Non-invasive cuff-less blood pressure machine learning algorithm using photoplethysmography and prior physiological data

Sen Yang, Stephen P. Morgan, Siu Yeung Cho, Ricardo Correia, Long Wen, Yaping Zhang

Research output: Journal PublicationArticlepeer-review

4 Citations (Scopus)

Abstract

Conventional blood pressure (BP) measurement methods have a number of drawbacks such as being invasive, cuff-based or requiring manual operation. Many studies are focussed on emerging methods of noninvasive, cuff-less and continuous BP measurement, and using only photoplethysmography to estimate BP has become popular. Although it is well known that physiological characteristics of the subject are important in BP estimation, this has not been widely explored. This article presents a novel method which adopts photoplethysmography and prior knowledge of a subject's physiological features to estimate DBP and SBP. Features extracted from a fingertip photoplethysmography signal and prior knowledge of a subject's physiological characteristics, such as gender, age, height, weight and BMI is used to estimate BP using three different machine learning models: Artificial neural networks, support vector machine and least absolute shrinkage and selection operator regression. The accuracy of BP estimation obtained when prior knowledge of the physiological characteristics are incorporated into the model is superior to those which do not take the physiological characteristics into consideration. In this study, the best performing algorithm is an artificial neural network which obtains a mean absolute error and SD of 4.74 ± 5.55 mm Hg for DBP and 9.18 ± 12.57 mm Hg for SBP compared to 6.61 ± 8.04 mm Hg for DBP and 11.12 ± 14.20 mm Hg for SBP without prior knowledge. The inclusion of prior knowledge of the physiological characteristics can improve the accuracy of BP estimation using machine learning methods, and the incorporation of more physiological characteristics enhances the accuracy of the BP estimation.

Original languageEnglish
Pages (from-to)312-320
Number of pages9
JournalBlood Pressure Monitoring
Volume26
Issue number4
DOIs
Publication statusPublished - Aug 2021

Keywords

  • blood pressure
  • cuff-less
  • photoplethysmography
  • physiology
  • wearable technology

ASJC Scopus subject areas

  • Internal Medicine
  • Cardiology and Cardiovascular Medicine
  • Assessment and Diagnosis
  • Advanced and Specialised Nursing

Fingerprint

Dive into the research topics of 'Non-invasive cuff-less blood pressure machine learning algorithm using photoplethysmography and prior physiological data'. Together they form a unique fingerprint.

Cite this