Assessment of respiratory flow and efforts using upper-body acceleration considering Sleep Apnea Syndrome

Date created: 
2012-05-31
Identifier: 
etd7204
Keywords: 
Obstructive sleep apnea
Central sleep apnea
Polysomnography (PSG)
Machine learning methods
Abstract: 

Sleep apnea monitoring requires measurement of both the respiratory flow and efforts in order to detect apnea periods and classify them into obstructive and central ones. In this paper, an innovative method for estimating the respiratory flow and efforts is proposed and evaluated in various sleeping postures and flow rates. We use three MEMS accelerometers mounted on the suprasternal notch, the thorax and the abdomen of subjects in supine, prone and lateral positions to record the upper airway acceleration and the chest and abdomen walls movement. The respiratory flow and efforts are estimated from the recorded acceleration signals by applying machine learning methods. To assess the agreement of estimated signals with the well-established measurement methods, Standard Error of Measurement (SEM) was calculated and ρ=1-SEM was derived from it for every condition. A significant agreement (ρ>0.82) between the estimated and reference signals was found. Additionally, tPTEF/tE and tPTIF/tI ratios for each breathing cycle of the estimated and the reference flow were calculated.

Document type: 
Thesis
Rights: 
Copyright remains with the author. The author has not granted permission for the file to be printed nor for the text to be copied and pasted. If you would like a printable copy of this thesis, please contact summit-permissions@sfu.ca.
File(s): 
Supervisor(s): 
Bozena Kaminska
Department: 
Applied Science: School of Engineering Science
Thesis type: 
(Thesis) M.A.Sc.
Statistics: