Background and Objectives: Polysomnography is manually scored by sleep experts. However, manual scoring is a time-consuming and labor-intensive task. The goal of this study was to verify the accuracy of automated sleep-stage scoring based on a deep learning algorithm compared to manual sleep-stage scoring. Materials and Methods: A total of 602 polysomnography datasets from subjects (Male:Female = 397:205) aged 19 to 65 years (mean age, 43.8, standard deviation = 12.2) were included in the study. The performance of the proposed model was evaluated based on kappa value and bootstrapped point-estimate of median percent agreement with a 95% bootstrap confidence interval and R = 1000. The proposed model was trained using 482 datasets and validated using 48 datasets. For testing, 72 datasets were selected randomly. Results: The proposed model exhibited good concordance rates with manual scoring for stages W (94%), N1 (83.9%), N2 (89%), N3 (92%), and R (93%). The average kappa value was 0.84. For the bootstrap method, high overall agreement between the automated deep learning algorithm and manual scoring was observed in stages W (98%), N1 (94%), N2 (92%), N3 (99%), and R (98%) and total (96%). Conclusions: Automated sleep-stage scoring using the proposed model may be a reliable method for sleep-stage classification.

Objective: Positive airway pressure (PAP) therapy effectively treats obstructive sleep apnea (OSA), yet adherence to the therapy presents significant challenges. This study identifies demographic and sleep study factors that influence short-term adherence to PAP therapy among patients with OSA by comparing data from adherent and non-adherent groups. Methods: Patients diagnosed with OSA via polysomnography who commenced PAP therapy after titration were divided into adherent and non-adherent groups. We employed propensity score matching in a 1:1 ratio based on age, gender, and body mass index (BMI), including a total of 150 patients in the analysis. Logistic regression analyses were conducted on all pertinent variables, excluding those with high multicollinearity. Non-significant variables were omitted from the final model, whose performance was evaluated using a receiver operating characteristic (ROC) curve, calculating the area under the curve (AUC). Results: Data from 150 participants (mean age 49.56 ± 14.31 years, 79% males, mean BMI 28.96 ± 5.11) were analyzed. Significant predictors of adherence included smoking status (odds ratio [OR] 0.267; 95% confidence interval [CI], 0.116–0.580; p = 0.001), Epworth sleepiness scale (OR 1.080; 95% CI, 1.004–1.166; p = 0.042), oxygen desaturation index (ODI) during titration (OR 0.906; 95% CI, 0.829–0.975, p = 0.015), and optimal PAP levels (OR 1.240; 95% CI, 1.007–1.119; p = 0.029). The ROC curve analysis indicated an AUC of 0.765, confirming the model’s effectiveness in distinguishing between adherent and non-adherent patients. Conclusions: Adherence is negatively affected by smoking, whereas higher daytime sleepiness, optimal PAP levels, and a lower ODI during titration are associated with better adherence, underscoring the importance of personalized treatment approaches.

Background and Objectives: Although numerous studies have explored various predictors of positive airway pressure (PAP) adherence, the potential impact of objective sleep scoring data obtained during PAP titration on adherence has not been thoroughly investigated. The objective of this study was to evaluate the association between objective sleep parameters obtained from PAP titration, including sleep efficiency (SE), wake after sleep onset (WASO), and sleep latency (SL), and short-term PAP adherence in individuals with obstructive sleep apnea (OSA). Materials and Methods: A total of 227 individuals with a confirmed diagnosis of OSA underwent overnight PAP titration and were subsequently divided into adherence and non-adherence groups. Baseline demographic characteristics, clinical data, diagnostic polysomnography results, and PAP titration data were obtained for all subjects. Paired sample t-tests were utilized to assess differences in sleep parameters between diagnostic polysomnography and PAP titration within each group. Binomial logistic regression was used to evaluate the predictive value of changes in SE, WASO, and SL for PAP adherence and to determine optimal cut-off values. A χ² analysis was conducted to assess the relationship between categorical improvements in SE and WASO and adherence to PAP therapy. Results: Among the study cohort, 176 (77.5%) participants were classified as adherent, while 51 (22.5%) participants were classified as non-adherent. SE during PAP titration (83.3 ± 12.6%) was significantly higher compared to baseline polysomnography (80.9 ± 12.4%, p = 0.020), and WASO was significantly reduced (63.9 ± 58.9 min vs. 77.7 ± 67.2 min, p = 0.016). No significant difference was observed in SL between the two groups. Logistic regression analysis indicated that increased SE (odds ratio [OR]: 1.025, p = 0.039) and decreased WASO (OR: 0.994, p = 0.027) both served as significant predictors of PAP adherence, but the overall predictive ability of these indicators was modest (area under the curve 0.60 for SE; 0.62 for WASO). The optimal thresholds distinguishing adherence were ΔSE ≥ 2.39% and ΔWASO < −1.5 min. Participants who exhibited improvements in SE (χ² = 5.296, p = 0.021) and WASO (χ² = 6.877, p = 0.009) demonstrated a significantly higher likelihood of adhering to PAP therapy. Conclusions: The findings demonstrate that objective increases in sleep quality, specifically elevated SE and decreased WASO during initial PAP titration, are significantly associated with short-term PAP adherence among patients with OSA.

Background: Polysomnography (PSG) is the gold standard for diagnosing sleep disorders. However, the subjectivity of manual scoring can lead to inter-scorer variability, undermining diagnostic accuracy and subsequent clinical decisions. This study aims to quantitatively assess scoring concordance among multiple scorers across various clinical subgroups to identify the factors that contribute to interpretive discrepancies. Methods: We conducted a retrospective analysis of overnight diagnostic PSG data from adult patients at a tertiary university hospital sleep center. Interrater reliability was evaluated by three independent expert scorers for 30 subjects selected through stratified random sampling. The polysomnographic data were independently and blindly scored according to the American Academy of Sleep Medicine criteria, focusing on sleep stages, arousals, respiratory events, and leg movements, all scored in 30 s epochs. Interrater agreement was measured using Fleiss’ κ, along with 95% confidence intervals, and included subgroup analyses by diagnostic category. Results: The analysis included a total of 28,291 epochs from 30 adults across normal, insomnia, obstructive sleep apnea (OSA) [mild–severe], and periodic limb movement (PLM) disorder subgroups. The overall interrater agreement for sleep staging among the three scorers was nearly perfect (Fleiss’ κ = 0.932), with the highest concordance observed in stages W, N2, and R, and excellent agreement in stages N1 and N3. Respiratory events showed particularly high reliability, with near-perfect agreement for apnea (κ = 0.955) and substantial agreement for hypopnea, arousals, and PLMs. Pairwise analyses indicated the highest concordance between scorer 1 and scorer 3, while the agreement between scorer 1 and scorer 2 was lower, particularly for detecting arousals and limb movements. Subgroup analyses showed the highest and most stable agreement in moderate OSA, whereas severe OSA exhibited reduced reliability for sleep staging and arousal scoring, indicating increased scoring complexity with greater sleep fragmentation. Conclusions: Although expert PSG scoring demonstrates high overall reliability, significant variability persists in complex cases like severe OSA. These findings underscore the necessity for structured quality assurance and automated tools to improve diagnostic consistency in clinical practice.

Background and Objective Few clinical studies have investigated the accuracy of non-contact monitoring devices for vital signs during sleep and sleep architecture in adults with sleep-disordered breathing (SDB). The purpose of this study was to assess the accuracy of a contactless monitoring device for 1) heart rate, respiratory rate, and body temperature during sleep and 2) sleep architecture in adults with SDB.Methods Thirty-five consecutive adults, who visited a tertiary university hospital due to suspected SDB, underwent a complete physical examination and standard (level 1) polysomnography plus body temperature measurement with a contactless monitoring device (HoneyCube System).Results A total of 30 subjects (mean age = 46.43 ± 12.9 years; male: female = 22: 8) were finally included, and five subjects were excluded due to inadequate data in this study. The intraclass correlation coefficient values of heart rate, respiratory rate, and body temperature measured using the contactless monitoring device were 0.91 (95% confidence interval [CI]: 0.892, 0.928), 0.937 (95% CI: 0.919, 0.954), and 0.918 (95% CI: 0.895, 0.941), respectively. The mean kappa value for sleep architecture was 0.562 (95% CI: 0.529, 0.596).Conclusions The contactless monitoring device showed good (almost perfect) agreement in terms of heart rate, respiratory rate, and body temperature and moderate agreement in sleep architecture with contact measurements. These results suggest that the HoneyCube System is a good candidate device for sleep monitoring at home and in multiple accommodations.