Page 1 |
Save page Remove page | Previous | 1 of 144 | Next |
|
small (250x250 max)
medium (500x500 max)
Large (1000x1000 max)
Extra Large
large ( > 500x500)
Full Resolution
All (PDF)
|
This page
All
|
AUTOMATIC STAGING OF SLEEP USING ONLY TWO ELECTRODES ON THE FOREHEAD by Djordje Popovic ________________________________________________________________________ A Dissertation Presented to the FACULTY OF THE USC GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (BIOMEDICAL ENGINEERING) December 2011 Copyright 2011 Djordje Popovic
Object Description
Title | Automatic staging of sleep using only two electrodes on the forehead |
Author | Popovic, Djordje |
Author email | popovic@usc.edu;dpopovic@b-alert.com |
Degree | Doctor of Philosophy |
Document type | Dissertation |
Degree program | Biomedical Engineering |
School | Viterbi School of Engineering |
Date defended/completed | 2011-07-26 |
Date submitted | 2011-10-12 |
Date approved | 2011-10-14 |
Restricted until | 2011-10-14 |
Date published | 2011-10-14 |
Advisor (committee chair) | Khoo, Michael C.K. |
Advisor (committee member) |
Westbrook, Philip R. Keens, Thomas G. Singh, Manbir Davoodi, Rahman |
Abstract | Multichannel polysomnography (PSG) is ill-suited for applications such as epidemiological studies, large-scale clinical trials, or sleep monitoring in domiciliary settings. An ideal alternative should be an unobtrusive, inexpensive and self-applicable device accompanied with validated algorithms for rapid processing of high volumes of data. This dissertation presents an algorithm for automatic sleep staging that operates on a single channel with only two electrodes on the forehead (Fp1 - Fp2). An advantage of such an approach is that adhesive disposable electrodes can be easily applied to the forehead by patients after minimal training. ❧ The algorithm, which combined spectral decomposition of the input signal with a decision tree, was developed on sleep records of 10 healthy sleep-deprived subjects, and validated on records of 11 sleep-deprived and 18 well-rested subjects. Epoch-by-epoch agreement between the automatic and referent scoring in the validation groups (81.8% for sleep-deprived and 80.8% for well-rested subjects) was substantial, and compared favorably to the inter-rater agreement and performance of other similar algorithms. Most misclassifications occurred during wake/sleep transitions because of the complete absence of alpha rhythm in the frontopolar EEG and significant between-subject variability of the surrogate feature used instead for the wake/sleep differentiation. Individualization of the pertinent threshold in the decision tree substantially improved the accuracy of the wake/sleep separation. In conclusion, the dissertation established the face and convergent validity of automatic sleep scoring from a single channel recorded with only two electrodes on the forehead, but additional studies on elderly subjects and clinical populations are warranted before the algorithm is introduced into clinical practice. |
Keyword | sleep; electroencephalography; EEG; staging; automatic staging |
Language | English |
Part of collection | University of Southern California dissertations and theses |
Publisher (of the original version) | University of Southern California |
Place of publication (of the original version) | Los Angeles, California |
Publisher (of the digital version) | University of Southern California. Libraries |
Provenance | Electronically uploaded by the author |
Type | texts |
Legacy record ID | usctheses-m |
Contributing entity | University of Southern California |
Rights | Popovic, Djordje |
Physical access | The author retains rights to his/her dissertation, thesis or other graduate work according to U.S. copyright law. Electronic access is being provided by the USC Libraries in agreement with the author, as the original true and official version of the work, but does not grant the reader permission to use the work if the desired use is covered by copyright. It is the author, as rights holder, who must provide use permission if such use is covered by copyright. The original signature page accompanying the original submission of the work to the USC Libraries is retained by the USC Libraries and a copy of it may be obtained by authorized requesters contacting the repository e-mail address given. |
Repository name | University of Southern California Digital Library |
Repository address | USC Digital Library, University of Southern California, University Park Campus MC 7002, 106 University Village, Los Angeles, California 90089-7002, USA |
Repository email | cisadmin@lib.usc.edu |
Archival file | uscthesesreloadpub_Volume71/etd-PopovicDjo-335-0.pdf |
Description
Title | Page 1 |
Contributing entity | University of Southern California |
Repository email | cisadmin@lib.usc.edu |
Full text | AUTOMATIC STAGING OF SLEEP USING ONLY TWO ELECTRODES ON THE FOREHEAD by Djordje Popovic ________________________________________________________________________ A Dissertation Presented to the FACULTY OF THE USC GRADUATE SCHOOL UNIVERSITY OF SOUTHERN CALIFORNIA In Partial Fulfillment of the Requirements for the Degree DOCTOR OF PHILOSOPHY (BIOMEDICAL ENGINEERING) December 2011 Copyright 2011 Djordje Popovic |