STUDY OBJECTIVES:Polysomnography (PSG) provides a comprehensive assessment of brain, cardiac, and respiratory activity during sleep. While it is widely used for diagnosing sleep disorders, its potential to assess future health risks has not been fully explored. This study aimed to develop and evaluate an interpretable framework to identify physiological patterns in PSG data linked to cardiovascular disease (CVD) outcomes, without relying on manual annotations (e.g. sleep stages). METHODS:We developed a self-supervised deep learning model that extracts meaningful patterns from multi-modal signals (electroencephalography [EEG], electrocardiography [ECG], and respiratory signals [Resp]). The model was trained on data from 4398 participants. Projection scores were derived by contrasting embeddings from individuals with and without CVD outcomes. External validation was conducted in an independent cohort with 1093 participants. The source code is available on https://github.com/miraclehetech/sleep-ssl. RESULTS:The projection scores revealed distinct and clinically meaningful patterns across modalities. ECG-derived features were predictive of both prevalent and incident cardiac conditions, particularly CVD mortality. EEG-derived features were predictive of incident hypertension and CVD mortality. Resp added complementary predictive value. Combining projection scores with the Framingham Risk Score consistently improved prediction, with area under the curve values ranging from 0.607 to 0.965 in the Sleep Heart Health Study test cohort and 0.710 to 0.807 across four of five outcomes in the external validation cohort, demonstrating robust cross-cohort generalizability. CONCLUSIONS:Our findings demonstrate that the proposed framework can generate individualized CVD risk scores directly from PSG data. The resulting projection scores have the potential to be integrated into clinical practice, enhancing risk assessment and supporting personalized care. Statement of Significance This study is among the first to apply a self-supervised framework for cardiovascular risk profiling using polysomnography (PSG) data. By transforming electroencephalography, electrocardiography, and Resp into interpretable projection scores, we identified physiological markers predictive of multiple cardiovascular outcomes. These risk profiles, combined with traditional risk scores, significantly improved prediction across both internal and external cohorts. Our findings highlight the untapped potential of PSG signals beyond sleep staging, providing an interpretable, scalable, and clinically actionable approach for personalized cardiovascular risk stratification.

INTRODUCTION:Sleep is a key component of a healthy lifestyle and the Center for Disease Control (CDC) and prevention recommends that adults get at least 7 hours of sleep each night. Within the United States, West Virginia is among the most sleep-deprived states with 42% of the population reporting insufficient sleep per the CDC. Sleep insufficiency in rural populations is linked to disparities in health and accessibility to health care services. The study evaluated the impact of sleep hygiene (SH) education on sleep duration and quality. METHODS:A 12-week randomized controlled trial of participants residing in Harrison County, WV. Baseline data included the Pittsburgh Sleep Quality Index (PSQI), Epworth Sleepiness Scale, and sleep duration as recorded by a sleep wearable. The intervention included an SH video on weeks 3 and 5. The control arm did not receive intervention but were allowed to cross over and receive intervention at week 8. RESULTS:A total of 100 participants (61 females) were recruited from the community. No changes in sleep duration were observed in intention to treat analysis between Arm 1 and Arm 2 at 7 weeks. In the treatment analysis, the compliant cohort demonstrated a significant increase of 31 minutes mean sleep duration (P = .01) as well as an improvement in the PSQI (6.30 to 5.68 by week 12, P = .05). CONCLUSION:The study demonstrates that the introduction of a modest SH intervention may have a beneficial effect on the duration and quality of sleep in a rural community. CLINICALTRIALS:gov Identifier: NCT04849572.

Over the past century, sleep has transitioned from the domain of artists, poets, and philosophers to the realm of scientists and clinicians. In the 20th century, pioneering sleep researchers and clinicians advanced their respective fields by forming organizations such as the American Academy of Sleep Medicine (AASM). For 50 years, the AASM has played a leading role in creating and shaping the field of sleep medicine, leveraging the multi-disciplinary expertise of its members to forge a new medical specialty. The organization emerged from a meeting in 1975, where academics whose research focused on sleep gathered to evaluate the necessity of establishing a new professional society to represent the nascent sleep disorders centers that were beginning to open across the country. The formation of the AASM was led by Dr. William Dement and other pioneers who played crucial roles in establishing the field through the clinical application of sleep research. Through the AASM, they created the building blocks of a medical specialty by developing accreditation and certification programs, diagnostic classifications, clinical practice guidelines, clinical training programs, peer-reviewed scientific journals, and a clinical and scientific meeting. Their persistent efforts eventually secured for the sleep medicine specialty both national recognition and broad acceptance within the medical community. Today, the field of sleep medicine remains strong as sleep physicians and other members of the clinical sleep team provide high-quality, comprehensive care for patients who have sleep and circadian disorders. Built on this solid foundation, the AASM and its members will continue to shape the future of sleep medicine.

Shiftwork is common and in 10-43% of individuals it leads to a diagnosis of shift work disorder (SWD), characterized by excessive sleepiness accompanied by reduced sleep duration and/or insomnia. While more individuals work early morning shifts compared to overnight shifts, few studies have investigated this population. We aimed to evaluate the efficacy of solriamfetol for the treatment of excessive sleepiness during workdays in participants with SWD who work early-morning shifts. We conducted a randomized, double-blind, placebo-controlled 4-week clinical trial in early morning shift workers (shift start 3-7AM). Participants had to report excessive daytime sleepiness and be at high risk for SWD as determined by a SWD questionnaire. Following screening and 2 weeks of baseline, participants were randomized into 4 weeks of placebo or solriamfetol (150mg taken after waking on workdays). The primary outcome was objective sleepiness measured by Maintenance of Wakefulness Test (MWT). Secondary outcomes included subjective sleepiness [measured by Karolinska Sleepiness Scale (KSS) and Epworth Sleepiness Scale (ESS)] and severity of illness [measured by Clinical Global Impression (CGI-Change) and Patient Global Impression (PGI-Change)]. Mixed-effects and logistic regression models were used to analyze the data. 74 participants completed study (median age 37 [28-46]; 27 females); 38 in the solriamfetol group and 36 in the placebo group. There was a significant difference between groups in the change in MWT sleep latency from baseline to end-of-treatment (p< 0.0001), with a greater increase in the solriamfetol group (12.5min, p< 0.0001) compared to placebo (3.1min, p=0.0108). There was a significant difference (p=0.0001) between the groups in the change in KSS and ESS scores, with a greater decrease in the solriamfetol group (KSS: -1.7, p< 0.0001; ESS: -7.2, p< 0.0001) compared to placebo (KSS: -0.5, p=0.0167; ESS: -2.4, p=0.0044). Finally, solriamfetol resulted in a higher percentage of participants showing improvement at end-of-treatment visit compared to placebo on CGI-Change (OR=4.4, p=0.0014) and on PGI-Change (OR=5.4, p=0.0002). Solriamfetol significantly improved objective and subjective sleepiness and reduced the severity of illness compared to placebo in participants with SWD who work early-morning shifts. www.clinicaltrials.gov (NCT04788953). Axsome Therapeutics, Jazz Pharmaceuticals, and Brigham and Women’s Hospital Center for Clinical Investigation.

Daridorexant, a dual orexin receptor antagonist, is approved for the treatment of insomnia disorder in adults. Approximately 30%-35% of patients with insomnia disorder also have obstructive sleep apnoea (OSA) of any severity. It is unclear whether sleep medications provide safe and effective treatment for insomnia in these patients. This post hoc analysis evaluated the efficacy and safety of daridorexant 25 and 50 mg on objective and self-reported insomnia variables and self-reported daytime functioning in patients with untreated mild OSA and comorbid insomnia disorder (COMISA). This analysis included participants with insomnia disorder enrolled in the Phase 3 study assessing either daridorexant 25 or 50 mg with an apnoea/hypopnoea index 5-< 15 events/h ('mild OSA'). Wake after sleep onset (WASO), latency to persistent sleep (LPS), self-reported total sleep time (sTST) and the Insomnia Daytime Symptoms and Impacts Questionnaire (IDSIQ) were assessed at Months 1 and 3. Safety endpoints were treatment-emergent adverse events, daytime somnolence and next-morning residual effects. In participants with mild OSA, daridorexant improved WASO, LPS, sTST and IDSIQ total score over time. The average treatment effect size for all efficacy parameters was numerically greater with daridorexant 50 mg than with daridorexant 25 mg; daridorexant 25 mg was not always greater than placebo. No safety concerns were reported for daridorexant 50 or 25 mg. In participants with comorbid insomnia and untreated mild OSA, daridorexant 50 mg versus placebo improved all sleep parameters over time and was well tolerated. Daridorexant warrants further investigation in COMISA. Trial Registration: ClinicalTrials.gov identifier: NCT03545191.

Introduction Sleeping hot is a common barrier to good sleep. Characteristics of the sleep environment may impact temperature regulation and sleep. We tested the effectiveness of one brand of bed sheets that advertise cooling properties on sleep and vasomotor symptoms.Methods Participants were recruited through multiple channels that included potential customers of the intervention sheets and targeted online advertisements. Participants completed a baseline questionnaire, daily electronic diary for 6 weeks, and an end-of-study questionnaire. Assessments included the Pittsburgh Sleep Quality Index and Restorative Sleep Questionnaire. Daily diaries assessed sleep, mood, and perceived temperature during sleep. Within-person responses were compared before and after use of the intervention bed sheets.Results 64 participants provided 2,627 total days of data. The study sample was 89% female, mean age 48 (SD 12). Sixty-nine percent of participants reported improved sleep quality after implementing the intervention. Mean improvement on the Pittsburgh Sleep Quality Index was 1.9 (95% CI 1.3-2.6), from 8.0 (SD 3.0) to 6.1 (SD 2.5) at end-of-study. The proportion of participants reporting trouble sleeping due to feeling too hot was reduced from 82.5 to 39.7%. Reported sleep duration increased 26 min (95% CI 14-38 min), from 6.5 h (SD 1.0) to 7.0 h (SD 0.8). Participants also reported improvements in night sweats, restorative sleep, mood, and alertness.Conclusion Individuals reported improvements on several dimensions of sleep health, reductions in night sweats, and less sleep disruption due to sleeping too hot after implementing the intervention bed sheets. These findings warrant replication in a randomized, placebo-controlled design.

Large language models (LLMs) have shown promising capabilities in visually interpreting medical time-series data. However, their general-purpose design can limit domain-specific precision, and the proprietary nature of many models poses challenges for fine-tuning on specialized clinical datasets. Conversely, small specialized models (SSMs) offer strong performance on focused tasks but lack the broader reasoning needed for complex medical decision-making. To address these complementary limitations, we introduce ConMIL (Conformalized Multiple Instance Learning), a novel decision-support framework distinctively synergizes three key components: (1) a new Multiple Instance Learning (MIL) mechanism, QTrans-Pooling, designed for per-class interpretability in identifying clinically relevant physiological signal segments; (2) conformal prediction, integrated with MIL to generate calibrated, set-valued outputs with statistical reliability guarantees; and (3) a structured approach for these interpretable and uncertainty-quantified SSM outputs to enhance the visual inspection capabilities of LLMs. Our experiments on arrhythmia detection and sleep stage classification demonstrate that ConMIL can enhance the accuracy of LLMs such as ChatGPT4.0, Qwen2-VL-7B, and MiMo-VL-7B-RL. For example, ConMIL -supported Qwen2-VL-7B and MiMo-VL-7B-RL both achieve 94.92

Insomnia, poor sleep quality, and extremes of sleep duration are associated with COVID-19 infection. This study assessed whether these factors are related to post-acute sequelae of SARS-CoV-2 infection (PASC). Cross-sectional survey of a general population of 24,803 United States adults to determine the association of insomnia, poor sleep quality, and sleep duration with PASC. Three definitions of PASC were used based on post COVID-19 clinical features: COVID-19 Outbreak Public Evaluation Initiative (COPE) (≥ 3), National Institute for Health and Care Excellence (NICE) (≥ 1), and Researching COVID to Enhance Recovery (RECOVER) (scoring algorithm). Prevalence rates of PASC were 21.9

OBJECTIVE:Poor sleep and obstructive sleep apnea (OSA) are prevalent among transportation workers. METHODS:Forty-five transportation workers from worksites in the Northeast US completed surveys assessing (1) sleepiness, (2) OSA, and (3) OSA stage of change and then participated in focus groups or interviews. RESULTS:Participants were 93.2% male, and 90.1% were White non-Hispanic. Furthermore, 77.8% scored high risk for OSA, whereas 11.1% of those at risk reported an OSA diagnosis. Only 31.4% of high-risk participants reported having contemplated OSA evaluation or treatment. Qualitative themes pertained to difficulty unwinding, uncertain work hours, fears about and barriers to OSA treatment, and misinformation about OSA. CONCLUSIONS:Results reveal a high prevalence of OSA risk and a low rate of diagnosis and OSA readiness to change. We identify themes for future interventions to improve awareness about OSA among transportation workers.

Snooze alarm use is a common, but poorly understood human behavior. We explore the prevalence and characteristics of snooze alarm use in more than 3 million nights collected in a global sample of users of a sleep monitoring smartphone application. On the nights that participants logged a sleep session, more than half (55.6%) of the sessions ended with a snooze alarm. Of the sleep sessions ending with snooze alarm, snooze alarm was pressed on average 2.4 times (95% CI: 2.4-2.5) and the average duration of snooze alarm use was 10.8 minutes (95% CI: 10.7-10.9). We observed significantly more snooze alarm use in women as compared to men. Long sleep sessions (> 9 h) were more likely to end with snooze alarm use than recommended duration (7 to 9 h) or short (< 7 h) sleep sessions. Sleepers who went to bed earlier used snooze alarm less, while those who went to bed later than usual used the snooze alarm more. Future research is needed to understand the impact of snooze alarm use on daytime performance.

Rationale: Obstructive sleep apnea (OSA) is a common condition that is usually treated by continuous positive airway pressure (CPAP) therapy, but poor adherence is common and is associated with worse patient outcomes and experiences. Patient satisfaction is increasingly adopted as a quality indicator by healthcare systems. Objectives: We tested the hypothesis that peer-driven intervention effected through an interactive voice response (IVR) system leads to better patient satisfaction (primary outcome), care coordination, and CPAP adherence than active control. Methods: We performed a 6-month randomized, parallel-group, controlled trial with CPAP-naive patients recruited from four centers and CPAP-adherent patients who were trained to be mentors delivering support through an IVR system. Measurements and Main Results: In 263 patients, intention-to-treat analysis of global satisfaction for sleep-specific services was better in the intervention group (4.57 ± 0.71 Likert scale score; mean ± SD) than in the active-control group (4.10 ± 1.13; P < 0.001). CPAP adherence was greater in the intervention group (4.5 ± 0.2 h/night; 62.0% ± 3.0% of nights >4 h use) versus the active-control group (3.7 ± 0.2 h/night; 51.4% ± 3.0% of nights >4 h use; P = 0.014 and P = 0.023). When compared with the active-control group, the Patient Assessment of Chronic Illness Care rating was moderately increased by an adjusted difference of 0.33 ± 0.12 (P = 0.009), Consumer Assessment of Healthcare Provider and Systems rating was not different (adjusted difference, 0.46 ± 0.26; P = 0.076), and Client Perception of Coordination Questionnaire was mildly better in the intervention group (adjusted difference, 0.15 ± 0.07; P = 0.035). Conclusions: Patient satisfaction with care delivery, CPAP adherence, and care coordination were improved by peer-driven intervention through an IVR system. New payor policies compensating peer support may enable implementation of this approach. Clinical trial registered with www.clinicaltrials.gov (NCT02056002).

Cross-sectional studies suggest that obstructive sleep apnea (OSA) is a potential risk factor for incident COVID-19 infection, but longitudinal studies are lacking. Two surveys from a large general population cohort, the COVID-19 Outbreak Public Evaluation (COPE) Initiative, undertaken 147 ± 58 days apart were analyzed to determine whether the pre-existing OSA was a risk factor for the incidence of COVID-19. Of the 24,803 respondents completing the initial survey, 14,950 were negative for COVID-19; data from the follow-up survey were available for 2,325 respondents. Those with incident COVID-19 infection had a slightly higher prevalence of OSA (COVID-19+: 14.3 vs. COVID-19-: 11.5

Positional obstructive sleep apnea (POSA) is characterized by a significant increase in airway obstruction and breathing disturbances when a patient sleeps in the supine position compared to sleeping on their side. While mandibular advancement devices (MADs) are effective in managing obstructive sleep apnea (OSA), their efficacy in treating POSA remains uncertain. This study evaluates the effectiveness of MADs in improving clinical and polysomnographic outcomes for patients with POSA. Clinical notes and sleep studies (in-lab polysomnography or home sleep apnea test) were reviewed from patients who received a MAD for OSA treatment between 2019 and 2023. Patients who met the diagnostic criteria for POSA (supine AHI at least double the lateral AHI) were analyzed. Sleep parameters, including the Epworth Sleepiness Scale (ESS), Apnea-Hypopnea Index (AHI), and minimum oxygen saturation (SpO2), were compared between baseline and follow-up visits after MAD titration and optimization. Of 167 patients, 49.7% (n=83) had POSA. The POSA cohort had a median baseline ESS of 8 (range 0-20, n=69), AHI of 13.3 events/hour (range 5.7-62.2, n=67), supine AHI of 19.2 events/hour (range: 8-109.8, n=67), lateral AHI of 5.3 events/hour (range 0-44; n=67), minimum SpO2 of 82% (range 0.7-90, n=67), sleep efficiency of 73.4% (range 37.2-78.9, n=6), and arousal index of 13.2 events/hour (range 6.8-36, n=6). After MAD intervention, the cohort demonstrated a median ESS of 6 (range 0-20), AHI of 8.7 events/hour (range 0.5-88.9), supine AHI of 11.4 events/hour (range 0-85.9), lateral AHI of 4.1 events/hour (range 0-100.8), minimum SpO2 of 82% (range 64-91), sleep efficiency of 81.5% (range 65.4-95.8), and arousal index of 22.7 events/hour (range 2.8-41.9). Patients experienced significant reductions in median overall AHI (p< 0.001) and supine AHI (p< 0.001) and improvement in sleep efficiency (p< 0.001). Similar outcomes were observed in the non-POSA cohort (n=84, 50.3%), including significant reductions in median overall AHI (p< 0.05) and lateral AHI (p< 0.001). Mandibular advancement devices (MADs) effectively improved clinical and polysomnographic outcomes in patients with POSA. Similar benefits in AHI reduction were observed in non-POSA patients, supporting MADs as a viable treatment for both groups. American Academy of Dental Sleep Medicine

Study objectivesAdults are advised to spend approximately one third of their lives sleeping, yet there is a dearth of scientific research on mattresses, a common sleep surface. We develop and conduct initial validation of the Boston Mattress Satisfaction Questionnaire (BMSQ).MethodsThe BMSQ was designed with sleep scientists and clinicians (n = 5) and mattress industry professionals (n = 2) to assess two broad domains: mattress satisfaction (MS) and mattress characteristics (MC), including mattress type, size, age, and extent to which the mattress is pain-inducing. MS is measured with questions assessing mattress comfort, firmness, temperature, and overall satisfaction on 10-point scales from 1 (least) to 10 (most satisfied). We administered the BMSQ to a large, population-based sample of US adults. We also asked demographic questions. We conducted exploratory factor analysis, then dichotomized BMSQ responses (low: ≤ 5; high ≥6) for multivariable logistic regression to explore the demographic characteristics associated with mattress satisfaction.ResultsAmong participants (n = 1,055), 47.7% were male and 52.2% female. Average age was 49.4 (s.d. = 17.5 years). The 4 BSMQ items demonstrated high inter-item correlation (≥0.8) and Cronbach's α of 0.95. BMSQ-MS variables were inversely correlated with perceptions of the mattress being pain-inducing (p < 0.001) and mattress (p < 0.001). BMSQ variables had a weak correlation with mattress size (p < 0.01). Regression revealed higher mattress satisfaction among those ≥75 years old (v. 18–24 years); Hispanic and Asian individuals (compared to White, non-Hispanic); those earning >$20,000 annually (compared to <$10,000); and those reporting foam, hybrid, air-filled chamber mattresses (compared to all-spring).ConclusionsOur findings suggest that the BMSQ may be useful for assessing mattress satisfaction.

BackgroundHigh school students often experience insufficient sleep, affecting their health and academics. While school-based sleep education programs show promise, their impact is often short-lived.PurposeThe purpose of the study was to explore the potential of a collaboratively designed, teacher-delivered sleep education program and to assess teacher and student sleep knowledge and behaviors.MethodsWe developed a high school sleep education program with input from students to ensure relevance and impact, then evaluated its feasibility and acceptability among 33 high school teachers and 40 students, alongside assessments of their sleep knowledge and behaviors.ResultsThe final program was rated enjoyable (70%) and recommendable (95%) and teachers found it appealing (83%) and feasible (63%).DiscussionSignificant gaps in sleep knowledge among students highlight the need for sleep education programs.Translation to Health Education PracticeThis study supports school-based, teacher-led sleep education as a practical approach to addressing student sleep issues, with teachers viewing the program as feasible and expressing strong concern for student sleep, while recommending further training to enhance delivery and impact.

Rapid eye movement sleep-related bradyarrhythmia syndrome is a rare condition marked by abnormal sinus arrest or atrioventricular conduction disturbance blocks during rapid eye movement sleep unassociated with sleep-disordered breathing. We present a case of a young male without a cardiovascular history exhibiting pauses of up to 9.7 seconds during polysomnography. Initially referred for suspected obstructive sleep apnea due to nocturnal awakenings with shortness of breath, confusion, and dizziness. Polysomnography results were unremarkable apart from electrocardiogram findings revealing prolonged sinus pauses related to rapid eye movement sleep. Evaluation via extended 14-day patch monitor revealed an overall normal sinus rhythm with the lowest heart rate recorded at 14 beats per minute and 412 pauses exceeding 2 seconds, with the longest pause lasting 12.5 seconds during nocturnal hours. A permanent pacemaker was considered, but after shared decision making with the patient, the decision was to continue monitoring without any intervention. Perez K, Shah M, Sridharan A, et al. REM sleep-related bradyarrhythmia syndrome. J Clin Sleep Med. 2025;21(2):435–438.

The goal of this study was to evaluate the association between a polygenic risk score (PRS) for QT prolongation (QTc-PRS), corrected QT intervals (QTc) and sudden cardiac death (SCD) in participants enrolled in the UK Biobank with and without sleep-disordered breathing (SDB). The QTc-PRS was calculated using allele copy number and previously reported effect estimates for each single nuclear polymorphism. Competing-risk regression models adjusting for age, sex, body mass index, QT prolonging medication, race, and comorbid cardiovascular conditions were used for SCD analyses. A total of 500,584 participants were evaluated (56.5 ± 8 years, 54