scholarly journals Classification and Detection of Breathing Patterns with Wearable Sensors and Deep Learning

Sensors ◽  
2020 ◽  
Vol 20 (22) ◽  
pp. 6481
Author(s):  
Kristin McClure ◽  
Brett Erdreich ◽  
Jason H. T. Bates ◽  
Ryan S. McGinnis ◽  
Axel Masquelin ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Wearable Sensors ◽  
Rapid Assessment ◽  
Central Sleep Apnea ◽  
Breathing Patterns ◽  
Movement Data ◽  
Normal Breathing ◽  
Obstructive Sleep

Rapid assessment of breathing patterns is important for several emergency medical situations. In this research, we developed a non-invasive breathing analysis system that automatically detects different types of breathing patterns of clinical significance. Accelerometer and gyroscopic data were collected from light-weight wireless sensors placed on the chest and abdomen of 100 normal volunteers who simulated various breathing events (central sleep apnea, coughing, obstructive sleep apnea, sighing, and yawning). We then constructed synthetic datasets by injecting annotated examples of the various patterns into segments of normal breathing. A one-dimensional convolutional neural network was implemented to detect the location of each event in each synthetic dataset and to classify it as belonging to one of the above event types. We achieved a mean F1 score of 92% for normal breathing, 87% for central sleep apnea, 72% for coughing, 51% for obstructive sleep apnea, 57% for sighing, and 63% for yawning. These results demonstrate that using deep learning to analyze chest and abdomen movement data from wearable sensors provides an unobtrusive means of monitoring the breathing pattern. This could have application in a number of critical medical situations such as detecting apneas during sleep at home and monitoring breathing events in mechanically ventilated patients in the intensive care unit.

scholarly journals Yolo4Apnea: Real-time Detection of Obstructive Sleep Apnea

2020 ◽  
Author(s):  
Sondre Hamnvik ◽  
Pierre Bernabé ◽  
Sagar Sen
Keyword(s):  
Obstructive Sleep Apnea ◽  
Heart Disease ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Real Time ◽  
Source Code ◽  
Learning System ◽  
Breathing Patterns ◽  
Obstructive Sleep ◽  
Abdominal Breathing

Obstructive sleep apnea is a serious sleep disorder that affects an estimated one billion adults worldwide. It causes breathing to repeatedly stop and start during sleep which over years increases the risk of hypertension, heart disease, stroke, Alzheimer's, and cancer. In this demo, we present Yolo4Apnea a deep learning system extending You Only Look Once (Yolo) system to detect sleep apnea events from abdominal breathing patterns in real-time enabling immediate awareness and action. Abdominal breathing is measured using a respiratory inductance plethysmography sensor worn around the stomach. The source code is available at https://github.com/simula-vias/Yolo4Apnea

scholarly journals Accurate Deep Learning-Based Sleep Staging in a Clinical Population with Suspected Obstructive Sleep Apnea

2019 ◽  
pp. 1-1 ◽  
Author(s):  
Henri Korkalainen ◽  
Timo Leppanen ◽  
Juhani Aakko ◽  
Sami Nikkonen ◽  
Samu Kainulainen ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Clinical Population ◽  
Sleep Staging ◽  
Obstructive Sleep

827 Central Sleep Apnea in a patient with Multiple Sclerosis

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A322-A323
Author(s):  
Rahul Dasgupta ◽  
Sonja Schütz ◽  
Tiffany Braley
Keyword(s):  
Multiple Sclerosis ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Sleep Disordered Breathing ◽  
Central Sleep Apnea ◽  
Progressive Multiple Sclerosis ◽  
Obstructive Sleep ◽  
Increased Risk ◽  
Demyelinating Lesions ◽  
The Brain

Abstract Introduction Sleep-disordered breathing is common in persons with multiple sclerosis (PwMS), and may contribute to debilitating fatigue and other chronic MS symptoms. The majority of research to date on SDB in MS has focused on the prevalence and consequences of obstructive sleep apnea; however, PwMS may also be at increased risk for central sleep apnea (CSA), and the utility of methods to assess CSA in PwMS warrant further exploration. We present a patient with secondary progressive multiple sclerosis who was found to have severe central sleep apnea on WatchPAT testing. Report of case(s) A 61 year-old female with a past medical history of secondary progressive multiple sclerosis presented with complaints of fragmented sleep. MRI of the brain, cervical spine, and thoracic spine showed numerous demyelinating lesions in the brain, brainstem, cervical, and thoracic spinal cord. Upon presentation, the patient noted snoring, witnessed apneas, and daytime sleepiness. WatchPAT demonstrated severe sleep apnea, with a pAHI of 63.3, and a minimum oxygen saturation of 90%. The majority of the scored events were non-obstructive in nature (73.1% of all scored events), and occurred intermittently in a periodic fashion. Conclusion The differential diagnosis of fatigue in PwMS should include sleep-disordered breathing, including both obstructive and central forms of sleep apnea. Demyelinating lesions in the brainstem (which may contribute to impairment of motor and sensory networks that control airway patency and respiratory drive), and progressive forms of MS, have been linked to both OSA and CSA. The present data illustrate this relationship in a person with progressive MS, and offer support for the WatchPAT as a cost-effective means to evaluate for both OSA and CSA in PwMS, while reducing patient burden. PwMS may be at increased risk for CSA. Careful clinical consideration should be given to ordering appropriate sleep testing to differentiate central from obstructive sleep apnea in PwMS, particularly for patients with demyelinating lesions in the brainstem. Support (if any) 1. Braley TJ, Segal BM, Chervin RD. Obstructive sleep apnea and fatigue in patients with multiple sclerosis. J Clin Sleep Med. 2014 Feb 15;10(2):155–62. doi: 10.5664/jcsm.3442. PMID: 24532998; PMCID: PMC3899317.

Brainstem Evoked Potentials in Adult Sleep Apnea

1982 ◽  
Vol 91 (6) ◽  
pp. 597-598 ◽  
Author(s):  
Nancy L. Snyderman ◽  
Margareta Møller ◽  
Jonas T. Johnson ◽  
Patricia B. Thearle
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Evoked Potentials ◽  
Central Sleep Apnea ◽  
Obstructive Sleep ◽  
Brainstem Dysfunction ◽  
Brainstem Evoked Potentials

Brainstem evoked potentials (BSEP) were recorded in 23 patients with adult sleep apnea (ASA). These patients were studied with all-night polysomnography prior to our testing. They were categorized as having obstructive, central, or mixed sleep apnea depending on the predominant sleep findings. All patients with central sleep apnea had abnormal BSEP with prolongation of wave V. A majority of the remaining patients with obstructive sleep apnea and mixed sleep apnea had abnormal BSEP, but without specific configurations. These findings substantiate our hypothesis that brainstem dysfunction may play a role in ASA.

393 Comparison of Oxygenation Abnormalities Between Obstructive Sleep Apnea and Central Sleep Apnea

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A156-A157
Author(s):  
Sikawat Thanaviratananich ◽  
Hao Cheng ◽  
Maria Pino ◽  
Krishna Sundar
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Demographic Data ◽  
Central Sleep Apnea ◽  
Nrem Sleep ◽  
Rate Of Change ◽  
Apnea Hypopnea Index ◽  
P Value ◽  
Obstructive Sleep ◽  
Cheyne Stokes Breathing

Abstract Introduction The apnea-hypopnea index (AHI) is used as a generic index to quantify both central sleep apnea (CSA) and obstructive sleep apnea (OSA) syndromes. Patterns of oxygenation abnormalities seen in CSA and OSA may be key to understanding differing clinical impacts of these disorders. Oxygen desaturation and resaturation slopes and durations in OSA and CSA were compared between OSA and CSA patients. Methods Polysomnographic data of patients aged 18 years or older with diagnosis of OSA and CSA, at University of Iowa Hospitals and Clinics, were analyzed and demographic data were collected. Oximetric changes during hypopneas and apneas were studied for desaturation/resaturation durations and desaturation/resaturation slopes. Desaturation and resaturation slopes were calculated as rate of change in oxygen saturation (ΔSpO2/Δtime). Comparison of hypoxemia-based parameters between patients with OSA and CSA was performed using unpaired t-test. Results 32 patients with OSA with median AHI of 15.4 (IQR 5.1 to 30.55) and median ODI of 15.47 (IQR 9.50 to 29.33) were compared to 15 patients with CSA with a median AHI of 20.4 (IQR 12.6 to 47.8) and median ODI of 27.56 (IQR 17.99 to 29.57). The mean number of desaturation and resaturation events was not significantly different between patients with OSA and CSA (OSA - 106.81±87.93; CSA - 130.67±76.88 with a p-value 0.1472). 4/15 CSA patients had Cheyne-Stokes breathing, 2/15 had treatment emergent central sleep apnea, 1/15 had methadone-associated CSA and for 8/15, no etiologies for CSA were found. Mean desaturation durations was significantly longer in OSA (20.84 s ± 5.67) compared to CSA (15.94 s ± 4.54) (p=0.0053) and consequently the desaturation slopes were steeper in CSA than OSA (-0.35%/sec ±0.180 vs. -0.243 ± 0.073; p=0.0064). The resaturation duration was not significantly longer in OSA (9.76 s ± 2.02) than CSA (9.057 s ± 2.17) (p=0.2857). Differences between desaturation duration and slopes between CSA and OSA persisted during REM and NREM sleep, and in supine sleep. Conclusion As compared to OSA, patients with CSA have different patterns of desaturations and resaturations with lesser hypoxic burden with CSA. This may have implications on the clinical outcomes seen between these two disorders. Support (if any):

scholarly journals A Detection and Therapeutic Device to Overcome Sleep Apnea in Infants

2020 ◽  
Vol 2 (1) ◽  
pp. 35
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Airway Pressure ◽  
Upper Airway ◽  
Periodic Breathing ◽  
Breathing Patterns ◽  
Efficient System ◽  
Pressure Therapy ◽  
Obstructive Sleep ◽  
Upper Airway Structure

Among the various sleep-disordered breathing patterns infant’s experience, like periodic breathing, premature apnea, obstructive sleep apnea, has been considered a major cause of concern. Upper airway structure, mechanics of the pulmonary system, etc., are a few reasons why the infants are vulnerable to obstructive sleep-disordered. An imbalance in the viscoelastic properties of the pharynx, dilators, and pressure can lead to airway collapse. A low level of oxygen in blood or hypoxemia is considered a characteristic in infants with severe OSA. Invasive treatments like nasopharyngeal tubes, continuous positive airway pressure (CPAP), or tracheostomy are found to be helpful in most cases where infants experience sleep apnea. This paper proposes an efficient system for monitoring obstructive sleep apnea in infants on a long-term basis, and if any anomaly is detected, the device provides Continuous Airway Pressure therapy until the abnormality is normalized.

407 Explanatory analysis of polysomnography for the identification of sleep apnea hypopnea events using deep learning neural network

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A161-A162
Author(s):  
Soonhyun Yook ◽  
Chaitanya Gupte ◽  
Zhixian Han ◽  
Eun Yeon Joo ◽  
Hea Ree Park ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Learning Algorithms ◽  
Sleep Apnea Syndrome ◽  
Learning Approaches ◽  
Explanatory Analysis ◽  
Technology Advancement ◽  
Obstructive Sleep ◽  
Deep Learning Neural Network

Abstract Introduction Using deep learning algorithms, we investigated univariate and multivariate effects of four polysomnography features including heart rate (HR), electrocardiogram (ECG), oxygen saturation (SpO2) and nasal air flow (NAF) on the identification of sleep apnea and hypopnea events. This explanatory analysis that may clarify the sensitivity and specificity of those features to SAs and SHs have not been probed. Methods We studied 804 polysomonography samples from 704 patients with obstructive sleep apnea and 100 controls. The input data were converted into scalograms as 4-channel 2D images to train Xception networks. For training, 77,638 patches were sampled from the original 6-hour sleep data with 30-second time width. A 10% of these patches were segregated as the test-set. With each feature sets, we tested the following classifications: 1) normal vs apnea vs hypopnea; 2) normal vs. apnea+hypopnea; 3) normal vs. apnea; and 4) normal vs. hypopnea. Results SpO2 classified normal vs. apnea most accurately (98%), followed by NAF (85%), ECG (77%), and HR (63%). SpO2 also showed the highest accuracy in classifying normal vs. hypopnea (87%), and normal vs. apnea+hypopnea (96%) and three groups (82%). When the combination of four features were used, the classification accuracies were generally improved compared to use of SpO2 only (normal vs. apnea 99%; vs. hypopnea 89%; vs. apnea+hypopnea: 94%; three groups: 86%). Conclusion Deep learning with SpO2 or NAF feature most accurately classified apneas from normal sleep events, suggesting these features’ characterization of sleep apnea events. Oxygen desaturation, which is a typical pattern of hypopnea, was only the feature showing reliable accuracy in classifying hypopnea vs. normal. Nevertheless, combination of four polysomnography features could improve the identification of sleep apnea and hypopnea. Furthermore, classifying normal vs. apnea+hypopnea was more accurate than separately classifying three groups, suggesting deep learning approaches as the primary screen tool. Since the classification accuracy of using SpO2 was higher than any other features, developing a portable equipment measuring SpO2 and running deep learning algorithms has the potential for inexpensive, accurate diagnostics of obstructive sleep apnea syndrome. Support (if any) This study was supported by USC STEVENS CENTER FOR INNOVATION TECHNOLOGY ADVANCEMENT GRANTS (TAG), BrightFocus Foundation Award (A2019052S).

The Association between Obstructive Sleep Apnea and Allergic Rhinitis: Current Literature Review

2021 ◽  
Vol 17 ◽  
Author(s):  
Shi Nee Tan ◽  
Baharudin Abdullah
Keyword(s):  
Obstructive Sleep Apnea ◽  
Allergic Rhinitis ◽  
Sleep Apnea ◽  
Central Sleep Apnea ◽  
Sleep Apnea Syndromes ◽  
T Helper 2 ◽  
Obstructive Sleep ◽  
Common Clinical Practice ◽  
High Level ◽  
Chemical Mediators

: Sleep-disordered breathing (SDB) is now a significant health problem in today's culture. It ranges from a spectrum of abnormal conditions during sleep from the primary snorer to mild, moderate, or severe obstructive sleep apnea (OSA). SDB also comprises other conditions, such as sleep-related hypoventilation, sleep-related hypoxemia, and central sleep apnea syndromes. One of the components of the pathophysiology of OSA that remain unclear is the association of allergic rhinitis (AR) in the evolution of OSA. Several studies relate OSA and AR's co-existence in the common clinical practice, but its correlation was not clear. This review article aimed to review the relationship between OSA and AR in terms of the role of chemical mediators and pathophysiological and the effect of AR treatment in support of OSA. The symptoms of AR further accelerate the clinical progression to OSA development. Inflammatory mediators such as histamine, cysteinyl leukotrienes, and interleukins are found at a high level in AR, which can aggravate AR symptoms such as nasal obstruction, rhinorrhea, and itchiness, which can then lead to sleep disruption in OSA patients. In addition, OSA patients also have increased chemical mediators such as tumor necrosis factor, interleukin 6, and 1, which would activate the T helper 2 phenotypes that can aggravate AR symptoms. This vicious cycle can potentiate each other and worsen the condition. Few studies have shown that treatment of AR can improve OSA, especially the use of intranasal steroid and leukotriene receptor antagonists. A detailed evaluation of rhinitis symptoms should be made for those OSA patients so that they can benefit not only from the improvement of AR but also the good sleep quality.

Sign in / Sign up

Export Citation Format

Share Document