Accelerometry-based estimation of respiratory rate for post-intensive care patient monitoring

Journal article

This paper evaluates the use of accelerometers for continuous monitoring of respiratory rate (RR), which is an important vital sign in post-intensive care patients or those inside the intensive care unit (ICU). The respiratory rate can be estimated from accelerometer and photoplethysmography (PPG) signals for patients following ICU discharge. Due to sensor faults, sensor detachment, and various artifacts arising from motion, RR estimates derived from accelerometry and PPG may not be sufficiently reliable for use with existing algorithms. This paper described a case study of 10 selected patients, for which fewer RR estimates have been obtained from PPG signals in comparison to those from accelerometry. We describe an algorithm for which we show a maximum mean absolute error between estimates derived from PPG and accelerometer of 2.56 breaths/min. Our results obtained using the 10 selected patients are highly promising for estimation of RR from accelerometers, where significant agreements have been observed with the PPG-based RR estimates in many segments and across various patients. We present this research as a step towards producing reliable RR monitoring systems using low-cost mobile accelerometers for monitoring patients inside the ICU or on the ward (post-ICU).

Authors: Jarchi, D; Rodgers, S-J; Tarassenko, L; Clifton, DA

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Institute of Electrical and Electronics Engineers
• Journal: IEEE Sensors Journal
• Volume: 18
• Issue: 12
• Pages: 4981-4989
• Publication date: 2018-04-19
• Acceptance date: 2018-04-05
• DOI: 10.1109/JSEN.2018.2828599
• EISSN: 2379-9153
• ISSN: 1530-437X
• Keywords: photo-plethysmography (PPG); adaptive line enhancer (ALE); respiratory rate (RR); accelerometer; auto-regressive (AR)