Marco A F Pimentel1, Alistair E W Johnson2, Peter H Charlton3, Drew Birrenkott4, Peter J Watkinson5, Lionel Tarassenko4, David A Clifton4. 1. Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, U.K. 2. Institute for Medical Engineering & ScienceMassachusetts Institute of Technology. 3. Guy's & St. Thomas' Hospital, and King's College. 4. Department of Engineering ScienceInstitute of Biomedical EngineeringUniversity of Oxford. 5. Oxford University Hospitals NHS Trust.
Abstract
GOAL: Current methods for estimating respiratory rate (RR) from the photoplethysmogram (PPG) typically fail to distinguish between periods of high- and low-quality input data, and fail to perform well on independent "validation" datasets. The lack of robustness of existing methods directly results in a lack of penetration of such systems into clinical practice. The present work proposes an alternative method to improve the robustness of the estimation of RR from the PPG. METHODS: The proposed algorithm is based on the use of multiple autoregressive models of different orders for determining the dominant respiratory frequency in the three respiratory-induced variations (frequency, amplitude, and intensity) derived from the PPG. The algorithm was tested on two different datasets comprising 95 eight-minute PPG recordings (in total) acquired from both children and adults in different clinical settings, and its performance using two window sizes (32 and 64 seconds) was compared with that of existing methods in the literature. RESULTS: The proposed method achieved comparable accuracy to existing methods in the literature, with mean absolute errors (median, 25[Formula: see text]-75[Formula: see text] percentiles for a window size of 32 seconds) of 1.5 (0.3-3.3) and 4.0 (1.8-5.5) breaths per minute (for each dataset respectively), whilst providing RR estimates for a greater proportion of windows (over 90% of the input data are kept). CONCLUSION: Increased robustness of RR estimation by the proposed method was demonstrated. SIGNIFICANCE: This work demonstrates that the use of large publicly available datasets is essential for improving the robustness of wearable-monitoring algorithms for use in clinical practice.
GOAL: Current methods for estimating respiratory rate (RR) from the photoplethysmogram (PPG) typically fail to distinguish between periods of high- and low-quality input data, and fail to perform well on independent "validation" datasets. The lack of robustness of existing methods directly results in a lack of penetration of such systems into clinical practice. The present work proposes an alternative method to improve the robustness of the estimation of RR from the PPG. METHODS: The proposed algorithm is based on the use of multiple autoregressive models of different orders for determining the dominant respiratory frequency in the three respiratory-induced variations (frequency, amplitude, and intensity) derived from the PPG. The algorithm was tested on two different datasets comprising 95 eight-minute PPG recordings (in total) acquired from both children and adults in different clinical settings, and its performance using two window sizes (32 and 64 seconds) was compared with that of existing methods in the literature. RESULTS: The proposed method achieved comparable accuracy to existing methods in the literature, with mean absolute errors (median, 25[Formula: see text]-75[Formula: see text] percentiles for a window size of 32 seconds) of 1.5 (0.3-3.3) and 4.0 (1.8-5.5) breaths per minute (for each dataset respectively), whilst providing RR estimates for a greater proportion of windows (over 90% of the input data are kept). CONCLUSION: Increased robustness of RR estimation by the proposed method was demonstrated. SIGNIFICANCE: This work demonstrates that the use of large publicly available datasets is essential for improving the robustness of wearable-monitoring algorithms for use in clinical practice.
Authors: Christina Orphanidou; Timothy Bonnici; Peter Charlton; David Clifton; David Vallance; Lionel Tarassenko Journal: IEEE J Biomed Health Inform Date: 2014-07-23 Impact factor: 5.772
Authors: Lionel Tarassenko; David A Clifton; Michael R Pinsky; Marilyn T Hravnak; John R Woods; Peter J Watkinson Journal: Resuscitation Date: 2011-03-23 Impact factor: 6.251
Authors: Carlos A Alvarez; Christopher A Clark; Song Zhang; Ethan A Halm; John J Shannon; Carlos E Girod; Lauren Cooper; Ruben Amarasingham Journal: BMC Med Inform Decis Mak Date: 2013-02-27 Impact factor: 2.796
Authors: Peter H Charlton; Panicos A Kyriaco; Jonathan Mant; Vaidotas Marozas; Phil Chowienczyk; Jordi Alastruey Journal: Proc IEEE Inst Electr Electron Eng Date: 2022-03-11 Impact factor: 10.961
Authors: Delaram Jarchi; Peter Charlton; Marco Pimentel; Alex Casson; Lionel Tarassenko; David A Clifton Journal: Healthc Technol Lett Date: 2019-02-21
Authors: Peter H Charlton; Drew A Birrenkott; Timothy Bonnici; Marco A F Pimentel; Alistair E W Johnson; Jordi Alastruey; Lionel Tarassenko; Peter J Watkinson; Richard Beale; David A Clifton Journal: IEEE Rev Biomed Eng Date: 2017-10-24