A Movement-Artefact-Free Heart-Rate Prediction System

Maarten Thoonen; Peter H. Veltink; F.R. Halfwerk; Robby van Delden; Ying Wang

doi:10.22489/CinC.2022.190

A Movement-Artefact-Free Heart-Rate Prediction System

Maarten Thoonen, Peter H. Veltink, F.R. Halfwerk, Robby van Delden, Ying Wang^*

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

143 Downloads (Pure)

Abstract

Continuous automatic heart rate (HR) monitoring plays a crucial role in timely intervention for postoperative patients. However, for effective alarm management, patients’ activities of daily living need to be considered as they influence HR. This explorative study aimed to develop a heartrate prediction system while performing six activities. An experiment with fourteen participants was conducted to gather data to build a system. This system consisted of a support-vector machine classifier for activity recognition and a k-Nearest Neighbors regressor for HR prediction.
The R-squared (a goodness-of-fit measure) of the HR predictor is 79% on average. Given the heterogeneity of different populations, the system will be further tested and developed using patient datasets in future towards linical practice applications.

Original language	English
Number of pages	4
DOIs	https://doi.org/10.22489/CinC.2022.190
Publication status	Published - 13 Oct 2022
Event	49th Computing in Cardiology Conference, CinC 2022 - Tampere, Finland Duration: 4 Sept 2022 → 7 Sept 2022 Conference number: 49 https://cinc.org/

Conference

Conference	49th Computing in Cardiology Conference, CinC 2022
Abbreviated title	CinC 2022
Country/Territory	Finland
City	Tampere
Period	4/09/22 → 7/09/22
Internet address	https://cinc.org/

Keywords

Vital signs
heart rate monitoring
Human Activity Recognition
heart rate prediction
Accelerometer

Access to Document

10.22489/CinC.2022.190

190_PreprintAccepted author version, 210 KB
CinC2022-190Final published version, 229 KB

Cite this

@conference{97a61ce67ab84a48bc1bd06a57d94aff,

title = "A Movement-Artefact-Free Heart-Rate Prediction System",

abstract = "Continuous automatic heart rate (HR) monitoring plays a crucial role in timely intervention for postoperative patients. However, for effective alarm management, patients{\textquoteright} activities of daily living need to be considered as they influence HR. This explorative study aimed to develop a heartrate prediction system while performing six activities. An experiment with fourteen participants was conducted to gather data to build a system. This system consisted of a support-vector machine classifier for activity recognition and a k-Nearest Neighbors regressor for HR prediction.The R-squared (a goodness-of-fit measure) of the HR predictor is 79% on average. Given the heterogeneity of different populations, the system will be further tested and developed using patient datasets in future towards linical practice applications.",

keywords = "Vital signs, heart rate monitoring, Human Activity Recognition, heart rate prediction, Accelerometer",

author = "Maarten Thoonen and Veltink, {Peter H.} and F.R. Halfwerk and {van Delden}, Robby and Ying Wang",

year = "2022",

month = oct,

day = "13",

doi = "10.22489/CinC.2022.190",

language = "English",

note = "49th Computing in Cardiology Conference, CinC 2022, CinC 2022 ; Conference date: 04-09-2022 Through 07-09-2022",

url = "https://cinc.org/",

}

TY - CONF

T1 - A Movement-Artefact-Free Heart-Rate Prediction System

AU - Thoonen, Maarten

AU - Veltink, Peter H.

AU - Halfwerk, F.R.

AU - van Delden, Robby

AU - Wang, Ying

N1 - Conference code: 49

PY - 2022/10/13

Y1 - 2022/10/13

N2 - Continuous automatic heart rate (HR) monitoring plays a crucial role in timely intervention for postoperative patients. However, for effective alarm management, patients’ activities of daily living need to be considered as they influence HR. This explorative study aimed to develop a heartrate prediction system while performing six activities. An experiment with fourteen participants was conducted to gather data to build a system. This system consisted of a support-vector machine classifier for activity recognition and a k-Nearest Neighbors regressor for HR prediction.The R-squared (a goodness-of-fit measure) of the HR predictor is 79% on average. Given the heterogeneity of different populations, the system will be further tested and developed using patient datasets in future towards linical practice applications.

AB - Continuous automatic heart rate (HR) monitoring plays a crucial role in timely intervention for postoperative patients. However, for effective alarm management, patients’ activities of daily living need to be considered as they influence HR. This explorative study aimed to develop a heartrate prediction system while performing six activities. An experiment with fourteen participants was conducted to gather data to build a system. This system consisted of a support-vector machine classifier for activity recognition and a k-Nearest Neighbors regressor for HR prediction.The R-squared (a goodness-of-fit measure) of the HR predictor is 79% on average. Given the heterogeneity of different populations, the system will be further tested and developed using patient datasets in future towards linical practice applications.

KW - Vital signs

KW - heart rate monitoring

KW - Human Activity Recognition

KW - heart rate prediction

KW - Accelerometer

UR - https://cinc.org/2022/Program/accepted/190.html

UR - https://cinc.org/final_program_papers_2022/

U2 - 10.22489/CinC.2022.190

DO - 10.22489/CinC.2022.190

M3 - Paper

T2 - 49th Computing in Cardiology Conference, CinC 2022

Y2 - 4 September 2022 through 7 September 2022

ER -

A Movement-Artefact-Free Heart-Rate Prediction System

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this