1208 Sleep Stage Prediction And Sleep Disordered Breathing Detection Using Raw Actigraphy And Photoplethysmography From Wearable Consumer Device

Abstract Introduction Wearable, multisensory consumer devices that estimate sleep are prevalent and hold great potential. Most validated actigraphic prediction studies of sleep stages (SS) have only used low resolution (30 sec) data and the Cole-Kripke algorithm. Other algorithms are often proprietary and not accessible or validated. We present an automatic, data-driven deep learning algorithm that process raw actigraphy (ACC) and photoplethysmography (PPG) using a low-cost consumer device at high (25Hz) and low resolution to predict SS and to detect sleep disordered breathing (SDB) events. Methods Our automatic, data-driven algorithm is a deep neural network trained and evaluated to predict SS and SDB events on 236 recordings of ACC data from a wrist-worn accelerometer and PPG data from the overlapping PSG. The network was tested on raw ACC and PPG data, which was collected at 25 Hz using the HUAMI Arc2 wristband from 39 participants that underwent a nocturnal polysomnography (PSG). Results Overall accuracy (Acc), recall (Re), specificity (Sp), and kappa (κ) per subject on the test dataset the prediction of wake, NREM, REM was Acc=76.6%, Re=72.4%, Sp=78.0%, kappa=0.42. On average, we found a 7 % higher performance using the raw sensor data as input instead of processed, low resolution inputs. PPG was especially useful for REM detection. The network assigned 55.6% of patients to the correct SDB severity group when using an apnea-hypopnea index above 15. Conclusion Current results show that SS prediction is significantly improved when using the raw sensor data; it indicates that the system holds promise as a potential pervasive monitoring device for patients with chronic sleep disorders. In contrast the system did not show potential as a sleep apnea screening tool. Additional studies are ongoing to examine the effects of pathology such as sleep apnea and periodic leg movement on SS prediction. Support Technical University of Denmark; University of Copenhagen, Copenhagen Center for Health Technology, Klarman Family Foundation.

Download Full-text

0968 Sleep-disordered Breathing In Schaaf-yang Syndrome

SLEEP ◽

10.1093/sleep/zsaa056.964 ◽

2020 ◽

Vol 43 (Supplement_1) ◽

pp. A367-A368

Author(s):

W Powell ◽

M Rech ◽

C Schaaf ◽

J Wrede

Keyword(s):

Sleep Apnea ◽

Sleep Disordered Breathing ◽

Central Sleep Apnea ◽

Sleep Time ◽

Sleep Stages ◽

Apnea Hypopnea Index ◽

Sleep Study ◽

Central Index ◽

Obstructive Sleep ◽

Disordered Breathing

Abstract Introduction Schaaf-Yang Syndrome (SYS) is a genetic disorder caused by truncating variants in the MAGEL2 gene located in the maternally imprinted, paternally expressed Prader-Willi syndrome (PWS) region at 15q11-13. The SYS phenotype shares features with PWS, a disorder with known high incidence of central and obstructive sleep apnea (OSA). However the spectrum of sleep-disordered breathing in SYS has not been described. Methods We performed a retrospective analysis of polysomnograms from 22 of the known 115 patients with molecular diagnosis of SYS. Sleep characteristics including total sleep time, latency, efficiency, % sleep stages, apnea-hypopnea index (AHI), obstructive index, central index, and oxygenation were analyzed for the whole group and by truncation location (c.1996dupC variants [n=11] or other locations [n=11]). Only the initial diagnostic study or initial diagnostic portion of a split-night study was used in analysis (analytic n=21). Results We collected 33 sleep study reports from 22 patients, ages 2 months - 18.5 years. Mean analyzed sleep time was 357 minutes (129-589 min) with mean sleep efficiency of 71.45% (45-94%) and sleep latency of 24.8 minutes (0-146 min). The mean apnea-hypopnea index (AHI) was 19.1/hr (0.9 -49/hr) with mean obstructive AHI of 16.3 (0.6-49/hr). Mean central index was 2.8/hr (0-14/hr). 18/21 (86%) were diagnosed with OSA, and 13/21 (62%) with moderate or severe OSA (oAHI >5/hr). Central sleep apnea was diagnosed in 2/21 (9.5%). 15 studies reported periodic limb movement index (PLMI) with mean of 7.8 (0-67/hr) and 4/15 (26%) with PLMI >5. Comparison of genotype groups did not reveal any difference in presence of OSA or severity of OSA. Conclusion OSA is frequently identified on polysomnography in patients with SYS. Central sleep apnea is less common, which is in contrast to PWS. The majority of patients with OSA had moderate or severe OSA, and 47% had severe OSA. Support N/A

Download Full-text

Postoperative Changes in Sleep-disordered Breathing and Sleep Architecture in Patients with Obstructive Sleep Apnea

Anesthesiology ◽

10.1097/aln.0000000000000040 ◽

2014 ◽

Vol 120 (2) ◽

pp. 287-298 ◽

Cited By ~ 75

Author(s):

Frances Chung ◽

Pu Liao ◽

Balaji Yegneswaran ◽

Colin M. Shapiro ◽

Weimin Kang

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Sleep Disordered Breathing ◽

Slow Wave Sleep ◽

Sleep Architecture ◽

Secondary Outcome ◽

Apnea Hypopnea Index ◽

Postoperative Changes ◽

Obstructive Sleep ◽

Disordered Breathing

Abstract Background: Anesthetics, analgesics, and surgery may profoundly affect sleep architecture and aggravate sleep-related breathing disturbances. The authors hypothesized that patients with preoperative polysomnographic evidence of obstructive sleep apnea (OSA) would experience greater changes in these parameters than patients without OSA. Methods: After obtaining approvals from the Institutional Review Boards, consented patients underwent portable polysomnography preoperatively and on postoperative nights (N) 1, 3, 5, and 7 at home or in hospital. The primary and secondary outcome measurements were polysomnographic parameters of sleep-disordered breathing and sleep architecture. Results: Of the 58 patients completed the study, 38 patients had OSA (apnea hypopnea index [AHI] >5) with median preoperative AHI of 18 events per hour and 20 non-OSA patients had median preoperative AHI of 2. AHI was increased after surgery in both OSA and non-OSA patients (P < 0.05), with peak increase on postoperative N3 (OSA vs. non-OSA, 29 [14, 57] vs. 8 [2, 18], median [25th, 75th percentile], P < 0.05). Hypopnea index accounted for 72% of the postoperative increase in AHI. The central apnea index was low (median = 0) but was significantly increased on postoperative N1 in only non-OSA patients. Sleep efficiency, rapid eye movement sleep, and slow-wave sleep were decreased on N1 in both groups, with gradual recovery. Conclusions: Postoperatively, sleep architecture was disturbed and AHI was increased in both OSA and non-OSA patients. Although the disturbances in sleep architecture were greatest on postoperative N1, breathing disturbances during sleep were greatest on postoperative N3.

Download Full-text

P.069 Respiratory dysfunction and sleep disordered breathing in children with Myasthenia Gravis

Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques ◽

10.1017/cjn.2018.171 ◽

2018 ◽

Vol 45 (s2) ◽

pp. S34-S34

Author(s):

HF Qashqari ◽

I Narang ◽

H Katzberg ◽

K Vezina ◽

A Khayat ◽

...

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Myasthenia Gravis ◽

Sleep Disordered Breathing ◽

Pediatric Population ◽

Respiratory Muscles ◽

Apnea Hypopnea Index ◽

Respiratory Dysfunction ◽

Obstructive Sleep ◽

Disordered Breathing

Background: Myasthenia Gravis ( MG) is an autoimmune disease that affects the neuromuscular junction. It typically presents with fluctuating muscle weakness which can affect respiratory muscles. Data about the prevalence of sleep disordered breathing in children with MG and the benefits of non-invasive ventilation outside the setting of MG crisis has not been studied so far. Methods: Eleven children between 3 and 18 years old with confirmed MG were recruited from the The Hospital for Sick Children Neuromuscular clinic in a prospective observational study. Informed consent was obtained and patients underwent PFTs, MIP/MEP, SNIP, FVC and standard polysomnography testing’s. Results: In our study, we found that 2/11 children had abnormal Apnea Hypopnea index (AHI) and were diagnosed with obstructive sleep apnea (OSA). One of them has juvenile ocular MG with mild to moderate OSA and the second child has congenital MG with mild OSA. CPAP therapy was initiated for both patients. Conclusions: In our cohort, obstructive sleep apnea rate was significantly higher in children with MG than the known prevalence in general pediatric population ( 18% vs 2-3% ). Early diagnosis and management of OSA can have great impact on children’s health and quality of life. A larger study is needed to validate our findings.

Download Full-text

Robust, ECG-based detection of Sleep-disordered breathing in large population-based cohorts

SLEEP ◽

10.1093/sleep/zsz276 ◽

2019 ◽

Vol 43 (5) ◽

Cited By ~ 1

Author(s):

Mads Olsen ◽

Emmanuel Mignot ◽

Poul Jorgen Jennum ◽

Helge Bjarup Dissing Sorensen

Keyword(s):

Sleep Disordered Breathing ◽

Large Population ◽

Population Based ◽

Small Sample ◽

Health Study ◽

Apnea Hypopnea Index ◽

Automatic Data ◽

Highly Correlated ◽

Ecg Database ◽

Disordered Breathing

Abstract Study Objectives Up to 5% of adults in Western countries have undiagnosed sleep-disordered breathing (SDB). Studies have shown that electrocardiogram (ECG)-based algorithms can identify SDB and may provide alternative screening. Most studies, however, have limited generalizability as they have been conducted using the apnea-ECG database, a small sample database that lacks complex SDB cases. Methods Here, we developed a fully automatic, data-driven algorithm that classifies apnea and hypopnea events based on the ECG using almost 10 000 polysomnographic sleep recordings from two large population-based samples, the Sleep Heart Health Study (SHHS) and the Multi-Ethnic Study of Atherosclerosis (MESA), which contain subjects with a broad range of sleep and cardiovascular diseases (CVDs) to ensure heterogeneity. Results Performances on average were sensitivity(Se)=68.7%, precision (Pr)=69.1%, score (F1)=66.6% per subject, and accuracy of correctly classifying apnea–hypopnea index (AHI) severity score was Acc=84.9%. Target AHI and predicted AHI were highly correlated (R2 = 0.828) across subjects, indicating validity in predicting SDB severity. Our algorithm proved to be statistically robust between databases, between different periodic leg movement index (PLMI) severity groups, and for subjects with previous CVD incidents. Further, our algorithm achieved the state-of-the-art performance of Se=87.8%, Sp=91.1%, Acc=89.9% using independent comparisons and Se=90.7%, Sp=95.7%, Acc=93.8% using a transfer learning comparison on the apnea-ECG database. Conclusions Our robust and automatic algorithm constitutes a minimally intrusive and inexpensive screening system for the detection of SDB events using the ECG to alleviate the current problems and costs associated with diagnosing SDB cases and to provide a system capable of identifying undiagnosed SDB cases.

Download Full-text

Prevalence of sleep-disordered breathing after stroke and TIA

Neurology ◽

10.1212/wnl.0000000000006904 ◽

2019 ◽

Vol 92 (7) ◽

pp. e648-e654 ◽

Cited By ~ 30

Author(s):

Andrea Seiler ◽

Millene Camilo ◽

Lyudmila Korostovtseva ◽

Alan G. Haynes ◽

Anne-Kathrin Brill ◽

...

Keyword(s):

Sleep Apnea ◽

Confidence Interval ◽

Sleep Disordered Breathing ◽

Meta Analysis ◽

Chronic Phase ◽

Cochrane Library ◽

Apnea Hypopnea Index ◽

Apnea Test ◽

Registration Number ◽

Disordered Breathing

ObjectiveTo perform a systematic review and meta-analysis on the prevalence of sleep-disordered breathing (SDB) after stroke.MethodsWe searched PubMed, Embase (Ovid), the Cochrane Library, and CINAHL (from their commencements to April 7, 2017) for clinical studies reporting prevalence and/or severity of SDB after stroke or TIA. Only sleep apnea tests performed with full polysomnography and diagnostic devices of the American Academy of Sleep Medicine categories I–IV were included. We conducted random-effects meta-analysis. PROSPERO registration number: CRD42017072339.ResultsThe initial search identified 5,211 publications. Eighty-nine studies (including 7,096 patients) met inclusion criteria. Fifty-four studies were performed in the acute phase after stroke (after less than 1 month), 23 studies in the subacute phase (after 1–3 months), and 12 studies in the chronic phase (after more than 3 months). Mean apnea-hypopnea index was 26.0/h (SD 21.7–31.2). Prevalence of SDB with apnea-hypopnea index greater than 5/h and greater than 30/h was found in 71% (95% confidence interval 66.6%–74.8%) and 30% (95% confidence interval 24.4%–35.5%) of patients, respectively. Severity and prevalence of SDB were similar in all examined phases after stroke, irrespective of the type of sleep apnea test performed. Heterogeneity between studies (I2) was mostly high.ConclusionThe high prevalence of SDB after stroke and TIA, which persists over time, is important in light of recent studies reporting the (1) feasibility and (2) efficacy of SDB treatment in this clinical setting.

Download Full-text

Respiratory timing and variability during sleep in children with sleep-disordered breathing

Journal of Applied Physiology ◽

10.1152/japplphysiol.00756.2012 ◽

2012 ◽

Vol 113 (10) ◽

pp. 1635-1642 ◽

Cited By ~ 16

Author(s):

Sarah A. Immanuel ◽

Yvonne Pamula ◽

Mark Kohler ◽

James Martin ◽

Declan Kennedy ◽

...

Keyword(s):

Sleep Disordered Breathing ◽

Upper Airway ◽

Sleep Stages ◽

Control Group ◽

Apnea Hypopnea Index ◽

Study Cohort ◽

Healthy Children ◽

Equivalent Time ◽

Before And After ◽

Disordered Breathing

Sleep-disordered breathing (SDB) in children is assessed by quantification of hypopnea and apnea events. Little is known, however, about respiratory timing and breath-to-breath variability during sleep. The aim of this study was to investigate respiratory parameters across sleep stages in children with SDB before and after treatment compared with healthy children. Overnight polysomnography (PSG) was conducted in 40 children with SDB prior to and 6 mo following adenotonsillectomy. For comparison, a control group of 40 healthy sex- and age-matched children underwent two PSGs at equivalent time points but without intervention. The following variables were measured breath by breath during obstruction-free periods in stage 2 nonrapid eye movement (NREM), stage 4 NREM, and REM sleep: inspiratory time (Ti), expiratory time (Te), total time (Ttotal), inspiratory duty cycle (DC; =Ti/Ttotal), respiratory frequency (fR), and SD of the parameters Ti, Te, fR, and DC. Variability in waveform morphology was also computed using the residue of respiratory patterns. The severity of SDB was relatively mild in the study cohort (obstructive apnea hypopnea index: baseline, 5.1 ± 9.4 vs. 0.1 ± 0.2, P < 0.001; follow-up, 0.3 ± 0.3 vs. 0.8 ± 1.0, P < 0.01). Compared with healthy controls, children with SDB showed significantly longer Ti and Te and a lower fR at the baseline study. These differences were not significant after adenotonsillectomy. Sleep stages were associated with significant differences in all of the respiratory measures in both groups of children. In conclusion, children with relatively mild SDB showed prolonged inspiration and expiration indicative of chronic narrowing of the upper airway. Treatment of SDB normalizes respiratory timing. Documentation of these parameters may aid in both understanding and management of children with SDB.

Download Full-text

Sleep-Disordered Breathing and Nocturnal Hypoxemia in Precapillary Pulmonary Hypertension: Prevalence, Pathophysiological Determinants, and Clinical Consequences

Respiration ◽

10.1159/000515602 ◽

2021 ◽

pp. 1-12

Author(s):

Jens Spiesshoefer ◽

Simon Herkenrath ◽

Katharina Harre ◽

Florian Kahles ◽

Anca Florian ◽

...

Keyword(s):

Pulmonary Hypertension ◽

Sleep Apnea ◽

Sleep Quality ◽

Sleep Disordered Breathing ◽

Central Sleep Apnea ◽

Apnea Hypopnea Index ◽

Amino Terminal ◽

Nocturnal Hypoxemia ◽

Obstructive Sleep ◽

Disordered Breathing

Background and objective: The clinical relevance and interrelation of sleep-disordered breathing and nocturnal hypoxemia in patients with precapillary pulmonary hypertension (PH) is not fully understood. Methods: Seventy-one patients with PH (age 63 ± 15 years, 41% male) and 35 matched controls were enrolled. Patients with PH underwent clinical examination with assessment of sleep quality, daytime sleepiness, 6-minute walk distance (6MWD), overnight cardiorespiratory polygraphy, lung function, hypercapnic ventilatory response (HCVR; by rebreathing technique), amino-terminal pro-brain natriuretic peptide (NT-proBNP) levels, and cardiac MRI (n = 34). Results: Prevalence of obstructive sleep apnea (OSA) was 68% in patients with PH (34% mild, apnea-hypopnea index [AHI] ≥5 to <15/h; 34% moderate to severe, AHI ≥15/h) versus 5% in controls (p < 0.01). Only 1 patient with PH showed predominant central sleep apnea (CSA). Nocturnal hypoxemia (mean oxygen saturation [SpO2] <90%) was present in 48% of patients with PH, independent of the presence of OSA. There were no significant differences in mean nocturnal SpO2, self-reported sleep quality, 6MWD, HCVR, and lung and cardiac function between patients with moderate to severe OSA and those with mild or no OSA (all p > 0.05). Right ventricular (RV) end-diastolic (r = −0.39; p = 0.03) and end-systolic (r = −0.36; p = 0.04) volumes were inversely correlated with mean nocturnal SpO2 but not with measures of OSA severity or daytime clinical variables. Conclusion: OSA, but not CSA, is highly prevalent in patients with PH, and OSA severity is not associated with nighttime SpO2, clinical and functional status. Nocturnal hypoxemia is a frequent finding and (in contrast to OSA) relates to structural RV remodeling in PH.

Download Full-text

Interhemispheric Brain Switching Correlates with Severity of Sleep-Disordered Breathing for Obstructive Sleep Apnea Patients

Applied Sciences ◽

10.3390/app9081568 ◽

2019 ◽

Vol 9 (8) ◽

pp. 1568

Author(s):

Yuwen Li ◽

Zhimin Zhang ◽

Guohun Zhu ◽

Hongping Gan ◽

Deyin Liu ◽

...

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Sleep Disordered Breathing ◽

Brain Activity ◽

Sleep Stages ◽

Interhemispheric Asymmetry ◽

Switching Rate ◽

Obstructive Sleep ◽

Significant Difference ◽

Disordered Breathing

(1) Background: Alternating interhemispheric slow-wave activity during sleep is well-established in birds and cetaceans, but its investigation in humans has been largely neglected. (2) Methods: Fuzzy entropy was used to calculate a laterality index (LI) from C3 and C4 EEG channels. The subjects were grouped according to an apnoea-hypopnoea index (AHI) for statistical analyses: Group A AHI < 15 (mild); Group B 15 ≤ AHI < 30 (moderate); Group C AHI ≥ 30 (severe). The LI distribution was analysed to characterise the brain activity variation in both hemispheres, and the cross-zero switching rate was given statistical tests to find the correlations with the severity of obstructive sleep apnea and sleep states, i.e., wake (W), light sleep (LS), deep sleep (DS), and REM. (3) Results: EEG brain switching activity was observed in all sleep stages, and the LI distribution shows that, for obstructive sleep apnea patients, the interhemispheric asymmetry of brain activity is more obvious than healthy people. A one-way ANOVA revealed a significant difference of switching rate among three groups (F(2,95) = 7.23, p = 0.0012), with Group C shows the least, and also a significant difference among four sleep stages (F(3,94) = 5.09, p = 0.0026), with REM the highest. (4) Conclusions: The alternating interhemispheric activity is confirmed ubiquitous for humans during sleep, and sleep-disordered breathing intends to exacerbate the interhemispheric asymmetry.

Download Full-text

The Association between Sleep-Disordered Breathing and Magnetic Resonance Imaging Findings in a Pediatric Cohort with Chiari 1 Malformation

Canadian Respiratory Journal ◽

10.1155/2015/831569 ◽

2015 ◽

Vol 22 (1) ◽

pp. 31-36 ◽

Cited By ~ 17

Author(s):

Reshma Amin ◽

Priya Sayal ◽

Aarti Sayal ◽

Colin Massicote ◽

Robin Pham ◽

...

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Sleep Disordered Breathing ◽

Clinical Symptoms ◽

Apnea Hypopnea Index ◽

Imaging Findings ◽

Tonsillar Herniation ◽

Predominant Type ◽

Obstructive Sleep ◽

Disordered Breathing

BACKGROUND: The prevalence of sleep-disordered breathing (SDB) reported in the literature for Chiari malformation type 1 (CM1) is uniformly high (24% to 70%). In Canada, there is limited access to pediatric polysomnography (PSG). Therefore, the identification of clinical features would be invaluable for triaging these children.OBJECTIVE: To identify demographic features, clinical symptoms/signs and radiological findings associated with SDB in a large pediatric cohort with CM1.METHODS: A retrospective review was conducted on children with CM1 who underwent baseline PSG. Data were collected on patient demographics (age, sex, weight, height, body mass index), clinical symptoms (chart review and clinical questionnaires), diagnostic imaging of the brain and cervicothoracic spine, and medical history at the time of referral.RESULTS: A total of 68 children were included in the review. The mean (± SD) age of the children at the time of PSG was 7.33±4.01 years; 56% (n=38) were male. There was a 49% prevalence of SDB in this cohort based on the overall apnea-hypopnea index. Obstructive sleep apnea was the predominant type of SDB. Tonsillar herniation was significantly correlated with obstructive apnea-hypopnea index (r=0.24; P=0.036).CONCLUSIONS: A direct relationship between the degree of cerebellar tonsillar herniation and obstructive sleep apnea was demonstrated. However, further prospective studies that include neurophysiological assessment are needed to further translate the central nervous system imaging findings to predict the presence of SDB.

Download Full-text

Dimensions of sleepiness and their correlations with sleep-disordered breathing in mild sleep apnea

Jornal Brasileiro de Pneumologia ◽

10.1590/s1806-37132009000600003 ◽

2009 ◽

Vol 35 (6) ◽

pp. 507-514 ◽

Cited By ~ 7

Author(s):

Denis Martinez ◽

Magali Santos Lumertz ◽

Maria do Carmo Sfreddo Lenz

Keyword(s):

Sleep Apnea ◽

Sleep Disordered Breathing ◽

Stepwise Multiple Regression ◽

Apnea Hypopnea Index ◽

Stage 2 Sleep ◽

The Mean ◽

Medical Histories ◽

Stage 1 ◽

Relevant Factors ◽

Disordered Breathing

OBJECTIVE: There are many ways of assessing sleepiness, which has many dimensions. In patients presenting a borderline apnea-hypopnea index (AHI, expressed as events/hour of sleep), the mechanisms of excessive daytime sleepiness (EDS) remain only partially understood. In the initial stages of sleep-disordered breathing, the AHI might be related to as-yet-unexplored EDS dimensions. METHODS: We reviewed the polysomnography results of 331 patients (52% males). The mean age was 40 ± 13 years, and the mean AHI was 4 ± 2 (range, 0-9). We assessed ten potential dimensions of sleepiness based on polysomnography results and medical histories. RESULTS: The AHI in non-rapid eye movement (NREM) stage 1 sleep (AHI-N1), in NREM stage 2 sleep (AHI-N2), and in REM sleep (AHI-REM) were, respectively, 6 ± 7, 3 ± 3 and 10 ± 4. The AHI-N2 correlated significantly with the greatest number of EDS dimensions (5/10), including the Epworth sleepiness scale score (r = 0.216, p < 0.001). Factor analysis, using Cronbach's alpha, reduced the variables to three relevant factors: QUESTIONNAIRE (α = 0.7); POLYSOMNOGRAPHY (α = 0.68); and COMPLAINTS (α = 0.55). We used these factors as dependent variables in a stepwise multiple regression analysis, adjusting for age, gender, and body mass index. The AHI-N1 correlated significantly with POLYSOMNOGRAPHY (β = -0.173, p = 0.003), and the AHI-N2 correlated significantly with COMPLAINTS (β = -0.152, p = 0.017). The AHI-REM did not correlate with any factor. CONCLUSIONS: Our results underscore the multidimensionality of EDS in mild sleep apnea.

Download Full-text