On improvement of detection of Obstructive Sleep Apnea by partial least square-based extraction of dynamic features

L M Sepulveda-Cano; C M Travieso-Gonzalez; J I Godino-Llorente; G Castellanos-Dominguez

doi:10.1109/IEMBS.2010.5627710

On improvement of detection of Obstructive Sleep Apnea by partial least square-based extraction of dynamic features

Annu Int Conf IEEE Eng Med Biol Soc. 2010:2010:6321-4. doi: 10.1109/IEMBS.2010.5627710.

Authors

L M Sepulveda-Cano¹, C M Travieso-Gonzalez, J I Godino-Llorente, G Castellanos-Dominguez

Affiliation

¹ Control and Digital Signal Processing Group, Universidad Nacional de Colombia, sede Manizales, Colombia. lmsepulvedac@unal.edu.co

PMID: 21097169
DOI: 10.1109/IEMBS.2010.5627710

Abstract

This paper presents a methodology for Obstructive Sleep Apnea (OSA) detection based on the HRV analysis, where as a measure of relevance PLS is used. Besides, two different combining approaches for the selection of the best set of contours are studied. Attained results can be oriented in research focused on finding alternative methods minimizing the HRV-derived parameters used for OSA diagnosing, with a diagnostic accuracy comparable to a polysomnogram. For two classes (normal, apnea) the results for PLS are: specificity 90%, sensibility 91% and accuracy 93.56%.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Electrocardiography / methods
Heart Rate / physiology*
Least-Squares Analysis
Signal Processing, Computer-Assisted*
Sleep Apnea, Obstructive / diagnosis*
Sleep Apnea, Obstructive / physiopathology