Airflow-Oximetry Combined Signal Based Automatic Detection of Sleep Apnea in Adults

Uddin, Md Bashir

Airflow-Oximetry Combined Signal Based Automatic Detection of Sleep Apnea in Adults

Uddin, Md Bashir

Permalink

Publication Type:: Thesis
Issue Date:: 2020

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download contents and abstractAdobe PDF (774.65 kB)

Adobe PDF

Download thesisAdobe PDF (13.89 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Uddin, Md Bashir
dc.date.accessioned	2021-05-26T04:34:38Z
dc.date.available	2021-05-26T04:34:38Z
dc.date.issued	2020
dc.identifier.uri	http://hdl.handle.net/10453/149237
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Sleep apnea, a common sleep disorder, can significantly decrease the quality of life and is closely associated with major health risks such as cardiovascular disease, sudden death, depression, and hypertension. It also elicits brain and physiological changes that vary across the night. Conventional diagnosis of sleep apnea using polysomnography (PSG) is costly and time-consuming, requiring manual scoring of sleep stages and respiratory events. Current automatic diagnostic algorithms used to detect sleep apnea vary in approaches with the use of different physiological signals. An effective, reliable, and accurate automatic method for the diagnosis of sleep apnea will be time-efficient and economical. This thesis is a narration of the work that led to the development of a novel algorithm suitable for the automatic diagnosis of sleep apnea. A systematic literature review of the existing methods (approaches and algorithms) was performed before designing the algorithm. This review presented an overview of methods to diagnose sleep apnea using respiratory and oximetry signals. The review identified the research gaps with indicating the major concerns, challenges, benefits, and limitations of using respiratory and oximetry signals for the diagnosis of sleep apnea. This thesis examined the electroencephalogram (EEG) spectral powers resulting from apnea duration of varying length and reported the changes in the relative powers in EEG frequency bands before and at apnea termination. The study was carried out for the purpose of justifying the usability of EEG for the automatic diagnosis of sleep apnea. It investigated the spectral power changes in delta, theta, alpha, sigma, and beta frequency bands of EEG as a function of apnea duration from 375 events. The study revealed a significant reduction in EEG relative powers (the low frequency theta, alpha, and sigma powers) both before and at apnea termination. The findings from the EEG spectral analysis suggests that the application of EEG signal in sleep apnea diagnosis is not reliable due to the random variations in spectral powers as well as the major challenges associated with EEG acquisition and its processing. Due to the limitations associated with the EEG for an unattended home diagnosis of sleep apnea, the EEG signal was excluded from the automatic detection approach […]	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/149237/2/02whole.pdf
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	au.edu.uts.lib/ppc
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Airflow-Oximetry Combined Signal Based Automatic Detection of Sleep Apnea in Adults	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Sleep apnea, a common sleep disorder, can significantly decrease the quality of life and is closely associated with major health risks such as cardiovascular disease, sudden death, depression, and hypertension. It also elicits brain and physiological changes that vary across the night. Conventional diagnosis of sleep apnea using polysomnography (PSG) is costly and time-consuming, requiring manual scoring of sleep stages and respiratory events. Current automatic diagnostic algorithms used to detect sleep apnea vary in approaches with the use of different physiological signals. An effective, reliable, and accurate automatic method for the diagnosis of sleep apnea will be time-efficient and economical. This thesis is a narration of the work that led to the development of a novel algorithm suitable for the automatic diagnosis of sleep apnea. A systematic literature review of the existing methods (approaches and algorithms) was performed before designing the algorithm. This review presented an overview of methods to diagnose sleep apnea using respiratory and oximetry signals. The review identified the research gaps with indicating the major concerns, challenges, benefits, and limitations of using respiratory and oximetry signals for the diagnosis of sleep apnea. This thesis examined the electroencephalogram (EEG) spectral powers resulting from apnea duration of varying length and reported the changes in the relative powers in EEG frequency bands before and at apnea termination. The study was carried out for the purpose of justifying the usability of EEG for the automatic diagnosis of sleep apnea. It investigated the spectral power changes in delta, theta, alpha, sigma, and beta frequency bands of EEG as a function of apnea duration from 375 events. The study revealed a significant reduction in EEG relative powers (the low frequency theta, alpha, and sigma powers) both before and at apnea termination. The findings from the EEG spectral analysis suggests that the application of EEG signal in sleep apnea diagnosis is not reliable due to the random variations in spectral powers as well as the major challenges associated with EEG acquisition and its processing. Due to the limitations associated with the EEG for an unattended home diagnosis of sleep apnea, the EEG signal was excluded from the automatic detection approach […]

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/149237