Cuffless blood pressure prediction from PPG using relevance vector machine

S. Shobitha, P. M. Amita, B. Niranjana Krupa, Gan Kok Beng

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Blood pressure is an important parameter in monitoring and non-invasive diagnosis of cardiovascular disease. It can be estimated by analyzing photoplethysmogram (PPG) signals. In this paper, features extracted from 156 PPG signals, obtained from 26 subjects under three different conditions, relaxed, exercise and rest, are used to predict both diastolicblood pressure (DBP) and systolicblood pressure (SBP) using relevance vector machine (RVM), a supervised machine learning algorithm. In addition, support vector machine (SVM) and random forest (RF) are used to predict SBP and DBP values, and hence validate the performance of RVM by comparing their results. Cohen's kappa score is used to compare the various regression models. From the results, we can infer that RVM performs best with average kappa scores of 0.99 for both SBP and DBP, with minimum computation time.

Original languageEnglish
Title of host publicationInternational Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages75-78
Number of pages4
Volume2018-January
ISBN (Electronic)9781538623619
DOIs
Publication statusPublished - 7 Feb 2018
Event2017 International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017 - Mysuru, India
Duration: 15 Dec 201716 Dec 2017

Other

Other2017 International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017
CountryIndia
CityMysuru
Period15/12/1716/12/17

Fingerprint

blood pressure
Blood pressure
predictions
Learning algorithms
Support vector machines
Learning systems
machine learning
Monitoring
physical exercise
regression analysis

Keywords

  • Cohen Kappa
  • Cuffless DBP
  • Cuffless SBP
  • PPG
  • RVM

ASJC Scopus subject areas

  • Radiation
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Shobitha, S., Amita, P. M., Krupa, B. N., & Kok Beng, G. (2018). Cuffless blood pressure prediction from PPG using relevance vector machine. In International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017 (Vol. 2018-January, pp. 75-78). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEECCOT.2017.8284610

Cuffless blood pressure prediction from PPG using relevance vector machine. / Shobitha, S.; Amita, P. M.; Krupa, B. Niranjana; Kok Beng, Gan.

International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 75-78.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shobitha, S, Amita, PM, Krupa, BN & Kok Beng, G 2018, Cuffless blood pressure prediction from PPG using relevance vector machine. in International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 75-78, 2017 International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017, Mysuru, India, 15/12/17. https://doi.org/10.1109/ICEECCOT.2017.8284610
Shobitha S, Amita PM, Krupa BN, Kok Beng G. Cuffless blood pressure prediction from PPG using relevance vector machine. In International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 75-78 https://doi.org/10.1109/ICEECCOT.2017.8284610
Shobitha, S. ; Amita, P. M. ; Krupa, B. Niranjana ; Kok Beng, Gan. / Cuffless blood pressure prediction from PPG using relevance vector machine. International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 75-78
@inproceedings{6d229d2abfb1488b8da3480e4310bf40,
title = "Cuffless blood pressure prediction from PPG using relevance vector machine",
abstract = "Blood pressure is an important parameter in monitoring and non-invasive diagnosis of cardiovascular disease. It can be estimated by analyzing photoplethysmogram (PPG) signals. In this paper, features extracted from 156 PPG signals, obtained from 26 subjects under three different conditions, relaxed, exercise and rest, are used to predict both diastolicblood pressure (DBP) and systolicblood pressure (SBP) using relevance vector machine (RVM), a supervised machine learning algorithm. In addition, support vector machine (SVM) and random forest (RF) are used to predict SBP and DBP values, and hence validate the performance of RVM by comparing their results. Cohen's kappa score is used to compare the various regression models. From the results, we can infer that RVM performs best with average kappa scores of 0.99 for both SBP and DBP, with minimum computation time.",
keywords = "Cohen Kappa, Cuffless DBP, Cuffless SBP, PPG, RVM",
author = "S. Shobitha and Amita, {P. M.} and Krupa, {B. Niranjana} and {Kok Beng}, Gan",
year = "2018",
month = "2",
day = "7",
doi = "10.1109/ICEECCOT.2017.8284610",
language = "English",
volume = "2018-January",
pages = "75--78",
booktitle = "International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Cuffless blood pressure prediction from PPG using relevance vector machine

AU - Shobitha, S.

AU - Amita, P. M.

AU - Krupa, B. Niranjana

AU - Kok Beng, Gan

PY - 2018/2/7

Y1 - 2018/2/7

N2 - Blood pressure is an important parameter in monitoring and non-invasive diagnosis of cardiovascular disease. It can be estimated by analyzing photoplethysmogram (PPG) signals. In this paper, features extracted from 156 PPG signals, obtained from 26 subjects under three different conditions, relaxed, exercise and rest, are used to predict both diastolicblood pressure (DBP) and systolicblood pressure (SBP) using relevance vector machine (RVM), a supervised machine learning algorithm. In addition, support vector machine (SVM) and random forest (RF) are used to predict SBP and DBP values, and hence validate the performance of RVM by comparing their results. Cohen's kappa score is used to compare the various regression models. From the results, we can infer that RVM performs best with average kappa scores of 0.99 for both SBP and DBP, with minimum computation time.

AB - Blood pressure is an important parameter in monitoring and non-invasive diagnosis of cardiovascular disease. It can be estimated by analyzing photoplethysmogram (PPG) signals. In this paper, features extracted from 156 PPG signals, obtained from 26 subjects under three different conditions, relaxed, exercise and rest, are used to predict both diastolicblood pressure (DBP) and systolicblood pressure (SBP) using relevance vector machine (RVM), a supervised machine learning algorithm. In addition, support vector machine (SVM) and random forest (RF) are used to predict SBP and DBP values, and hence validate the performance of RVM by comparing their results. Cohen's kappa score is used to compare the various regression models. From the results, we can infer that RVM performs best with average kappa scores of 0.99 for both SBP and DBP, with minimum computation time.

KW - Cohen Kappa

KW - Cuffless DBP

KW - Cuffless SBP

KW - PPG

KW - RVM

UR - http://www.scopus.com/inward/record.url?scp=85046534307&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85046534307&partnerID=8YFLogxK

U2 - 10.1109/ICEECCOT.2017.8284610

DO - 10.1109/ICEECCOT.2017.8284610

M3 - Conference contribution

VL - 2018-January

SP - 75

EP - 78

BT - International Conference on Electrical, Electronics, Communication Computer Technologies and Optimization Techniques, ICEECCOT 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -