A novel deep learning based automatic auscultatory method to measure blood pressure

Fei Pan, Peiyu He, Fei Chen, Jing Zhang, He Wang, D. Zheng

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background It is clinically important to develop innovative techniques that can accurately measure blood pressures (BP) automatically. Objectives This study aimed to present and evaluate a novel automatic BP measurement method based on deep learning method, and to confirm the effects on measured BPs of the position and contact pressure of stethoscope. Methods 30 healthy subjects were recruited. 9 BP measurements (from three different stethoscope contact pressures and three repeats) were performed on each subject. The convolutional neural network (CNN) was designed and trained to identify the Korotkoff sounds at a beat-by-beat level. Next, a mapping algorithm was developed to relate the identified Korotkoff beats to the corresponding cuff pressures for systolic and diastolic BP (SBP and DBP) determinations. Its performance was evaluated by investigating the effects of the position and contact pressure of stethoscope on measured BPs in comparison with reference manual auscultatory method. Results The overall measurement errors of the proposed method were 1.4 ± 2.4 mmHg for SBP and 3.3 ± 2.9 mmHg for DBP from all the measurements. In addition, the method demonstrated that there were small SBP differences between the 2 stethoscope positions, respectively at the 3 stethoscope contact pressures, and that DBP from the stethoscope under the cuff was significantly lower than that from outside the cuff by 2.0 mmHg (P < 0.01). Conclusion Our findings suggested that the deep learning based method was an effective technique to measure BP, and could be developed further to replace the current oscillometric based automatic blood pressure measurement method.
Original languageEnglish
Pages (from-to)71-78
Number of pages8
JournalInternational Journal of Medical Informatics
Volume128
Early online date29 Apr 2019
DOIs
Publication statusPublished - Aug 2019
Externally publishedYes

Fingerprint

Blood pressure
Pressure measurement
Measurement errors
Deep learning
Acoustic waves
Neural networks

Keywords

  • Blood pressure measurement
  • Convolutional neural network
  • Manual auscultatory method
  • Stethoscope position
  • Stethoscope contact pressure

Cite this

A novel deep learning based automatic auscultatory method to measure blood pressure. / Pan, Fei; He, Peiyu; Chen, Fei; Zhang, Jing; Wang, He; Zheng, D.

In: International Journal of Medical Informatics, Vol. 128, 08.2019, p. 71-78.

Research output: Contribution to journalArticle

Pan, Fei ; He, Peiyu ; Chen, Fei ; Zhang, Jing ; Wang, He ; Zheng, D. / A novel deep learning based automatic auscultatory method to measure blood pressure. In: International Journal of Medical Informatics. 2019 ; Vol. 128. pp. 71-78.
@article{f0bfaac01a094beabcc9b31a67a84aa8,
title = "A novel deep learning based automatic auscultatory method to measure blood pressure",
abstract = "Background It is clinically important to develop innovative techniques that can accurately measure blood pressures (BP) automatically. Objectives This study aimed to present and evaluate a novel automatic BP measurement method based on deep learning method, and to confirm the effects on measured BPs of the position and contact pressure of stethoscope. Methods 30 healthy subjects were recruited. 9 BP measurements (from three different stethoscope contact pressures and three repeats) were performed on each subject. The convolutional neural network (CNN) was designed and trained to identify the Korotkoff sounds at a beat-by-beat level. Next, a mapping algorithm was developed to relate the identified Korotkoff beats to the corresponding cuff pressures for systolic and diastolic BP (SBP and DBP) determinations. Its performance was evaluated by investigating the effects of the position and contact pressure of stethoscope on measured BPs in comparison with reference manual auscultatory method. Results The overall measurement errors of the proposed method were 1.4 ± 2.4 mmHg for SBP and 3.3 ± 2.9 mmHg for DBP from all the measurements. In addition, the method demonstrated that there were small SBP differences between the 2 stethoscope positions, respectively at the 3 stethoscope contact pressures, and that DBP from the stethoscope under the cuff was significantly lower than that from outside the cuff by 2.0 mmHg (P < 0.01). Conclusion Our findings suggested that the deep learning based method was an effective technique to measure BP, and could be developed further to replace the current oscillometric based automatic blood pressure measurement method.",
keywords = "Blood pressure measurement, Convolutional neural network, Manual auscultatory method, Stethoscope position, Stethoscope contact pressure",
author = "Fei Pan and Peiyu He and Fei Chen and Jing Zhang and He Wang and D. Zheng",
year = "2019",
month = "8",
doi = "10.1016/j.ijmedinf.2019.04.023",
language = "English",
volume = "128",
pages = "71--78",
journal = "International Journal of Medical Informatics",

}

TY - JOUR

T1 - A novel deep learning based automatic auscultatory method to measure blood pressure

AU - Pan, Fei

AU - He, Peiyu

AU - Chen, Fei

AU - Zhang, Jing

AU - Wang, He

AU - Zheng, D.

PY - 2019/8

Y1 - 2019/8

N2 - Background It is clinically important to develop innovative techniques that can accurately measure blood pressures (BP) automatically. Objectives This study aimed to present and evaluate a novel automatic BP measurement method based on deep learning method, and to confirm the effects on measured BPs of the position and contact pressure of stethoscope. Methods 30 healthy subjects were recruited. 9 BP measurements (from three different stethoscope contact pressures and three repeats) were performed on each subject. The convolutional neural network (CNN) was designed and trained to identify the Korotkoff sounds at a beat-by-beat level. Next, a mapping algorithm was developed to relate the identified Korotkoff beats to the corresponding cuff pressures for systolic and diastolic BP (SBP and DBP) determinations. Its performance was evaluated by investigating the effects of the position and contact pressure of stethoscope on measured BPs in comparison with reference manual auscultatory method. Results The overall measurement errors of the proposed method were 1.4 ± 2.4 mmHg for SBP and 3.3 ± 2.9 mmHg for DBP from all the measurements. In addition, the method demonstrated that there were small SBP differences between the 2 stethoscope positions, respectively at the 3 stethoscope contact pressures, and that DBP from the stethoscope under the cuff was significantly lower than that from outside the cuff by 2.0 mmHg (P < 0.01). Conclusion Our findings suggested that the deep learning based method was an effective technique to measure BP, and could be developed further to replace the current oscillometric based automatic blood pressure measurement method.

AB - Background It is clinically important to develop innovative techniques that can accurately measure blood pressures (BP) automatically. Objectives This study aimed to present and evaluate a novel automatic BP measurement method based on deep learning method, and to confirm the effects on measured BPs of the position and contact pressure of stethoscope. Methods 30 healthy subjects were recruited. 9 BP measurements (from three different stethoscope contact pressures and three repeats) were performed on each subject. The convolutional neural network (CNN) was designed and trained to identify the Korotkoff sounds at a beat-by-beat level. Next, a mapping algorithm was developed to relate the identified Korotkoff beats to the corresponding cuff pressures for systolic and diastolic BP (SBP and DBP) determinations. Its performance was evaluated by investigating the effects of the position and contact pressure of stethoscope on measured BPs in comparison with reference manual auscultatory method. Results The overall measurement errors of the proposed method were 1.4 ± 2.4 mmHg for SBP and 3.3 ± 2.9 mmHg for DBP from all the measurements. In addition, the method demonstrated that there were small SBP differences between the 2 stethoscope positions, respectively at the 3 stethoscope contact pressures, and that DBP from the stethoscope under the cuff was significantly lower than that from outside the cuff by 2.0 mmHg (P < 0.01). Conclusion Our findings suggested that the deep learning based method was an effective technique to measure BP, and could be developed further to replace the current oscillometric based automatic blood pressure measurement method.

KW - Blood pressure measurement

KW - Convolutional neural network

KW - Manual auscultatory method

KW - Stethoscope position

KW - Stethoscope contact pressure

UR - http://www.scopus.com/inward/record.url?eid=2-s2.0-85065531167&partnerID=MN8TOARS

U2 - 10.1016/j.ijmedinf.2019.04.023

DO - 10.1016/j.ijmedinf.2019.04.023

M3 - Article

VL - 128

SP - 71

EP - 78

JO - International Journal of Medical Informatics

JF - International Journal of Medical Informatics

ER -