Modeling of oxygen saturation and respiration for sleep apnea detection

Sleep apnea is a serious sleep disorder affecting millions of people. Combining different sensor data with the cardiorespiratory system models can greatly help to create a better sleep apnea detection system. Oxygen saturation and respiration signals are the most commonly used physiological signals...

Full description

Saved in:
Bibliographic Details
Published in2016 50th Asilomar Conference on Signals, Systems and Computers pp. 1636 - 1640
Main Authors Gutta, Sandeep, Qi Cheng
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2016
Subjects
Data models
Delay effects
Electrocardiography
Feature extraction
Mathematical model
Sleep apnea
Support vector machines
Online AccessGet full text
DOI10.1109/ACSSC.2016.7869657

Cover

More Information
Summary:Sleep apnea is a serious sleep disorder affecting millions of people. Combining different sensor data with the cardiorespiratory system models can greatly help to create a better sleep apnea detection system. Oxygen saturation and respiration signals are the most commonly used physiological signals for sleep apnea detection. In this paper, we propose a new mathematical model relating the oxygen saturation level to the respiration signal. The model parameters are estimated by solving a nonlinear least square optimization problem. Experimental results on real sleep apnea data show the accuracy of the proposed model.
DOI:10.1109/ACSSC.2016.7869657