Journal of Clinical Sleep Medicine最新文献

Study objectives: Despite frequent sleep disruption in the pediatric intensive care unit, bedside sleep monitoring in real time is currently not available. Supervised machine learning applied to electrocardiography data may provide a solution, because cardiovascular dynamics are directly modulated by the autonomic nervous system during sleep.

Methods: This retrospective study used hospital-based polysomnography recordings obtained in noncritically ill children between 2017 and 2021. Six age categories were defined: 6-12 months, 1-3 years, 3-5 years, 5-9 years, 9-13 years, and 13-18 years. Features were derived in time, frequency, and nonlinear domain from preprocessed electrocardiography data. Sleep classification models were developed for 2, 3, 4, and 5 states using logistic regression, random forest, and XGBoost classifiers during 5-fold nested cross-validation. Models were additionally validated across age categories.

Results: A total of 90 noncritically ill children were included with a median (Q1, Q3) recording length of 549.0 (494.8, 601.3) minutes. The 3 models obtained an area under the receiver operator characteristic curve of 0.72-0.78 with minimal variation across classifiers and age categories. Balanced accuracies were 0.70-0.72, 0.59-0.61, 0.50-0.51, and 0.41-0.42 for 2, 3, 4, and 5 states, respectively. Generally, the XGBoost model obtained the highest balanced accuracy (P < .05), except for 5 states for which logistic regression excelled (P = .67).

Conclusions: Electrocardiography-based machine learning models are a promising and noninvasive method for automated sleep classification directly at the bedside of noncritically ill children aged 6 months-18 years. Models obtained moderate-to-good performance for 2- and 3-state classification.

Citation: van Twist E, Meester AM, Cramer ABG, et al. Supervised machine learning on electrocardiography features to classify sleep in noncritically ill children. J Clin Sleep Med. 2025;21(2):261-268.

Study objectives: We evaluated the efficacy of vibrotactile positional therapy (PT) compared to standard continuous positive airway pressure (CPAP) therapy in mild-to-moderate positional obstructive sleep apnea.

Methods: We conducted a prospective crossover randomized controlled trial of adult patients with treatment-naïve, symptomatic, mild-to-moderate positional obstructive sleep apnea, defined as ≥ 5 total apnea-hypopnea index < 30 with supine-to-nonsupine apnea-hypopnea index ratio ≥ 2. Participants were randomized to in-laboratory treatment initiation polysomnography with either PT or CPAP on sequential nights before an 8-week trial of each therapy. The primary end point was symptomatic improvement (Epworth Sleepiness Scale; ΔESS). Secondary end points included patient preference, usage, sleep architecture, and quality of life measures.

Results: A total of 52 participants were enrolled and completed both arms of the study. Participants were symptomatic with a median ESS score of 12 (interquartile range, 10-14). Treatment resulted in a significant (P < .001) symptomatic improvement with both PT and CPAP (ΔESS 4; interquartile range, 6-11) without a significant difference between treatment arms (P = .782). PT was effective at restricting supine sleep and demonstrated improved sleep efficiency compared with CPAP, although no better than baseline. Both therapies were effective at reducing apnea-hypopnea index, although CPAP demonstrated superior apnea-hypopnea index reduction. There were otherwise no clinically significant differences in sleep architecture, usage, or secondary outcomes including overall patient preference.

Conclusions: In this cohort, treatment with PT or CPAP resulted in clinically significant symptomatic improvement (ΔESS) that was not significantly different between treatment arms. No real difference was seen in other secondary outcome measures. This study provides further evidence to support the use of PT as an alternative first-line therapy with CPAP in appropriately selected patients with positional obstructive sleep apnea.

Clinical trial registration: Registry: Australian New Zealand Clinical Trials Registry; Name: Prospective crossover trial of Positional and Continuous positive airway pressure Therapy for the treatment of mild-to-moderate positional obstructive sleep apnea; URL: https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=377221&isReview=true; Identifier: ACTRN12619000475145.

Citation: Wilson MR, Carroll R, Kinder S, et al. Prospective crossover trial of positional and CPAP therapy for the treatment of mild-to-moderate positional obstructive sleep apnea. J Clin Sleep Med. 2025;21(2):305-313.

A 72-year-old patient had a severe sleep apnea syndrome well controlled for many years through continuous positive airway pressure therapy. When switching to a newer device with upgraded functions, therapy completely failed. A video recording performed by the patient's wife showed high-frequency mask movements suggesting inability to maintain a therapeutic pressure with high-frequency pressure fluctuations, confirmed afterwards during full night polysomnography and in a bench study. Continuous positive airway pressure therapy manufacturers may put on the market new devices with supposedly better algorithms that in fact may have escaped serious premarketing evaluation and that may jeopardize the efficacy of a well proven treatment. We suggest that better evaluations are necessary before marketing therapeutic devices, and that postmarketing assessment of unanticipated side effects should become the norm.

Citation: Mwenge GB, Liistro G, Smetcoren C, Debaille C. Unveiling the hidden risks of CPAP device innovations and the necessity of patient-centric testing. J Clin Sleep Med. 2025;21(2):421-425.

Study objectives: To characterize public practices and perspectives on the use of consumer sleep technology (CST) and evaluate perspectives on using CST as a screening tool for obstructive sleep apnea.

Methods: We designed a survey instrument incorporating content from validated instruments (STOP-Bang and the Epworth Sleepiness Scale) and hypothesis-generated questions. Survey development involved multidisciplinary collaboration among 3 board-certified sleep medicine experts, researchers, and consumers. The survey was disseminated across a national sample of adults living in the United States via an online platform.

Results: Among 897 respondents, the mean (standard deviation) age was 47.5 (16.9) years; 73.1% were female, 81.8% were White, and 505 respondents (56.3%) reported having tracked sleep using CST. Factors associated with decreased odds of CST use included household income < $30,000 (odds ratio [OR] 0.47, 95% confidence interval [CI] 0.28-0.79; P = .004), Medicaid insurance (OR 0.43, 95% CI 0.26-0.69; P = .001), Medicare insurance (OR 0.59, 95% CI 0.41-0.84; P = .004), and lack of a primary care physician (OR 0.55, 95% CI 0.33-0.91; P = .021). Most respondents (91.1%) agreed or strongly agreed that screening for obstructive sleep apnea would be a useful feature of CST, but respondents reporting an education of high school diploma or less (OR 0.48, 95% CI 0.29-0.79; P = .004) were less likely to agree with this statement.

Conclusions: Attitudes toward and use of CST differed based on demographic and socioeconomic factors. Further study is needed to understand and address barriers to CST adoption and to characterize implications for equitable access to care for sleep disorders.

Citation: Lenze NR, Kazemi RJ, Ikeda AK, et al. Public engagement with consumer sleep technology for obstructive sleep apnea screening: implications for equity, access, and practice. J Clin Sleep Med. 2025;21(2):345-353.

Telehealth use greatly expanded under the Centers for Medicare and Medicaid Services waivers at the start of the COVID-19 pandemic; however, the uncertainty and limitations of continued coverage risks loss of this momentum. Permanent coverage with adequate reimbursement is essential for the long-term acceptance and expansion of telehealth services. Telehealth supports both the current and future need for sleep health management by expanding patient access, increasing clinician efficiency, improving patient safety, and addressing health care equity. Sleep medicine is an ideal field for telehealth due to limited provider access, safety concerns with sleepy patients, availability of remote patient monitoring for treatment management, and the minimal need for repeated physical examinations. Telehealth is noninferior for delivery of cognitive behavioral therapy for insomnia and can enhance obstructive sleep apnea treatment adherence. It is the position of the American Academy of Sleep Medicine that telehealth is an essential tool for the provision of high-quality, patient-centered care for patients with sleep disorders. We encourage all stakeholders including legislators, policymakers, clinicians, and patients to work together to address payment models, interstate care, technology access, prescribing practices, and ongoing research to ensure that sleep telehealth services are permanently available and accessible for all patients seeking sleep medicine care.

Citation: Vohra KP, Johnson KG, Dalal A, et al. Recommendations for permanent sleep telehealth: an American Academy of Sleep Medicine position statement. J Clin Sleep Med. 2025;21(2):401-404.

Study objectives: Evaluate the performance of the SANSA device to simultaneously assess obstructive sleep apnea (OSA) and cardiac arrhythmias.

Methods: Participants suspected or known to have OSA underwent polysomnography (PSG) while wearing SANSA. SANSA's algorithm was trained using 86 records and tested on 67 to evaluate training bias. SANSA performance was evaluated against ground truth PSG scored by the consensus of three technologists. PSG scoring from individual testing sites was also evaluated against consensus. Diagnostic performance was evaluated using standard apnea-hypopnea index (AHI) cutoffs. AHI and total sleep time (TST) agreement was analyzed using correlation and Bland-Altman plots. ECG was reviewed for presence of significant arrhythmias (frequent premature atrial/ventricular complexes and atrial fibrillation).

Results: SANSA's sensitivity and specificity to detect OSA ranged from 91-97% and 78-97%, respectively, across all severity levels. SANSA TST correlation with Consensus PSG TST was 0.83 with a mean difference of 3.8 minutes (limits of agreement: -91.1 to 98.7). Significant arrhythmias were detected in 32% of participants. These participants had a greater AHI (27.5 versus 15.8, P=0.003) and spent nearly twice as long at reduced oxygenation levels (47.5 versus 20.5 minutes under 88% SpO₂, P = 0.009).

Conclusions: SANSA is a promising tool for comprehensive OSA evaluation, offering the unique advantage of concurrent arrhythmia detection. This dual functionality may improve patient outcomes through early diagnosis and management of both conditions.