BioWatch

A Noninvasive Wrist-Based Blood Pressure Monitor That Incorporates Training Techniques for Posture and Subject Variability

Simi Susan Thomas, Viswam Nathan, Chengzhi Zong, Karthikeyan Soundarapandian, Xiangrong Shi, Roozbeh Jafari

Research output: Contribution to journalArticleResearchpeer-review

34 Citations (Scopus)

Abstract

Noninvasive continuous blood pressure (BP) monitoring is not yet practically available for daily use. Challenges include making the system easily wearable, reducing noise level and improving accuracy. Variations in each person's physical characteristics, as well as the possibility of different postures, increase the complexity of continuous BP monitoring, especially outside the hospital. This study attempts to provide an easily wearable solution and proposes training to specific posture and individual for further improving accuracy. The wrist watch-based system we developed can measure electrocardiogram and photoplethysmogram. From these two signals, we measure pulse transit time through which we can obtain systolic and diastolic blood pressure through regression techniques. In this study, we investigate various functions to perform the training to obtain blood pressure. We validate measurements on different postures and subjects, and show the value of training the device to each posture and each subject. We observed that the average RMSE between the measured actual systolic BP and calculated systolic BP is between 7.83 to 9.37 mmHg across 11 subjects. The corresponding range of error for diastolic BP is 5.77 to 6.90 mmHg. The system can also automatically detect the arm position of the user using an accelerometer with an average accuracy of 98%, to make sure that the sensor is kept at the proper height. This system, called BioWatch, can potentially be a unified solution for heart rate, SPO2 and continuous BP monitoring.

Original languageEnglish
Article number7163275
Pages (from-to)1291-1300
Number of pages10
JournalIEEE Journal of Biomedical and Health Informatics
Volume20
Issue number5
DOIs
StatePublished - 1 Sep 2016

Fingerprint

Blood Pressure Monitors
Blood pressure
Wrist
Posture
Teaching
Blood Pressure
Monitoring
Watches
Electrocardiography
Accelerometers
Pulse Wave Analysis
Noise

Keywords

  • Blood pressure
  • electrocardiogram
  • photoplethysmogram
  • pulse transit time
  • wrist-based physiological monitoring

Cite this

Thomas, Simi Susan ; Nathan, Viswam ; Zong, Chengzhi ; Soundarapandian, Karthikeyan ; Shi, Xiangrong ; Jafari, Roozbeh. / BioWatch : A Noninvasive Wrist-Based Blood Pressure Monitor That Incorporates Training Techniques for Posture and Subject Variability. In: IEEE Journal of Biomedical and Health Informatics. 2016 ; Vol. 20, No. 5. pp. 1291-1300.
@article{d18907b8a8b54a1db00300c317707045,
title = "BioWatch: A Noninvasive Wrist-Based Blood Pressure Monitor That Incorporates Training Techniques for Posture and Subject Variability",
abstract = "Noninvasive continuous blood pressure (BP) monitoring is not yet practically available for daily use. Challenges include making the system easily wearable, reducing noise level and improving accuracy. Variations in each person's physical characteristics, as well as the possibility of different postures, increase the complexity of continuous BP monitoring, especially outside the hospital. This study attempts to provide an easily wearable solution and proposes training to specific posture and individual for further improving accuracy. The wrist watch-based system we developed can measure electrocardiogram and photoplethysmogram. From these two signals, we measure pulse transit time through which we can obtain systolic and diastolic blood pressure through regression techniques. In this study, we investigate various functions to perform the training to obtain blood pressure. We validate measurements on different postures and subjects, and show the value of training the device to each posture and each subject. We observed that the average RMSE between the measured actual systolic BP and calculated systolic BP is between 7.83 to 9.37 mmHg across 11 subjects. The corresponding range of error for diastolic BP is 5.77 to 6.90 mmHg. The system can also automatically detect the arm position of the user using an accelerometer with an average accuracy of 98{\%}, to make sure that the sensor is kept at the proper height. This system, called BioWatch, can potentially be a unified solution for heart rate, SPO2 and continuous BP monitoring.",
keywords = "Blood pressure, electrocardiogram, photoplethysmogram, pulse transit time, wrist-based physiological monitoring",
author = "Thomas, {Simi Susan} and Viswam Nathan and Chengzhi Zong and Karthikeyan Soundarapandian and Xiangrong Shi and Roozbeh Jafari",
year = "2016",
month = "9",
day = "1",
doi = "10.1109/JBHI.2015.2458779",
language = "English",
volume = "20",
pages = "1291--1300",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "5",

}

BioWatch : A Noninvasive Wrist-Based Blood Pressure Monitor That Incorporates Training Techniques for Posture and Subject Variability. / Thomas, Simi Susan; Nathan, Viswam; Zong, Chengzhi; Soundarapandian, Karthikeyan; Shi, Xiangrong; Jafari, Roozbeh.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 20, No. 5, 7163275, 01.09.2016, p. 1291-1300.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - BioWatch

T2 - A Noninvasive Wrist-Based Blood Pressure Monitor That Incorporates Training Techniques for Posture and Subject Variability

AU - Thomas, Simi Susan

AU - Nathan, Viswam

AU - Zong, Chengzhi

AU - Soundarapandian, Karthikeyan

AU - Shi, Xiangrong

AU - Jafari, Roozbeh

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Noninvasive continuous blood pressure (BP) monitoring is not yet practically available for daily use. Challenges include making the system easily wearable, reducing noise level and improving accuracy. Variations in each person's physical characteristics, as well as the possibility of different postures, increase the complexity of continuous BP monitoring, especially outside the hospital. This study attempts to provide an easily wearable solution and proposes training to specific posture and individual for further improving accuracy. The wrist watch-based system we developed can measure electrocardiogram and photoplethysmogram. From these two signals, we measure pulse transit time through which we can obtain systolic and diastolic blood pressure through regression techniques. In this study, we investigate various functions to perform the training to obtain blood pressure. We validate measurements on different postures and subjects, and show the value of training the device to each posture and each subject. We observed that the average RMSE between the measured actual systolic BP and calculated systolic BP is between 7.83 to 9.37 mmHg across 11 subjects. The corresponding range of error for diastolic BP is 5.77 to 6.90 mmHg. The system can also automatically detect the arm position of the user using an accelerometer with an average accuracy of 98%, to make sure that the sensor is kept at the proper height. This system, called BioWatch, can potentially be a unified solution for heart rate, SPO2 and continuous BP monitoring.

AB - Noninvasive continuous blood pressure (BP) monitoring is not yet practically available for daily use. Challenges include making the system easily wearable, reducing noise level and improving accuracy. Variations in each person's physical characteristics, as well as the possibility of different postures, increase the complexity of continuous BP monitoring, especially outside the hospital. This study attempts to provide an easily wearable solution and proposes training to specific posture and individual for further improving accuracy. The wrist watch-based system we developed can measure electrocardiogram and photoplethysmogram. From these two signals, we measure pulse transit time through which we can obtain systolic and diastolic blood pressure through regression techniques. In this study, we investigate various functions to perform the training to obtain blood pressure. We validate measurements on different postures and subjects, and show the value of training the device to each posture and each subject. We observed that the average RMSE between the measured actual systolic BP and calculated systolic BP is between 7.83 to 9.37 mmHg across 11 subjects. The corresponding range of error for diastolic BP is 5.77 to 6.90 mmHg. The system can also automatically detect the arm position of the user using an accelerometer with an average accuracy of 98%, to make sure that the sensor is kept at the proper height. This system, called BioWatch, can potentially be a unified solution for heart rate, SPO2 and continuous BP monitoring.

KW - Blood pressure

KW - electrocardiogram

KW - photoplethysmogram

KW - pulse transit time

KW - wrist-based physiological monitoring

UR - http://www.scopus.com/inward/record.url?scp=84987762658&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2015.2458779

DO - 10.1109/JBHI.2015.2458779

M3 - Article

VL - 20

SP - 1291

EP - 1300

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 5

M1 - 7163275

ER -