Robust estimation of respiratory rate via ECG- and PPG-derived respiratory quality indices

Respiratory rate (RR) is one of the most informative indicators of a patient's health status. However, automated, non-invasive measurements of RR are insufficiently robust for use in clinical practice. A number of methods have been described in the literature to estimate RR from both photo-plet...

Full description

Saved in:
Bibliographic Details
Published in2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Vol. 2016; pp. 676 - 679
Main Authors Birrenkott, Drew A., Pimentel, Marco A. F., Watkinson, Peter J., Clifton, David A.
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.08.2016
Subjects
Adolescent
Adult
Aged
Algorithms
Child
Child, Preschool
Complexity theory
Correlation
Electrocardiography
Fourier Analysis
Frequency modulation
Humans
Infant
Intensive Care Units
IP networks
Middle Aged
MIMICs
Plethysmography
Respiratory Rate - physiology
Signal Processing, Computer-Assisted
Young Adult
Online AccessGet full text

Cover

More Information
Summary:Respiratory rate (RR) is one of the most informative indicators of a patient's health status. However, automated, non-invasive measurements of RR are insufficiently robust for use in clinical practice. A number of methods have been described in the literature to estimate RR from both photo-plethysmography (PPG) and electrocardiography (ECG) based on three physiological modulations of respiration: amplitude modulation (AM), frequency modulation (FM), and baseline wander (BW). However, the quality of the respiratory information acquired is highly patient-dependent and often too noisy to be used. We address this by proposing respiratory quality indices (RQIs) that quantify the quality of the respiratory signal that can be extracted from each modulation from both PPG and ECG waveforms. Signal quality indices (SQIs) detect artefact in the ECG and PPG, which is relatively straight-forward. RQIs have a different role: they quantify if an individual patient's physiology is modulating the sensor waveforms. We have designed four RQIs based on Fourier transform (RQI FFT ), autocorrelation (RQI AC ), autoregression (RQI AR ), and Hjorth complexity (RQI HC ). We validated the approach using PPG and ECG data in the CapnoBase and MIMIC II datasets. We conclude that the novel implementation of an RQI-based preprocessing step has the potential to improve substantially the performance of RR estimation algorithms.
ISSN:1557-170X
DOI:10.1109/EMBC.2016.7590792