Detection of sleep apnoea in infants using ECG and oximetry signals

Author

Cohen, G. ; de Chazal, Philip

Author_Institution

MARCS Inst., Univ. of Western Sydney, Sydney, NSW, Australia

fYear

2013

fDate

22-25 Sept. 2013

Firstpage

859

Lastpage

862

Abstract

We present a study into the usage of combined nighttime electrocardiogram (ECG) and pulse oximetry recordings to automatically detect sleep apnoea in infants. The study draws upon the polysomnogram recordings found inside the National Collaborative Home Infant Monitoring Evaluation (CHIME) database. Viable ECG data, pulse oximetry data and scored respiratory information was extracted for 288 subjects from this dataset and time-aligned to 30s epochs. Features were extracted from both the ECG and the pulse-oximetry data and were then used alongside the scored respiratory information to train a classification model based on linear discriminants. Performance of the classifier was evaluated using a leave-one-out cross-validation scheme and an accuracy of 82.6% was achieved, with a specificity of 82. 6% and a sensitivity of 58.0%.

Keywords

electrocardiography; feature extraction; medical disorders; medical signal processing; oximetry; paediatrics; pneumodynamics; signal classification; sleep; ECG; National Collaborative Home Infant Monitoring Evaluation database; accuracy; classification model; electrocardiogram; feature extraction; infants; leave-one-out cross-validation scheme; linear discriminants; oximetry signals; polysomnogram recordings; pulse oximetry recordings; scored respiratory information; sensitivity; sleep apnoea; specificity; time 30 s; Abstracts; Electrocardiography; Estimation; Feature extraction; Monitoring; Pediatrics; Reliability;

fLanguage

English

Publisher

ieee

Conference_Titel

Computing in Cardiology Conference (CinC), 2013

Conference_Location

Zaragoza

ISSN

2325-8861

Print_ISBN

978-1-4799-0884-4

Type

conf

Filename

6713513