Search Results (59)

The clinical diagnosis of sleep apnea conventionally necessitates resource-intensive Polysomnography (PSG). We propose a weakly supervised framework to detect apnea using non-invasive Ballistocardiography (BCG), thereby addressing the critical scarcity of labeled BCG data. Instead of manual annotation, our pipeline transfers knowledge from a synchronized ECG signal, using it as a “teacher” to generate pseudo-labels for the BCG model. We formulated a User-Defined Function (UDF) that combines Heart Rate Variability and ECG-Derived Respiration to autonomously label the BCG windows. These pseudo-labels were subsequently employed to train a 1D Convolutional Neural Network. Testing on a public dataset, the CNN model achieved 71.8% accuracy against the pseudo-labels. When projected against the clinical ground truth, we estimate a true accuracy of 77.7%. These results validate that ECG-based supervision can effectively train low-cost home sensors without the bottleneck of manual medical annotation. Full article

Background: Obstructive sleep apnea (OSA) is a major modifiable risk factor for atrial fibrillation (AF), promoting arrhythmogenesis through intermittent hypoxia, autonomic activation, and atrial remodeling. Although continuous positive airway pressure (CPAP) effectively treats OSA, real-world evidence linking objectively measured CPAP exposure to clinically relevant AF recurrence remains limited. Aims: We aimed to evaluate the association between CPAP adherence and risk of recurrent paroxysmal AF, and to compare time to first recurrence between patients with mean nightly CPAP use ≥4 h/night versus <4 h/night. Materials and Methods: In this prospective observational cohort (2017–2024), consecutive hospitalized and outpatient adults with severe obstructive sleep apnea (OSA; apnea–hypopnea index > 30 events/h) and documented paroxysmal atrial fibrillation (AF) were enrolled. Persistent and long-standing persistent AF were excluded to ensure a homogeneous population with respect to atrial substrate. OSA was assessed using home sleep apnea testing (ResMed ApneaLink), and all patients initiated continuous positive airway pressure (CPAP) therapy (ResMed AirSense 10). Objective adherence data were obtained via the ResMed AirView telemonitoring platform. Exclusion criteria included permanent AF, prior pulmonary vein isolation, central sleep apnea, left ventricular ejection fraction < 50%, end-stage chronic kidney disease (eGFR < 15 mL/min/1.73 m² or dialysis), or inability to initiate or maintain CPAP therapy. Patients were followed for 12 months. The primary endpoint was time to first documented recurrence of paroxysmal AF (≥30 s on 12-lead electrocardiography or 24-h Holter monitoring). Progression to permanent AF, defined after unsuccessful rhythm control attempts and subsequent transition to a rate control strategy, was assessed as a secondary endpoint. Time-to-event analyses used Kaplan–Meier estimates with log-rank testing, and Cox proportional hazards regression adjusted for age, body mass index, apnea–hypopnea index, heart failure, left atrial volume index, and antiarrhythmic drug therapy. Results: The final analysis included 91 patients (mean age 62.15 ± 8.29 years; 68.13% men). Mean nightly CPAP use was ≥4 h/night in 49 patients and <4 h/night in 42 patients. During follow-up, paroxysmal AF recurrence occurred in 12/49 (24.5%) patients in the ≥4 h/night group and 16/42 (38.1%) in the <4 h/night group. Mean arrhythmia-free survival at 12 months was numerically higher in the ≥4 h/night group (11.25 vs. 10.51 months), without a statistically significant difference in Kaplan–Meier curves (log-rank p = 0.11). In multivariable Cox regression, binary adherence (≥4 h/night) was not independently associated with recurrence (HR 0.52, p = 0.13), whereas mean nightly CPAP use analyzed as a continuous variable remained independently associated with delayed recurrence (per 1-h increase: HR 0.66, 95% CI 0.48–0.91, p = 0.01). Progression to permanent AF occurred in 4/49 (10.0%) versus 9/42 (17.6%) patients, respectively (p = 0.29). Conclusions: In this real-world cohort of patients with severe OSA and paroxysmal AF, higher objectively measured CPAP exposure was independently associated with delayed AF recurrence when analyzed as a continuous variable, suggesting a graded association between objectively measured CPAP exposure and AF recurrence. Larger studies with extended follow-up and continuous rhythm monitoring are warranted to confirm long-term rhythm benefits and effects on AF progression. Full article

Background: Obstructive Sleep Apnea (OSA) is highly prevalent yet underdiagnosed due to the scarcity of Polysomnography (PSG) resources. Audio-based screening offers a scalable solution, but often lacks the granularity to precisely localize respiratory events or accurately estimate the Apnea-Hypopnea Index (AHI). This study aims to develop a fine-grained and lightweight detection framework for OSA screening, enabling precise respiratory event localization and AHI estimation using non-contact audio signals. Methods: A Dual-Stream Convolutional Recurrent Neural Network (CRNN), integrating Log Mel-spectrograms and energy profiles with BiLSTM, was proposed. The model was trained on the PSG-Audio dataset (Sismanoglio Hospital cohort, 286 subjects) and subjected to a comprehensive three-level evaluation: (1) frame-level classification performance; (2) event-level temporal localization precision, quantified by Intersection over Union (IoU) and onset/offset boundary errors; and (3) patient-level clinical utility, assessing AHI correlation, error margins, and screening performance across different severity thresholds. Generalization was rigorously validated on an independent external cohort from Beijing Tongren Hospital (60 subjects), which was specifically curated to ensure a relatively balanced distribution of disease severity. Results: On the internal test set, the model achieved a frame level macro F1 score of 0.64 and demonstrated accurate event localization, with an IoU of 0.82. In the external validation, the audio derived AHI showed a strong correlation with PSG-AHI (r = 0.96, MAE = 6.03 events/h). For screening, the model achieved sensitivities of 98.0%, 89.5%, and 89.3%, and specificities of 88.9%, 90.9%, and 100.0% at AHI thresholds of 5, 15, and 30 events per hour, respectively. Conclusions: The Fine-Grained and Lightweight Dual-Stream CRNN provides a robust, clinically interpretable solution for non-contact OSA screening. The favorable screening performance observed in the external cohort, characterized by high sensitivity for mild cases and high specificity for severe disease, highlights its potential as a reliable tool for accessible home-based screening. Full article

The interpretation and diagnosis of central sleep apnea in pediatrics by nocturnal polysomnography is challenging due to its technical complexity, which involves the simultaneous recording of multiple physiological parameters related to sleep and wakefulness. Furthermore, the unfamiliar environment of a sleep laboratory can hinder sleep evaluation, and diagnostic backlogs are common due to restricted capacity at specialist tertiary centers. The ability to undertake home sleep studies in a familiar environment using simple, robust, and low-cost technology is attractive. The potential to repurpose the PneumoWave biosensor, a UKCA Class 1 device, registered as an accelerometer-based monitoring device that is intended to capture and store chest motion data continuously over a period of time for retrospective analysis, was explored in an in vitro model of central sleep apnea. The PneumoWave system contains a biosensor (PW010), which was able to record simulated apnea episodes of 5 to 20 s across physiologically relevant pediatric breathing rates using an in vitro manikin model and manual annotation. The findings confirm that the PneumoWave biosensor could be a useful technology to support home sleep apnea testing and warrant further exploration. Full article

Background: Orofacial myofunctional therapy (OMT) is an emerging adjunctive treatment for obstructive sleep apnea (OSA), but its effects on upper airway structural support, particularly the hyoid complex, are not well defined. This study assessed the short-term effects of OMT on hyoid bone position and sleep-related indices in adults with mild to moderate OSA. Methods: In this assessor-blinded randomized controlled trial (ClinicalTrials.gov Identifier: NCT06079073), 13 adults with mild to moderate OSA were randomized to a 12-week web-based OMT program (n = 9) or a waitlist control group (n = 4). Cone-beam computed tomography (CBCT) and three-night home sleep testing were performed at baseline and follow-up. The primary outcome was change in axis-based cephalometric hyoid position measures; secondary outcomes included sleep parameters such as the apnea–hypopnea index (AHI). Results: No significant within- or between-group differences were observed in AHI, oxygen desaturation index, or mean nocturnal SpO₂ after 12 weeks (all p > 0.05). However, several cephalometric variables showed significant between-group differences. The waitlist group exhibited greater posterior–inferior hyoid displacement than the OMT group, with large effect sizes across multiple vector measures (all p ≤ 0.045; r = 0.56–0.66). Posterior and inferior hyoid displacement was associated with higher AHI and lower SpO₂, whereas increased lower pharyngeal airway width was associated with lower AHI. Conclusions: Short-term OMT did not improve sleep-disordered breathing indices but was associated with stabilization of hyoid bone position. These findings suggest that structural stabilization may precede functional improvement and highlight the clinical relevance of vector-based hyoid analysis. Full article

Background/Objectives: Polysomnography (PSG) is the gold standard for diagnosing sleep-disordered breathing (SDB). However, in a hospital testing setting, it may produce the first-night effect, viz., prolonged sleep latency, lower sleep efficiency, and uncertain apnea–hypopnea index (AHI). Here, we aim to determine the influences of hypnotic agents and gender. Methods: In this retrospective study, we reviewed the post-PSG questionnaires and electronic medical records of patients aged ≥20 years receiving overnight PSG for the diagnosis of SDB at Taichung Veterans General Hospital in a period between April 2024 and March 2025. Results: We studied a total of 1053 patients, aged 47.0 ± 14.7 years old. Compared to sleeping at home, 42.2% of patients reported worse perceived sleep quality (PSQ) with hypnotic agents, and 53.0%, without, before PSG testing in the hospital. For those without taking hypnotic agents, men had an odds ratio (OR) of 1.570 (95% CI: 1.127–2.189) for worsening PSQ compared to women (p = 0.008). Also, per increasing 1 Epworth Sleepiness Scale (ESS) score, the risk of worsening PSQ was reduced by OR of 0.963 (95% CI: 0.933–0.994) (p = 0.021). Once male patients had ESS < 10, as many as 57.3% of them reported the worse PSQ. Conclusions: Our study suggests a potentially more patient-centric approach to diagnosing sleep-disordered breathing. In some male patients with ESS scores < 10, short-acting hypnotics might be considered during in-lab PSG to improve subjective comfort, thereby potentially enhancing study reliability. Meanwhile, home sleep apnea testing can serve as a practical initial tool for selected patients—offering convenience, mitigating the first-night effect, and potentially reducing long wait times. However, its use in individuals with comorbid insomnia requires careful clinical judgment to avoid false-negative results, often making in-lab assessment the preferred option in such cases. Full article

Background/Objectives: Obstructive sleep apnea (OSA) during pregnancy may reduce maternal oxygenation, cause sleep fragmentation, and influence offspring development. This pilot study explored potential associations between OSA during pregnancy and child outcomes at age 3. Methods: Pregnant women aged 23–48 years who underwent home sleep apnea testing (HSAT) at 28–32 weeks of gestation between June 2021 and July 2025 were enrolled. OSA was defined as an apnea–hypopnea index (AHI) ≥ 5. Mothers and children were prospectively followed until the child reached 3 years of age. Children’s developmental levels (motor, cognitive/adaptive, language/social, and total) were evaluated using the New K-Type Developmental Test. Anthropometric measures (height, weight, and head circumference) and dental occlusion were also assessed. Correlations between the maternal AHI and developmental indices were examined. Results: Thirty-four women, including six with OSA, completed the follow-up assessment. No significant differences were observed in children’s physical growth or occlusion between the OSA and non-OSA groups. The maternal AHI showed a negative tendency with the total developmental index and the cognitive/adaptive and language/social domains. One participant with severe OSA (AHI = 69.3) showed markedly lower developmental scores, suggesting a possible dose-dependent trend rather than a definitive threshold. Given the small number of OSA cases and the influence of a single severe case, these findings should be interpreted cautiously as preliminary and descriptive. Conclusions: OSA during pregnancy may be associated with differences in early childhood development. The findings highlight the importance of maternal sleep health awareness and feasible screening approaches, such as HSAT, during pregnancy. Full article

Background: Obstructive sleep apnea (OSA) is frequent but underrecognized after stroke, worsening prognosis, recurrence, and mortality. Polysomnography is rarely feasible in acute care, and existing screening tools have limited accuracy. We aimed to identify simple OSA clinical predictors to improve risk stratification in stroke patients. Methods: In this prospective study, 116 consecutive acute stroke patients (mean age 73 years, 57% male) underwent standardized clinical evaluation, Berlin Questionnaire, Epworth Sleepiness Scale (ESS), and home sleep apnea test during hospitalization. OSA was defined as apnea–hypopnea index (AHI) ≥ 15. Logistic regression identified independent predictors; the model’s performance was assessed by accuracy, sensitivity, specificity, and ROC curves. Results: OSA was diagnosed in 42 patients (36%). OSA patients showed higher NIHSS at admission (p = 0.048) and higher ESS scores (p = 0.047), but similar vascular risk factors and stroke subtypes compared to non-OSA patients. In a multivariate analysis, age (OR 1.05; 95% CI 1.00–1.10; p = 0.036) and witnessed apneas (OR 6.20; 95% CI 1.31–29.22; p = 0.021) were OSA independent predictors. The two-variable models achieved 72.9% accuracy, 90.3% specificity, 41.2% sensitivity, Nagelkerke R² = 0.223, and AUC = 0.739 (p < 0.001), outperforming both the Berlin Questionnaire (AUC 0.596) and ESS (AUC 0.616). Conclusions: A simple model based on age and witnessed apneas reliably identified stroke patients at high risk for OSA, with good discriminative performance and higher accuracy than standard questionnaires. Its high specificity supports targeted allocation of sleep studies in resource-limited acute settings, potentially improving early detection, secondary prevention, and care pathways after stroke. Full article

Obstructive sleep apnea–hypopnea syndrome (OSAHS) is a prevalent sleep disorder strongly linked to increased cardiovascular and metabolic risk. While prior studies have explored snore-based analysis for OSAHS, they have largely focused on either detection or classification in isolation. Here, we present a two-stage framework that integrates precise snoring event detection with deep learning-based classification. In the first stage, we develop an Adaptive Multi-Feature Fusion Endpoint Detection algorithm (AMFF-ED), which leverages short-time energy, spectral entropy, zero-crossing rate, and spectral centroid to accurately isolate snore segments following spectral subtraction noise reduction. Through adaptive statistical thresholding, joint decision-making, and post-processing, our method achieves a segmentation accuracy of 96.4%. Building upon this, we construct a balanced dataset comprising 6830 normal and 6814 OSAHS-related snore samples, which are transformed into Mel spectrograms and input into ERBG-Net—a hybrid deep neural network combining ECA-enhanced ResNet18 with bidirectional GRUs. This architecture captures both spectral patterns and temporal dynamics of snoring sounds. The experimental results demonstrate a classification accuracy of 95.84% and an F1 score of 94.82% on the test set, highlighting the model’s robust performance and its potential as a foundation for automated, at-home OSAHS screening. Full article

Obstructive sleep apnea (OSA) is a highly prevalent and underdiagnosed sleep disorder with significant cardiovascular implications, namely in atrial fibrillation (AF) patients. Despite its clinical relevance, OSA prevalence among AF patients and the diagnostic strategies used remain heterogeneous across studies, complicating screening, and treatment pathways. Our aim was to synthesize recent evidence on OSA prevalence in AF populations and to critically evaluate the diagnostic methods and screening strategies employed in clinical studies, by conducting a systematic review using PubMed and Google Scholar to identify original clinical studies published between January-2019 and December-2024. Inclusion criteria targeted adult AF populations assessed for OSA or sleep-disordered breathing. The results were analyzed by two independent reviewers. Non-concordances were resolved by consensus. Data extracted included study characteristics, population profiles, diagnostic approaches, prevalence rates, symptom profiles, and clinical correlates. Thirty-eight studies were included, comprising predominantly observational studies. Prevalence estimates of OSA in AF populations ranged from 5% to 90%, with most studies reporting rates > 60%. A consistent burden of moderate-to-severe OSA was observed. Diagnostic methods varied widely, from polysomnography (PSG) and home sleep apnea testing to pacemaker-derived monitoring and questionnaires such as STOP-Bang and Epworth Sleepiness Scale (ESS). Underdiagnosis was attributed to minimal symptomatology, lack of physician awareness, and reliance on subjective tools. Several studies highlighted the limited sensitivity of standard screening instruments in AF populations and advocated for objective testing even in asymptomatic patients. Marked heterogeneity in study designs, diagnostic methods, and populations precluded quantitative synthesis and limited direct comparisons. Objective diagnostic testing, particularly PSG, is essential to improve OSA detection rates and guide individualized management. Integration of structured screening protocols into AF care—especially for high-risk patients—and interdisciplinary collaboration are critical. Full article

Poor sleep quality and excessive daytime sleepiness are commonly reported by individuals with cystic fibrosis. The potential impact of comorbid sleep-disordered breathing (SDB), particularly obstructive sleep apnea (OSA), has not been extensively studied in the CF population. At present, there are no specific recommendations available to help clinicians identify patients with CF who are at increased risk of sleep disorders. Home sleep apnea testing using a validated peripheral arterial tonometry (PAT) device may offer an accurate diagnosis of OSA in a more convenient and low-cost method than in-lab polysomnography. In this single-center study of 19 adults with CF, we found an increased prevalence of OSA among individuals with CF compared to general population estimates. Although associations with an FEV < 70% predicted and a modified Mallampati score ≥ 3 were observed, these odds ratios did not reach statistical significance, likely reflecting limited power in this small pilot sample. There was no association found between the self-reported presence of nocturnal cough or snoring and OSA. We also found no association between OSA and abnormal scores on commonly used, validated sleep questionnaires, suggesting that CF-specific scales may be needed for effective screening in the CF clinic. Full article

Measurement of respiratory patterns during sleep plays a critical role in assessing sleep quality and diagnosing sleep disorders such as sleep apnea syndrome, which is associated with many adverse health outcomes, including cardiovascular disease, diabetes, and cognitive impairments. Traditional methods for measuring breathing often rely on expensive and complex sensors, such as polysomnography equipment, which can be cumbersome and costly and are typically confined to clinical settings. These factors limit the performance of respiratory monitoring in routine settings and prevent convenient and extensive screening. Recognizing the need for accessible and cost-effective solutions, we developed a portable sleep sensor that uses an electret condenser microphone (ECM), which is inexpensive and easy to obtain, to measure nasal airflows. Constant current circuits that bias the ECM and circuit constants suitable for measurement enable special uses of the ECM. Furthermore, data transmission through the XBee wireless communication module, which employs the ZigBee short-range wireless communication standard, enables highly portable measurements. This customized configuration allows the ECM to detect subtle changes in airflow associated with breathing patterns, enabling the monitoring of respiratory activity with minimal invasiveness and complexity. Furthermore, the wireless module not only reduces the size and weight of the device, but also facilitates continuous data collection during sleep without disturbing user comfort. This portable wireless sensor runs on batteries, providing approximately 50 h of uptime, a ±50 Pa pressure range, and 20 Hz real-time sampling. Our portable sleep sensor is a practical and efficient solution for respiratory monitoring outside of the traditional clinical setting. Full article

Obstructive sleep apnea (OSA) is common among older populations and individuals with cardiovascular diseases. OSA diagnosis is primarily conducted using polysomnography or recommended home sleep apnea test (HSAT) devices. Wireless wearable devices have emerged as promising tools for OSA screening and follow-up. This study introduces a novel automated algorithm for detecting OSA using abdominal movement signals and acceleration data collected by a wireless abdomen-worn sensor (Soomirang). Thirty-seven subjects underwent overnight monitoring using an HSAT device and the Soomirang system simultaneously. Normal and apnea events were classified using an MLP-Mixer deep learning model based on Soomirang data, which was also used to estimate total sleep time (ST). Pearson correlation and Bland–Altman analyses were conducted to evaluate the agreement of ST and the apnea–hypopnea index (AHI) calculated by the HSAT device and Soomirang. ST demonstrated a correlation of 0.9 with an average time difference of 7.5 min, while AHI showed a correlation of 0.95 with an average AHI difference of 3. The accuracy, sensitivity, and specificity of the Soomirang for detecting OSA were 97.14%, 100%, and 95.45% at AHI ≥ 15, respectively. The proposed algorithm, utilizing data from a wireless abdomen-worn device exhibited excellent performance in detecting moderate to severe OSA. The findings underscored the potential of a simple device as an accessible and effective tool for OSA screening and follow-up. Full article

Background: The high prevalence of obstructive sleep apnea (OSA), about 30% of people worldwide over 30 years old, underscores the crucial need for early screening. This study aimed to identify key predictive factors for OSA; use these factors to develop a screening equation for a population at high risk for OSA; and prospectively validate this equation’s application. Methods: The study included two phases: a retrospective phase examining anthropometric data, the Epworth sleepiness scale (ESS), and the home sleep apnea test (HSAT) from 200 patients referred to the Respiratory Sleep Disorder Center at Policlinico Umberto I, Rome, Italy (January 2020–January 2023) to create a predictive equation for OSA using multivariate analysis (with the most predictive data according to scientific literature). A prospective phase testing this equation on 53 patients from May 2023 to September 2024. Results: In the retrospective phase, the most predictive variables for the apnea–hypopnea index (AHI) identified were neck circumference (NC) and the Epworth sleepiness scale (ESS). The predictive equation derived from the multivariate analysis was as follows: AHIp = [−70.498 + (2.196 × NC) + (0.809 × ESS)]. In the prospective phase of the study, we compared the AHI predicted by the equation (AHIp) with the AHI measured via the HSAT (AHIm) in 53 patients recruited. The results showed that AHIp had a sensitivity of 95%, a specificity of 28%, a positive predictive value (PPV) of 46%, and a negative predictive value (NPV) of 90%. Conclusions: This study identified NC and ESS as key predictors of OSA, forming a predictive equation. This equation, showing high sensitivity and high NPV, may be useful as a screening method to rule out OSA. Full article

Obstructive sleep apnea (OSA) is a heterogenous disease process that cannot be adequately categorized by AHI alone. There is a significant prevalence of OSA in the general population with ongoing efforts to evaluate the risk factors contributing to OSA and its associated clinical implications. Only by improving our understanding of OSA can we advance our methods in the diagnosis and treatment of OSA. For this article, the authors reviewed keywords of obstructive sleep apnea diagnosis and therapy in the databases of Embase, Medline, and Medline ePub over the past 3 years, excluding any articles that only addressed sleep apnea in children under age 17 years. This review article is divided into three main sections. First, we will investigate the use of novel screening tools, biomarkers, anthropometric measurements, and novel wearable technologies that show promise in improving the diagnosis of OSA. There is mention of comorbid conditions seen in OSA patients since certain disease combinations can significantly worsen health and should raise our awareness to diagnose and manage those concomitant disorders. The second section will look at the current and developing treatment options for OSA. These include positive airway therapy (PAP), mandibular advancement device (MAD), exciting new findings in certain medications, orofacial myofunctional therapy (OMT), hypoglossal nerve stimulation therapy (HGNS), and other surgical options. We will conclude with a section reviewing the current Clinical Practice Guidelines for Diagnostic Testing in Adults with Obstructive Sleep Apnea from 2017, which strongly advises polysomnography (PSG) or home sleep apnea testing (HSAT), along with comprehensive sleep evaluation for uncomplicated patients with a clinical presentation of OSA. Full article