Impact of compressed sensing on clinically relevant metrics for ambulatory ECG monitoring

Author

Craven, D. ; McGinley, B. ; Kilmartin, L. ; Glavin, M. ; Jones, E.

Author_Institution

Coll. of Eng. & Inf., Nat. Univ. of Ireland Galway, Galway, Ireland

Volume

51

Issue

4

fYear

2015

fDate

2 19 2015

Firstpage

323

Lastpage

325

Abstract

Recent research has examined the combination of compressed sensing with over-complete dictionaries for the lossy compression of electrocardiogram (ECG) signals. The application of dictionary learning to automatically create the dictionary is described. A novel analysis of the reconstructed signals using a range of clinical metrics based around QRS feature extraction and heart rate variability is employed. Two methods for dictionary creation are proposed: patient specific and patient agnostic. A detailed comparison of each approach is described. Considering ambulatory ECG monitoring as an application, each methodology is analysed for a wide range of compression ratios.

Keywords

biomedical electronics; cardiovascular system; compressed sensing; electrocardiography; feature extraction; medical diagnostic computing; medical signal processing; patient monitoring; signal reconstruction; DL application; ECG monitoring CS impact; ECG monitoring compressed sensing impact; ECG signals; HRV-based clinical metrics; QRS feature extraction-based clinical metrics; ambulatory ECG monitoring; ambulatory electrocardiogram monitoring; automatic dictionary creation; clinically relevant ECG monitoring metrics; clinically relevant electrocardiogram monitoring metrics; compression ratio; dictionary creation methods; dictionary learning; electrocardiogram monitoring CS impact; electrocardiogram signals; heart rate variability-based clinical metrics; lossy compression; over-complete dictionaries; patient agnostic dictionary creation method analysis; patient specific dictionary creation method analysis; reconstructed ECG signal analysis; reconstructed electrocardiogram signal analysis;

fLanguage

English

Journal_Title

Electronics Letters

Publisher

iet

ISSN

0013-5194

Type

jour

DOI

10.1049/el.2014.4188

Filename

7042423