Sleep Apnea Severity Estimation from Respiratory Related Movements Using Deep Learning

Hafezi, Maziar; Montazeri, N.; Zhu, Kevin; Alshaer, Hisham; Yadollahi, Azadeh; Taati, Babak

doi:10.1109/embc.2019.8857524

Cited by 11 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The estimated AHI values in this study had a strong correlation with PSG-derived AHI values. Previously, we published the proof of concept for using deep learning and the accelerometer data for sleep apnea screening [41]. However, that study was validated on 20 subjects and only the correlation between the estimated AHI and PSG-based AHI were reported.…”

Section: Discussionmentioning

confidence: 99%

“…The cut-off frequency of 25 Hz was selected to preserve high-frequency vibrations caused by snoring. Seven morphological features from each movement axis (x, y, and z) were extracted using a sliding window of 10 seconds with a 9 seconds overlap [41]. We selected the sliding window of 10 seconds as the average duration of each breath is 3 seconds and at least three breaths were happening within each window.…”

Section: Data Analyses 1) Feature Extractionmentioning

confidence: 99%

“…We previously analyzed different window lengths and different deep-learning architectures for event-by-event classification [41]. In this study, we developed a supervised deep learning classifier and optimized the hyper-parameters to increase the accuracy of the model.…”

Section: ) Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Sleep Apnea Severity Estimation From Tracheal Movements Using a Deep Learning Model

et al. 2020

Self Cite

View full text Add to dashboard Cite

Sleep apnea is a chronic respiratory disorder and its standard assessment requires full night in-laboratory polysomnography (PSG). However, PSG is expensive, time-consuming, and inconvenient. Thus, there is a need to monitor sleep apnea with more convenient wearable devices. The objective of this study was to implement deep learning algorithms to monitor sleep apnea severity based on respiratory movements that can be easily recorded over the trachea. Methods: Adult individuals referred to the sleep laboratory at the Toronto Rehabilitation Institute for overnight sleep studies were included (N=69). Simultaneously with the PSG, an accelerometer was attached to the participant's suprasternal notch to record tracheal respiratory movements. Twenty-one features were extracted from the tracheal movements and used in a deep learning classifier to detect respiratory events. The apnea hypopnea index (AHI) was estimated as the number of events per hour of sleep. Results: The F1 score of the event-by-event detection algorithm was between 12% and 71% for different groups of sleep apnea severity. There was a strong correlation between the estimated and the PSG-derived AHI (r=0.86, p < 0.0001). Using the AHI cutoff of 15, the sensitivity, specificity, and accuracy of diagnosing sleep apnea were 81%, 87%, and 84%, respectively. Conclusion: A combination of advanced machine learning algorithms and respiratory-related movements can accurately estimate sleep apnea severity and detect respiratory events during sleep. Significance: The proposed method can be implemented as a cost-effective and reliable wearable device for monitoring sleep apnea in the home and community. INDEX TERMS Accelerometer, apnea hypopnea index, deep learning, physiological features, wearable devices, sleep apnea monitoring.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Data Analyses 1) Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

Sleep Apnea Severity Estimation From Tracheal Movements Using a Deep Learning Model

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…The DL approach has been applied to medical settings and language processing and can extract the rich data contained in PSG and automatically finish sleep staging. 68 A study using three DL methods (CNN, LSTM, CNN + LSTM) to estimate the AHI 69 demonstrated the correlation r value between the gold standard AHI with an estimated value of 0.84, which showed that this system may serve as a convenient tool for a homebased sleep apnea test (HSAT). The HSAT is expected to be more efficacious and cost effective and to eventually play a crucial part in quantifying OSA in the future.…”

Section: Deep Learning/machine Learningmentioning

confidence: 99%

<p>A Review of Current Tools Used for Evaluating the Severity of Obstructive Sleep Apnea</p>

Cao

Luo

Xiao

2020

NSS

View full text Add to dashboard Cite

“…Tracheal signals have been extensively used to monitor respiration during sleep and assess the severity of sleep apnea by estimating AHI. [8][9][10][11][12][13][14][15][16][17] Tracheal sounds can be conveniently recorded using a microphone embedded in a portable device attached over the suprasternal notch. Recently, we have developed a device called "The Patch" to record tracheal respiratory related sounds and movements.…”

Section: Introductionmentioning

confidence: 99%

<p>Sleep/Wakefulness Detection Using Tracheal Sounds and Movements</p>

Ghahjaverestan¹,

Akbarian²,

Hafezi³

et al. 2020

NSS

Self Cite

View full text Add to dashboard Cite

Sleep Apnea Severity Estimation from Respiratory Related Movements Using Deep Learning

Cited by 11 publications

References 16 publications

Sleep Apnea Severity Estimation From Tracheal Movements Using a Deep Learning Model

Sleep Apnea Severity Estimation From Tracheal Movements Using a Deep Learning Model

<p>A Review of Current Tools Used for Evaluating the Severity of Obstructive Sleep Apnea</p>

<p>Sleep/Wakefulness Detection Using Tracheal Sounds and Movements</p>

Contact Info

Product

Resources

About