Estimation of respiratory rate from motion contaminated photoplethysmography signals incorporating accelerometry.

Delaram Jarchi,Alex Casson,David A. Clifton,Lionel Tarassenko,Marco Pimentel,Peter Charlton

doi:10.1049/htl.2018.5019

Delaram Jarchi, Alex Casson + Show 4 more

Open Access

https://doi.org/10.1049/htl.2018.5019

Copy DOI

Abstract

Estimation of respiratory rate (RR) from photoplethysmography (PPG) signals has important applications in the healthcare sector, from assisting doctors onwards to monitoring patients in their own homes. The problem is still very challenging, particularly during the motion for large segments of data, where results from different methods often do not agree. The authors aim to propose a new technique which performs motion reduction from PPG signals with the help of simultaneous acceleration signals where the PPG and accelerometer sensors need to be embedded in the same sensor unit. This method also reconstructs motion corrupted PPG signals in the Hilbert domain. An auto-regressive (AR) based technique has been used to estimate the RR from reconstructed PPGs. The proposed method has provided promising results for the estimation of RRs and their variations from PPG signals corrupted with motion artefact. The proposed platform is able to contribute to continuous in-hospital and home-based monitoring of patients using PPG signals under various conditions such as rest and motion states.

Highlights

Respiratory rate (RR) is a key physiological measurement which can be combined with other vital signs to derive patients’ early warning scores [1]
Reduction of motion artefact and PPG reconstruction: To reduce motion artefact of the PPG signals, normalised least mean squares (NLMS) filters as explained in Section 2.1 have been applied to the two PPG signals, using each of the three accelerometer axis signals
The time–frequency spectra of raw PPG signals affected by motion artefact is shown in Figs. 2a and 3a, using the short time Fourier transform (STFT) with window length 6 s with an overlap of 2 s

Summary

Introduction

Respiratory rate (RR) is a key physiological measurement which can be combined with other vital signs to derive patients’ early warning scores [1]. Common practice for monitoring patients’ RR is for nurses to count the number breaths in a minute. This is not always accurate or repeatable [7] and is done infrequently as part of 4 h manual observations. To provide more regular and accurate measurements, continuous monitoring of patients’ vital signs is possible through the use of non-obtrusive and light-weight wearable sensors. These signals are often corrupted by motion artefact, so robust signal processing and machine learning techniques are required to obtain reliable estimates. The quality of the PPG data from wearable sensors (wrist-type PPG sensor or pulse oximeter with a finger/ear probe) is higher than video-based systems, so in this research wrist-type PPG sensor is used to derive RR

Methods

Results

Conclusion