Identification of major depression patients using machine learning models based on heart rate variability during sleep stages for pre-hospital screening.

With the COVID-19 pandemic causing challenges in hospital admissions globally, the role of home health monitoring in aiding the diagnosis of mental health disorders has become increasingly important. This paper proposes an interpretable machine learning solution to optimise initial screening for major depressive disorder (MDD) in both male and female patients. The data is from the Stanford Technical Analysis and Sleep Genome Study (STAGES). We analyzed 5-min short-term electrocardiogram (ECG) signals during nighttime sleep stages of 40 MDD patients and 40 healthy controls, with a 1:1 gender ratio. After preprocessing, we calculated the time-frequency parameters of heart rate variability (HRV) based on the ECG signals and used common machine learning algorithms for classification, along with feature importance analysis for global decision analysis. Ultimately, the Bayesian optimised extremely randomized trees classifier (BO-ERTC) showed the best performance on this dataset (accuracy 86.32%, specificity 86.49%, sensitivity 85.85%, F1-score 0.86). By using feature importance analysis on the cases confirmed by BO-ERTC, we found that gender is one of the most important factors affecting the prediction of the model, which should not be overlooked in our assisted diagnosis. This method can be embedded in portable ECG monitoring systems and is consistent with the literature results.

Feasibility and parental perception of home sleep studies during COVID-19: a tertiary sleep centre experience.

OBJECTIVE: Rapid implementation of home sleep studies during the first UK COVID-19 'lockdown'-completion rates, family feedback and factors that predict success. DESIGN: We included all patients who had a sleep study conducted at home instead of as inpatient from 30 March 2020 to 30 June 2020. Studies with less than 4 hours of data for analysis were defined 'unsuccessful'. RESULTS: 137 patients were included. 96 underwent home respiratory polygraphy (HRP), median age 5.5 years. 41 had oxycapnography (O2/CO2), median age 5 years. 56% HRP and 83% O2/CO2 were successful. A diagnosis of autism predicted a lower success rate (29%) as did age under 5 years. CONCLUSION: Switching studies rapidly from an inpatient to a home environment is possible, but there are several challenges that include a higher failure rate in younger children and those with neurodevelopmental disorders.

Diagnostic accuracy and feasibility of portable sleep monitoring in patients with obstructive sleep apnea: Re-exploring the utility in the current COVID-19 pandemic.

Portable sleep monitoring (PSM) is a promising alternative diagnostic tool for Obstructive Sleep Apnea (OSA) especially in high burden resource limited settings. We aimed to determine the diagnostic accuracy and feasibility of PSM device-based studies in patients presenting for evaluation of OSA at a tertiary care hospital in North-India. PSM studies (using a Type-III PSM device) were compared for technical reliability and diagnostic accuracy with the standard laboratory-based Type-I polysomnography (PSG). Patients were also interviewed about their experience on undergoing an unsupervised PSM studies. Fifty patients (68% males) were enrolled in the study, of which only 30% patients expressed their concerns about undergoing unsupervised PSM studies which included safety issues, ease of use, diagnostic accuracy, etc. Technical acceptability criteria were easily met by the PSM studies with signal loss in 12% studies (complete data loss and inaccessible data in 6% studies), warranting repetition sleep studies in four patients. The overall sensitivity of PSM device (AHI ≥5) was 93.5% (area under curve; AUC: 0.87). The diagnostic accuracy was 68.5%, 80%, and 91.4% for mild, moderate, and severe cases of OSA, respectively. An overall strong correlation was observed between PSM-AHI (apnoea-hypopnoea index) and PSG (r>0.85, p≤0.001), especially in severe OSA. The observed sensitivity was >90% for AHI>20 (clinically significant OSA), with high specificity of 91% for severe OSA (AUC: 0.94, 0.97 for AHI>20, AHI>30 respectively). The overall Bland-Altman concordance analysis also demonstrated only a small dispersion for PSM studies with a Cronbach's coefficient of 0.95. Therefore, there is good diagnostic accuracy as well as feasibility of home-based portable sleep studies in Indian patients. It can be promoted for widespread use in high burden countries like India for diagnosing and managing appropriately selected stable patients with high clinical probability of OSA, especially during the ongoing crises of COVID-19 pandemic.

Recent Progress in Long-Term Sleep Monitoring Technology.

Sleep is an essential physiological activity, accounting for about one-third of our lives, which significantly impacts our memory, mood, health, and children's growth. Especially after the COVID-19 epidemic, sleep health issues have attracted more attention. In recent years, with the development of wearable electronic devices, there have been more and more studies, products, or solutions related to sleep monitoring. Many mature technologies, such as polysomnography, have been applied to clinical practice. However, it is urgent to develop wearable or non-contacting electronic devices suitable for household continuous sleep monitoring. This paper first introduces the basic knowledge of sleep and the significance of sleep monitoring. Then, according to the types of physiological signals monitored, this paper describes the research progress of bioelectrical signals, biomechanical signals, and biochemical signals used for sleep monitoring. However, it is not ideal to monitor the sleep quality for the whole night based on only one signal. Therefore, this paper reviews the research on multi-signal monitoring and introduces systematic sleep monitoring schemes. Finally, a conclusion and discussion of sleep monitoring are presented to propose potential future directions and prospects for sleep monitoring.

Sleep testing during the pandemic.

BACKGROUND: The COVID-19 pandemic disrupted the U.S. healthcare system, reducing the capacity available for unrelated conditions, such as sleep disordered breathing, and increasing concerns about the safety of in-lab testing. This study characterizes how the pandemic impacted the assessment of sleep disordered breathing and use of associated services. METHODS: Sleep testing claims occurring between January 2019 and June 2021 were extracted from the database of a national healthcare organization. Utilization was trended. Logistic regressions were run to assess the association between quarter of initial testing, whether testing was followed by treatment, and whether testing was followed by a clinical visit with a diagnosis related to sleep apnea, after controlling for patient-related factors. A Cox proportional hazards model assessed factors influencing time to treatment. Finally, a logistic regression assessed factors influencing the finality of home-based testing. RESULTS: In Q2 2021, home-based testing utilization was 134% of its initial level, while in-lab and split night testing were both at 61% of initial levels. Patients receiving initial home-based testing did not significantly differ in their likelihood of treatment, but were significantly less likely to have a clinical visit for sleep apnea (P < 0.01). Patients initially tested in 2021 were treated significantly more quickly than those initially tested in Q1 2019. Home-based testing occurring in Q4 2019 or later was significantly more likely to be definitive than home-based testing occurring Q1 2019. CONCLUSIONS: Home-based sleep testing increased significantly and durably in 2020, and was associated with faster time to treatment than initial in-lab testing.

Postal Delivery of Sleep Monitoring Devices: Research Implications.

The purpose of this article is to describe the protocol development, feasibility, and lessons learned in the postal mail delivery of sleep monitoring devices to study participants. The original study protocol included four in-person visits with distribution of a sleep monitoring device (Actiwatch) and return of the Actiwatch via the postal service in a self-addressed, stamped envelope. The COVID-19 pandemic limited in-person research contact thus requiring a remote study protocol for application and return of the Actiwatches using postal delivery. While there were postal delivery and return challenges, the overall return rate of 94.4% confirmed remote protocol feasibility. Key lessons learned were: consistent and frequent communication via telephone calls and/or text; confirming required postage; and use of package tracking labels. All these strategies contributed to successful postal delivery/return and concomitantly decreased the potential loss of data and valuable research equipment.

Unattended home sleep studies for the diagnosis of obstructive sleep apnea in a population of French children.

BACKGROUND: Ambulatory exams were preferred in children during the COVID-19 pandemic. Polysomnography (PSG), the gold standard for obstructive sleep apnea (OSA) diagnosis, requires several leads and sensors to be attached to the child's body. Children are more comfortable with respiratory polygraphic (RP) recording, which needs fewer sensors. OBJECTIVE: To compare respiratory parameters obtained by home RP with those obtained by home PSG with the device installed at the child's home by a trained sleep nurse from a national health care provider. METHODS: Data from home PSGs performed in children aged 2-19 years were retrospectively included. The obstructive apnea-hypopnea index (OAHI) was computed in PSG and then in RP after removing the sleep signals. The two indexes were compared using non-parametric paired Wilcoxon rank test, Bland-Altman analysis and sensitivity-specificity analysis. RESULTS: 44 PSGs of 44 children were included with only 34 (77%) PSGs interpretable. Median (min-max) OAHI was significantly underestimated in RP than in PSG (2.2 (0-25) vs 4.0 (0.4-28), p < 0.0001), confirmed also by the Bland-Altman diagram, the magnitude of the difference being mean ± standard deviation -1.7 ± 1.7. The sensitivity and specificity of OAHI in RP to identify an OAHI ≥2/h in PSG was 0.91 for both. CONCLUSION: Unattended ambulatory RP performed at child's house and installed under carefully controlled conditions is a useful exam for diagnosing OSA in children with or without comorbidities. However, RP must be installed in a supervised environment and interpreted with caution as it tends to underestimate OSA severity.

Effect of Seat Angle when Sleeping in a Car on Quality of Sleep and Its Impact on Calculation Performance the Following Day.

The number of occasions to stay in a car overnight is increasing during disasters; however, the effects on sleep and the impact on daytime functioning are not well understood. We investigated the effect of seat angle when sleeping in a car and its impact on calculation performance the following day. Fifteen healthy males participated in three trials (sleeping in a car with the front seat angled at 45° and 60° in a laboratory and sleeping at home); sleep and calculation performance the following day were compared. Increased wake after sleep onset and decreased slow-wave sleep were observed in the 60° trial, that is, near-vertical, compared with the others. Subjective sleep quality and calculation performance in the 45° and 60° trials were poorer than those in the home trial. The effect of seat angle on sleep was confirmed objectively, but not subjectively, suggesting that a large seat angle might cause sleep impairment.

Obstructive Sleep Apnea and Cardiovascular Diseases: Sad Realities and Untold Truths regarding Care of Patients in 2022.

Obstructive sleep apnea (OSA) is one of the most common and serious sleep-related breathing disorders with a high prevalence among patients with cardiovascular (CV) diseases. Despite its widespread presence, OSA remains severely undiagnosed and untreated. CV mortality and morbidity are significantly increased in the presence of OSA as it is associated with an increased risk of resistant hypertension, heart failure, arrhythmias, and coronary artery disease. Evaluation and treatment of OSA should focus on recognizing patients at risk of developing OSA. The use of screening questionnaires should be routine, but a formal polysomnography sleep study is fundamental in establishing and classifying OSA. Recognition of OSA patients will allow for the institution of appropriate therapy that should alleviate OSA-related symptoms with the intent of decreasing adverse CV risk. In this review, we focus on the impact OSA has on CV disease and evaluate contemporary OSA treatments. Our goal is to heighten awareness among CV practitioners.

Studying the Effect of Long COVID-19 Infection on Sleep Quality Using Wearable Health Devices: Observational Study.

BACKGROUND: Patients with COVID-19 have increased sleep disturbances and decreased sleep quality during and after the infection. The current published literature focuses mainly on qualitative analyses based on surveys and subjective measurements rather than quantitative data. OBJECTIVE: In this paper, we assessed the long-term effects of COVID-19 through sleep patterns from continuous signals collected via wearable wristbands. METHODS: Patients with a history of COVID-19 were compared to a control arm of individuals who never had COVID-19. Baseline demographics were collected for each subject. Linear correlations among the mean duration of each sleep phase and the mean daily biometrics were performed. The average duration for each subject's total sleep time and sleep phases per night was calculated and compared between the 2 groups. RESULTS: This study includes 122 patients with COVID-19 and 588 controls (N=710). Total sleep time was positively correlated with respiratory rate (RR) and oxygen saturation (SpO2). Increased awake sleep phase was correlated with increased heart rate, decreased RR, heart rate variability (HRV), and SpO2. Increased light sleep time was correlated with increased RR and SpO2 in the group with COVID-19. Deep sleep duration was correlated with decreased heart rate as well as increased RR and SpO2. When comparing different sleep phases, patients with long COVID-19 had decreased light sleep (244, SD 67 vs 258, SD 67; P=.003) and decreased deep sleep time (123, SD 66 vs 128, SD 58; P=.02). CONCLUSIONS: Regardless of the demographic background and symptom levels, patients with a history of COVID-19 infection demonstrated altered sleep architecture when compared to matched controls. The sleep of patients with COVID-19 was characterized by decreased total sleep and deep sleep.

Comparison of a home sleep test with in-laboratory polysomnography in the diagnosis of obstructive sleep apnea syndrome.

BACKGROUND: In-laboratory, polysomnography (PSG) is the gold standard for diagnosing obstructive sleep apnea syndrome (OSAS). However, the long waiting list and sleeping at a hospital make patients hesitate to undergo the examination, thereby delaying diagnosis. During coronavirus disease 2019 (COVID-19) pandemic, sleep labs are almost closed, and the delay is worsening. The home sleep test (HST) enables subjects to be tested at home, a familiar and comfortable environment, without a long waiting list. This study assessed the accuracy of a type III HST in diagnosing OSAS in the Taiwanese population and identified factors affecting the diagnostic accuracy. METHODS: This retrospective study included 67 patients with clinically suspected OSAS. All patients were allocated to receive both PSG and the HST. The apnea-hypopnea index (AHI) measured through PSG was used as the standard. The sensitivity, specificity, and accuracy of the HST in diagnosing and evaluating the severity of OSAS were analyzed. RESULTS: Among the 67 patients, no significant difference was noted in the average AHI values obtained using PSG and the HST ( p = 0.103). The AHI obtained from HST was significantly correlated with that obtained from PSG, with the correlation coefficient being 0.779 ( p < 0.001). The sensitivity, specificity, and accuracy of the HST in diagnosing OSAS were 94.9%, 62.5%, and 91.0%, respectively, and 80.0%, 74.1%, and 77.6% in diagnosing moderate to severe OSAS. Furthermore, the difference in AHIs measured using the two tests were positively correlated with the severity of sleep apnea. CONCLUSION: The HST used in preliminary screening of patients with suspected OSAS achieved an accuracy of >90%. For patients with moderate to severe OSAS, the accuracy was below 80%. Therefore, for patients who receive an OSAS diagnosis through the HST, arrangement of PSG is recommended for determining the severity of the OSAS and giving proper treatment.

Did COVID-19 impact Positive Airway Pressure adherence in 2020? A cross-sectional study of 8477 patients with sleep apnea.

BACKGROUND: Whether the COVID-19 pandemic impacts Positive Airway Pressure (PAP) adherence over the long-term is unknown and only preliminary short-term data have been reported. METHODS: With the aim of describing the impact of the first and second waves of COVID-19 on PAP adherence during 2020 in France, we designed a cross-sectional study of Sleep-Apnea (SA)-patients under PAP telemonitoring. To examine PAP adherence in adult SA patients, we assessed de-identified data from a non-profit healthcare provider database during the period January 1, 2019 to December 31, 2020. Included patients met the following criteria: (i) PAP-treated for at least 4 months before January 1, 2019 and with continuous PAP during both 2019 and 2020; (ii) ≥ 360 daily PAP telemonitored data per year. For PAP adherence, data were collected using the PAP-software. RESULTS: 8477/10482 patients were finally included in the analysis [72.4% male, median age 70 years (IQ25-75: 61-77], 25.6% < 62 years old, initial Apnea-Hypopnea Index (AHI) of 41 (31-59)/h. Median PAP adherence was 7.21 (6.12-8.10) h/day in 2020 versus 7.12 (6.05-8.02) h/day in 2019, p < 0.001. The median difference in PAP adherence between the first 2020 lockdown and the corresponding 2019 weeks was 9.75 (CI95% 8.75-10.75) min/day, p < 0.001. The median difference in PAP adherence between the second 2020 lockdown and the corresponding 2019 weeks was 5.00 (CI95% 4.00-6.00) min/day, p < 0.001. If we consider the minimal clinically important difference of 30 min for PAP adherence, 30.4% and 26% of the patients increased their PAP adherence by at least 30 min during the first and second lockdowns respectively; 17.6% and 19.3% of the patients lowered their PAP adherence by at least 30 min in the first and second lockdowns, respectively. CONCLUSION: During the first and second lockdowns, the COVID-19 pandemic had a clinically irrelevant effect on PAP adherence for the study population. Future studies are needed to describe COVID-19 pandemic impact on PAP adherence not only for long-term PAP-treated SA patients but also for incident cases. Trial registration The COVADENE study was registered on March 1st, 2021 on ClinicalTrials.gov (Identifier: NCT04775966).

Twenty-year follow-up of children with obstructive sleep apnea.

STUDY OBJECTIVES: Obstructive sleep apnea (OSA) in children is associated with acute metabolic, cardiovascular, and neurocognitive abnormalities. The long-term outcomes of childhood OSA into adulthood have not been established. We performed a 20-year follow-up of patients with polysomnography-documented OSA in childhood compared to a healthy control group to evaluate the long-term anthropometric, sleep, cognitive, and cardiovascular outcomes. METHODS: Children diagnosed with severe OSA between ages 1 and 17 years (mean, 4.87 ± 2.77) were prospectively contacted by telephone as young adults after approximately 20 years. Data collected included reported anthropometric information, educational level, health history, and Berlin questionnaire scores. RESULTS: Young adults with confirmed severe OSA in childhood had significantly higher adulthood body mass index (P = .038), fewer academic degrees (P < .001), and more snoring (P = .045) compared to control patients. The apnea-hypopnea index during childhood trended toward predicting cardiovascular outcomes and the results of the Berlin questionnaire in adulthood. CONCLUSIONS: Adults with a history of severe childhood OSA have a high risk of snoring, elevated body mass index, and lower academic achievement in adulthood. Thus, children with severe OSA may be at increased risk of chronic diseases later in life. The intervening coronavirus disease 2019 (COVID-19) pandemic has introduced considerable additional neurobehavioral morbidity complicating the identification of the full long-term consequences of childhood OSA. CITATION: Nosetti L, Zaffanello M, Katz ES, et al. Twenty-year follow-up of children with obstructive sleep apnea. J Clin Sleep Med. 2022;18(6):1573-1581.

A clinical trial to evaluate the dayzz smartphone app on employee sleep, health, and productivity at a large US employer.

Sleep deficiency is a hidden cost of our 24-7 society, with 70% of adults in the US admitting that they routinely obtain insufficient sleep. Further, it is estimated that 50-70 million adults in the US have a sleep disorder. Undiagnosed and untreated sleep disorders are associated with diminished health for the individual and increased costs for the employer. Research has shown that adverse impacts on employees and employers can be mitigated through sleep health education and sleep disorder screening and treatment programs. Smartphone applications (app) are increasingly commonplace and represent promising, scalable modalities for such programs. The dayzz app is a personalized sleep training program that incorporates assessment of sleep disorders and offers a personalized comprehensive sleep improvement solution. Using a sample of day workers affiliated with a large institution of higher education, we will conduct a single-site, parallel-group, randomized, waitlist control trial. Participants will be randomly assigned to either use the dayzz app throughout the study or receive the dayzz app at the end of the study. We will collect data on feasibility and acceptability of the dayzz app; employee sleep, including sleep behavioral changes, sleep duration, regularity, and quality; employee presenteeism, absenteeism, and performance; employee mood; adverse and safety outcomes; and healthcare utilization on a monthly basis throughout the study, as well as collect more granular daily data from the employee during pre-specified intervals. Our results will illuminate whether a personalized smartphone app is a viable approach for improving employee sleep, health, and productivity. Trial registration: ClinicalTrials.gov Identifier: NCT04224285.

Current and future strategies for diagnostic and management of obstructive sleep apnea.

INTRODUCTION: Obstructive sleep apnea (OSA) is a common sleep disorder with multiple comorbidities including hypertension, diabetes, and cardiovascular disorders. Detected based on an overnight sleep study is called polysomnography (PSG); OSA still remains undiagnosed in majority of the population mainly attributed to lack of awareness. To overcome the limitations posed by PSG such as patient discomfort and overnight hospitalization, newer technologies are being explored. In addition, challenges associated with current management of OSA using continuous positive airway pressure (CPAP), etc. presents several pitfalls. AREAS COVERED: Conventional and modern detection/management techniques including PSG, CPAP, smart wearable/pillows, bio-motion sensors, etc., have both pros and cons. To fulfill the limitations in OSA diagnostics, there is an imperative need for new technology for screening of symptomatic and more importantly asymptomatic OSA patients to reduce the risk of several associated life-threatening comorbidities. In this line, molecular marker-based diagnostics have shown great promises. EXPERT OPINION: A detailed overview is presented on the OSA management and diagnostic approaches and recent advances in the molecular screening methods. The potentials of biomarker-based detection and its limitations are also portrayed and a comparison between the standard, current modern approaches, and promising futuristic technologies for OSA diagnostics and management is set forth.ABBREVIATIONS AHI: Apnea hypopnea index; AI: artificial intelligence; CAM: Cell adhesion molecules; CPAP: Continuous Positive Airway Pressure; COVID-19: Coronavirus Disease 2019; CVD: Cardiovascular disease; ELISA: Enzyme linked immunosorbent assay; HSAT: Home sleep apnea testing; IR-UWB: Impulse radio-ultra wideband; MMA: maxillomandibular advancement; PSG: Polysomnography; OSA: Obstructive sleep apnea; SOD: Superoxide dismutase; QD: Quantum dot.

Positive airway pressure therapy adherence for obstructive sleep apnea during the COVID-19 pandemic.

PURPOSE: Positive airway pressure (PAP) adherence is a significant issue among patients with obstructive sleep apnea (OSA). However, the data are limited regarding PAP adherence during the current COVID-19 pandemic. METHODS: A cross-sectional study was conducted between February and October 2020 at the Excellence Center for Sleep Disorders, King Chulalongkorn Memorial Hospital, Bangkok, Thailand. Patients with ongoing PAP-treated OSA were recruited. Data on PAP adherence before and during the COVID-19 pandemic were collected. Furthermore, pre-test and post-test questionnaires on knowledge on COVID-19, OSA, and PAP before and after tele-education were also evaluated. RESULTS: Of a total 156 patients, the majority had severe OSA (72%). By self-report, there was no significant difference in PAP usage in hours per day before compared to during the pandemic (p = 0.45), though in a subgroup with highest educational attainment (degree higher than bachelor's), PAP usage did increase during the pandemic (mean difference 0.23 ± 0.10; 95% CI 0.02-0.40, p = 0.03). However, objective PAP usage data demonstrated a trend towards increased usage comparing before and during the pandemic (4.64 ± 1.49 vs 5.12 ± 1.41; mean difference 0.48 ± 1.33; 95% CI 0.13-10.90, p = 0.12). Basic knowledge was significantly improved after tele-education (p < 0.001). CONCLUSION: By objective data, there was a trend towards increased PAP usage during the COVID-19 pandemic for the entire group. In a subgroup of patients with highest educational attainment, PAP adherence increased by self-report. Tele-education appeared to improve knowledge on COVID-19, OSA, and PAP usage.