the baseline methods (Base U-Net and CNN–MHA), achieving a high level of accuracy in event-level segmentation (with an F1-score of 0.8019) and OSA severity grading (91.43%). These findings underscore the significant potential of our radar-based event-level detection system as a non-contact, low-cost, and accurate solution for OSA assessment. This technology offers a promising avenue for transforming sleep apnea diagnosis, making large-scale screening and continuous home monitoring a practical reality and ultimately leading to improved patient outcomes and public health impacts. Full article