Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer

Fons Schipper; Ruud J.G. van Sloun; Angela Grassi; Jan Brouwer; Fokke van Meulen; Sebastiaan Overeem; Pedro Fonseca

doi:10.1088/1361-6579/ad2f5e

Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer

Fons Schipper (Corresponding author), Ruud J.G. van Sloun, Angela Grassi, Jan Brouwer, Fokke van Meulen, Sebastiaan Overeem, Pedro Fonseca

Research output: Contribution to journal › Article › Academic › peer-review

2 Citations (Scopus)

41 Downloads (Pure)

Abstract

Objective - Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assessment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.

Approach - We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximum a-posterior estimation and a Markov decision process to approach an optimal solution.

Main Results - The maximum a-posterior estimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heart rate measurement. Performance was held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.

Significance - The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

Original language	English
Article number	035009
Number of pages	12
Journal	Physiological Measurement
Volume	45
Issue number	3
Early online date	2 Mar 2024
DOIs	https://doi.org/10.1088/1361-6579/ad2f5e
Publication status	Published - 21 Mar 2024

Funding

This work has been performed in the IMPULS framework of the Eindhoven MedTech Innovation Center (e/MTIC, incorporating Eindhoven University of Technology, Philips Research, and Sleep Medicine Center Kempenhaeghe). The funders had no role in the study design, decision to publish, or preparation of the manuscript. Fons Schipper, Angela Grassi, Pedro Fonseca, and Jan Brouwer are employed by Philips Research. The employer had no influence on the study and on the decision to publish. Ruud van Sloun is employed by both Philips Research and by the Eindhoven University of Technology. The other authors declare no competing interests.

Funders	Funder number
Eindhoven University of Technology
Sleep Medicine Centre Kempenhaeghe

Keywords

Heart Rate
Monitoring, Physiologic
Sleep
Humans
Signal Processing, Computer-Assisted
Female
Male
Thorax
Accelerometry
heartrate
maximum a-posteriori estimation
accelerometer
Markov decision process
inter-beat interval
seismocardiography

Access to Document

10.1088/1361-6579/ad2f5e

pdfFinal published version, 1.46 MBLicence: CC BY

Cite this

@article{db1158ab3b444d0292334d9516a77bde,

title = "Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer",

abstract = "Objective - Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assessment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach - We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximum a-posterior estimation and a Markov decision process to approach an optimal solution. Main Results - The maximum a-posterior estimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95\% limits of agreement of -1.7 to +1.0 beats per minute for heart rate measurement. Performance was held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance - The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.",

keywords = "Heart Rate, Monitoring, Physiologic, Sleep, Humans, Signal Processing, Computer-Assisted, Female, Male, Thorax, Accelerometry, heartrate, maximum a-posteriori estimation, accelerometer, Markov decision process, inter-beat interval, seismocardiography",

author = "Fons Schipper and \{van Sloun\}, \{Ruud J.G.\} and Angela Grassi and Jan Brouwer and \{van Meulen\}, Fokke and Sebastiaan Overeem and Pedro Fonseca",

note = "Creative Commons Attribution license.",

year = "2024",

month = mar,

day = "21",

doi = "10.1088/1361-6579/ad2f5e",

language = "English",

volume = "45",

journal = "Physiological Measurement",

issn = "0967-3334",

publisher = "IOP Publishing Ltd.",

number = "3",

}

TY - JOUR

T1 - Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer

AU - Schipper, Fons

AU - van Sloun, Ruud J.G.

AU - Grassi, Angela

AU - Brouwer, Jan

AU - van Meulen, Fokke

AU - Overeem, Sebastiaan

AU - Fonseca, Pedro

N1 - Creative Commons Attribution license.

PY - 2024/3/21

Y1 - 2024/3/21

N2 - Objective - Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assessment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach - We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximum a-posterior estimation and a Markov decision process to approach an optimal solution. Main Results - The maximum a-posterior estimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heart rate measurement. Performance was held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance - The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

AB - Objective - Unobtrusive long-term monitoring of cardiac parameters is important in a wide variety of clinical applications, such as the assessment of acute illness severity and unobtrusive sleep monitoring. Here we determined the accuracy and robustness of heartbeat detection by an accelerometer worn on the chest.Approach - We performed overnight recordings in 147 individuals (69 female, 78 male) referred to two sleep centers. Two methods for heartbeat detection in the acceleration signal were compared: one previously described approach, based on local periodicity, and a novel extended method incorporating maximum a-posterior estimation and a Markov decision process to approach an optimal solution. Main Results - The maximum a-posterior estimation significantly improved performance, with a mean absolute error for the estimation of inter-beat intervals of only 3.5 ms, and 95% limits of agreement of -1.7 to +1.0 beats per minute for heart rate measurement. Performance was held during posture changes and was only weakly affected by the presence of sleep disorders and demographic factors.Significance - The new method may enable the use of a chest-worn accelerometer in a variety of applications such as ambulatory sleep staging and in-patient monitoring.

KW - Heart Rate

KW - Monitoring, Physiologic

KW - Sleep

KW - Humans

KW - Signal Processing, Computer-Assisted

KW - Female

KW - Male

KW - Thorax

KW - Accelerometry

KW - heartrate

KW - maximum a-posteriori estimation

KW - accelerometer

KW - Markov decision process

KW - inter-beat interval

KW - seismocardiography

UR - http://www.scopus.com/inward/record.url?scp=85188519809&partnerID=8YFLogxK

U2 - 10.1088/1361-6579/ad2f5e

DO - 10.1088/1361-6579/ad2f5e

M3 - Article

C2 - 38430565

SN - 0967-3334

VL - 45

JO - Physiological Measurement

JF - Physiological Measurement

IS - 3

M1 - 035009

ER -

Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Sleep Medicine

Cite this

Maximum a-posteriori detection of heartbeats from a chest-worn accelerometer

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Research areas

Sleep Medicine

Cite this