scholarly journals Detecting Excessive Daytime Sleepiness With CNN And Commercial Grade EEG

2021 ◽  
Vol 12 (3) ◽  
pp. 186
Author(s):  
I Putu Agus Eka Darma Udayana ◽  
Made Sudarma ◽  
Ni Wayan Sri Ariyani
Keyword(s):  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Epworth Sleepiness Scale ◽  
Sleep Medicine ◽  
Assessment Method ◽  
University Student ◽  
Self Assessment ◽  
Commercial Grade ◽  
Obstructive Sleep ◽  
Small Dataset

Epworth sleepiness scale is a self-assessment method in sleep medicine that has been proven to be a good predictor of obstructive sleep apnea. However, the over-reliance of the method making the process not socially distancing friendly enough in response to a global covid-19 pandemic. A study states that the Epworth sleepiness scale is correlated with the brainwave signal that commercial-grade EEG can capture. This study tried to train a classifier powered by CNN and deep learning that could perform as well as the Epworth with the objectiveness of brainwave signal. We test the classifier using the 20 university student using the Epworth sleepiness test beforehand. Then, we put the participant in 10 minutes EEG session, downsampling the data for normalization purposes and trying to predict the outcome of the ESS in respect of their brainwave state. The AI predict the reaching 65% of accuracy and 81% of sensitivity with just under 100.000 dataset which is excellent considering small dataset although this still have plenty room for improvement.

394 A convolutional neural networks model for the detection of cortical arousals from heart rate

SLEEP ◽  
2021 ◽  
Vol 44 (Supplement_2) ◽  
pp. A157-A157
Author(s):  
Brandon Lockyer ◽  
Andrew Wellman ◽  
Kirsi-Marja Zitting
Keyword(s):  
Neural Networks ◽  
Heart Rate ◽  
Obstructive Sleep Apnea ◽  
Deep Learning ◽  
Sleep Apnea ◽  
Sympathetic Activity ◽  
Sleep Medicine ◽  
Wearable Devices ◽  
Obstructive Sleep ◽  
Preliminary Study

Abstract Introduction Cortical arousals are transient events of disturbed sleep that occur frequently in sleep disordered breathing (SDB) and can be used as an indicator of sleep quality. While cortical arousals are typically scored from the electroencephalogram (EEG), arousals are associated with increased sympathetic activity and could therefore be detected from measures of sympathetic activity such as heart rate. Most home sleep test and consumer wearable devices enable continuous recording of heart rate via the electrocardiogram (ECG) or optical heart rate sensors without the inconvenience of EEG electrodes. In this preliminary study, we developed a deep learning-based convolutional neural networks (CNN) model to detect arousals from heart rate. Methods This study included 1,083 polysomnograms (PSGs) from five independent studies (Tucson Children’s Assessment of Sleep Apnea, Mechanisms of Pharyngeal Collapse in Sleep Apnea, Impact of the Arousal Threshold in Obstructive Sleep Apnea, Predicting Successful Sleep Apnea Treatment with Acetazolamide in Heart Failure Patients, Combination Therapy for the Treatment of Obstructive Sleep Apnea) that were scored for arousals according to American Academy of Sleep Medicine scoring rules. These studies included PSGs from both children and adults (ages 6 and above), with most data coming from participants with evidence or diagnosis of SDB. We used the Pan-Tomkins algorithm to detect R-peaks from the raw ECG signal, transformed the peaks into normalized instantaneous heart rate at 1 Hz frequency, and produced arousal probability in 1-second resolution using a simple CNN model. Due to slight asynchrony between the appearance of arousals in the EEG versus the heart rate, all overlaps between model-predicted arousals and manually scored arousals were considered true-positives. Results We evaluated the model on a validation set (n=216). The model achieved a gross area under precision-recall curve score of 0.67 and a gross area under receiver operating characteristics curve of 0.91 Correlation between the number of model-detected and manually scored arousal events was r=0.76. Conclusion This preliminary study demonstrates that a deep learning approach has the potential to accurately detect arousals in home sleep tests and consumer wearable devices that measure heart rate. Support (if any) The study was supported by grant #207-SR-19 from the American Academy of Sleep Medicine Foundation.

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

scholarly journals Subjective and Objective Appraisal of Activity in Adults with Obstructive Sleep Apnea

2011 ◽  
Vol 2011 ◽  
pp. 1-6 ◽  
Author(s):  
Eileen R. Chasens ◽  
Susan M. Sereika ◽  
Martin P. Houze ◽  
Patrick J. Strollo
Keyword(s):  
Physical Activity ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Epworth Sleepiness Scale ◽  
Functional Outcomes ◽  
Apnea Hypopnea Index ◽  
Sleep Study ◽  
Obstructive Sleep ◽  
Subjective Sleepiness ◽  
Aging Adults

Objective.This study examined the association between obstructive sleep apnea (OSA), daytime sleepiness, functional activity, and objective physical activity.Setting.Subjects (N=37) being evaluated for OSA were recruited from a sleep clinic.Participants. The sample was balanced by gender (53% male), middle-aged, primarily White, and overweight or obese with a mean BMI of 33.98 (SD=7.35;median BMI=32.30). Over 40% reported subjective sleepiness (Epworth Sleepiness Scale (ESS) ≥10) and had OSA (78% with apnea + hypopnea index (AHI) ≥5/hr).Measurements.Evaluation included questionnaires to evaluate subjective sleepiness (Epworth Sleepiness Scale (ESS)) and functional outcomes (Functional Outcomes of Sleep Questionnaire (FOSQ)), an activity monitor, and an overnight sleep study to determine OSA severity.Results.Increased subjective sleepiness was significantly associated with lower scores on the FOSQ but not with average number of steps walked per day. A multiple regression analysis showed that higher AHI values were significantly associated with lower average number of steps walked per day after controlling patient's age, sex, and ESS.Conclusion.Subjective sleepiness was associated with perceived difficulty in activity but not with objectively measured activity. However, OSA severity was associated with decreased objective physical activity in aging adults.

scholarly journals 0907 Implementation Of Pathway For Severe Obstructive Sleep Apnea Management In Children

SLEEP ◽  
2020 ◽  
Vol 43 (Supplement_1) ◽  
pp. A345-A345
Author(s):  
S Gehring ◽  
L Auricchio ◽  
S Kidwell ◽  
K Oppy ◽  
S Smallwood ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Health Care Providers ◽  
Therapeutic Option ◽  
Sleep Medicine ◽  
Close Monitoring ◽  
Severe Obstructive Sleep Apnea ◽  
Care Providers ◽  
Oxygen Supplementation ◽  
Obstructive Sleep

Abstract Introduction Obstructive Sleep Apnea (OSA) is associated with neuro-cognitive, cardiovascular and metabolic morbidity in children. Adeno-tonsillectomy is the first line of treatment for OSA with PAP therapy and Oxygen supplementation being alternative therapeutic options in select cases. Severe Obstructive Sleep Apnea is a known risk factor for postoperative respiratory complications after adenotonsillectomy. Therefore, inpatient adenotonsillectomy with close monitoring is recommended for this group of children. Challenges to safe and timely care for this high risk group of children can be overcome with effective coordination of care between different locations and health care providers. Methods All children seeking treatment at Dayton Children’s Division of Sleep Medicine were managed through a pathway developed by a multi-disciplinary team involving sleep medicine, otolaryngology and clinical logistics. Severe OSA was defined as AHI ≥15 events/hr (children <2 year old), AHI ≥15 events/hr with three or more Oxygen desaturations <80% (children ≥2 to <6 years old), AHI ≥ 30 events/hr with three or more Oxygen desaturations <80% (Children ≥6 to 18 years old). Results A total of 78 children were diagnosed with severe OSA in 2019. All children were successfully triaged to appropriate therapeutic option (Adenonotonsillectomy, PAP, O2) within 24 hours of diagnosis. Urgent adenotonsillectomy was performed on the same day in 4 children and within 2 weeks on 12 children. There was no postoperative respiratory complication after urgent adenotonsillectomy. Thirteen children had adenotonsillectomy after 2 weeks. PAP therapy was started in 28 children (34%). Therapy was initiated on the same day in 10 children and the next day on one child. Oxygen supplementation was started in 21 children (27%). Conclusion A multidisciplinary collaborative approach can result in delivery of timely and safe care for severe OSA in children. Support NA

Abstract TP221: Using Berlin Questionnaire and Epworth Sleepiness Scale to Identify Stroke Patients at Risk for the Sleep Apnea Syndrome

Stroke ◽  
2013 ◽  
Vol 44 (suppl_1) ◽  
Author(s):  
Millene Camilo ◽  
Alan Eckeli ◽  
Heidi Sander ◽  
Regina Fernandes ◽  
Joao Leite ◽  
...  
Keyword(s):  
Obstructive Sleep Apnea ◽  
Ischemic Stroke ◽  
Sleep Apnea ◽  
Positive Predictive Value ◽  
Negative Predictive Value ◽  
Predictive Value ◽  
Epworth Sleepiness Scale ◽  
Berlin Questionnaire ◽  
Stroke Patients ◽  
Obstructive Sleep

Background: Sleep-disordered breathing (SDB) is frequent in the acute phase of stroke. Obstructive sleep apnea (OSA) has been found in 62% of stroke patients. The impact of OSA is significant after ischemic stroke, including early neurological deterioration, poor functional outcome and increased long-term mortality. However, performing polysomnography (PSG) for all patients with acute stroke for diagnose OSA is still impracticable. Therefore clinical tools to select patients at higher risk for OSA would be essential. The aim of this study was to determine the validity of the Berlin Questionnaire (BQ) and the Epworth Sleepiness Scale (ESS) to identify stroke patients in whom the PSG would be indicated. Methods: Subjects with ischemic stroke were stratified into high and low risk groups for SDB using a BQ. The ESS ≥ 10 was used to define excessive daytime sleepiness. The BQ and ESS were administered to the relatives of stroke patients at hospital admission. All patients were submitted to a full overnight PSG at the first night after symptoms onset. OSA severity was measured by the apnea-hypopnea index (AHI). Results: We prospectively studied 40 ischemic stroke patients. The mean age was 62 ± 12.1 years and the obstructive sleep apnea (AHI ≥ 15) was present in 67.5%. On stratifying risk of OSA in these patients based on the QB, 77.5% belonged to the high-risk and 50% to the ESS ≥ 10. The sensitivity of QB was 85%, the specificity 35%, the positive predictive value 74% and the negative predictive value 55%. For ESS was respectively 63%, 85%, 89% and 52%. The diagnostic value of the BQ and ESS in combination to predict OSA had a sensitivity of 58%, a specificity of 89%, a positive predictive value of 95% and a negative predictive value of 38%. Conclusions: The QB even applied to the bed-partners of stroke patients is a useful screening tool for OSA.

Sign in / Sign up

Export Citation Format

Share Document