Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset
Applying machine learning techniques to electrocardiography and photoplethysmography signals and their multivariate-derived waveforms is an ongoing effort to estimate non-occlusive blood pressure. Unfortunately, real ambulatory electrocardiography and photoplethysmography waveforms are inevitably af...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
AIMS Press
2023-01-01
|
Series: | Mathematical Biosciences and Engineering |
Subjects: | |
Online Access: | https://www.aimspress.com/article/doi/10.3934/mbe.2023045?viewType=HTML |
_version_ | 1797985163710300160 |
---|---|
author | Mark Kei Fong Wong Hao Hei Si Zhou Lim Eddie Yin-Kwee Ng |
author_facet | Mark Kei Fong Wong Hao Hei Si Zhou Lim Eddie Yin-Kwee Ng |
author_sort | Mark Kei Fong Wong |
collection | DOAJ |
description | Applying machine learning techniques to electrocardiography and photoplethysmography signals and their multivariate-derived waveforms is an ongoing effort to estimate non-occlusive blood pressure. Unfortunately, real ambulatory electrocardiography and photoplethysmography waveforms are inevitably affected by motion and noise artifacts, so established machine learning architectures perform poorly when trained on data of the Multiparameter Intelligent Monitoring in Intensive Care II type, a publicly available ICU database. Our study addresses this problem by applying four well-established machine learning methods, i.e., random forest regression, support vector regression, Adaboost regression and artificial neural networks, to a small, self-sampled electrocardiography-photoplethysmography dataset (n = 54) to improve the robustness of machine learning to real-world BP estimates. We evaluated the performance using a selection of optimal feature morphologies of waveforms by using pulse arrival time, morphological and frequency photoplethysmography parameters and heart rate variability as characterization data. On the basis of the root mean square error and mean absolute error, our study showed that support vector regression gave the best performance for blood pressure estimation from noisy data, achieving an mean absolute error of 6.97 mmHg, which meets the level C criteria set by the British Hypertension Society. We demonstrate that ambulatory electrocardiography- photoplethysmography signals acquired by mobile discrete devices can be used to estimate blood pressure. |
first_indexed | 2024-04-11T07:14:18Z |
format | Article |
id | doaj.art-2681433327d847dfad23cc85c11592b4 |
institution | Directory Open Access Journal |
issn | 1551-0018 |
language | English |
last_indexed | 2024-04-11T07:14:18Z |
publishDate | 2023-01-01 |
publisher | AIMS Press |
record_format | Article |
series | Mathematical Biosciences and Engineering |
spelling | doaj.art-2681433327d847dfad23cc85c11592b42022-12-22T04:38:04ZengAIMS PressMathematical Biosciences and Engineering1551-00182023-01-0120197599710.3934/mbe.2023045Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram datasetMark Kei Fong Wong0Hao Hei1Si Zhou Lim2Eddie Yin-Kwee Ng31. School of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, Singapore2. School of Electrical and Electronic Engineering, Nanyang Technological University, 639798, Singapore1. School of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, Singapore1. School of Mechanical and Aerospace Engineering, Nanyang Technological University, 639798, SingaporeApplying machine learning techniques to electrocardiography and photoplethysmography signals and their multivariate-derived waveforms is an ongoing effort to estimate non-occlusive blood pressure. Unfortunately, real ambulatory electrocardiography and photoplethysmography waveforms are inevitably affected by motion and noise artifacts, so established machine learning architectures perform poorly when trained on data of the Multiparameter Intelligent Monitoring in Intensive Care II type, a publicly available ICU database. Our study addresses this problem by applying four well-established machine learning methods, i.e., random forest regression, support vector regression, Adaboost regression and artificial neural networks, to a small, self-sampled electrocardiography-photoplethysmography dataset (n = 54) to improve the robustness of machine learning to real-world BP estimates. We evaluated the performance using a selection of optimal feature morphologies of waveforms by using pulse arrival time, morphological and frequency photoplethysmography parameters and heart rate variability as characterization data. On the basis of the root mean square error and mean absolute error, our study showed that support vector regression gave the best performance for blood pressure estimation from noisy data, achieving an mean absolute error of 6.97 mmHg, which meets the level C criteria set by the British Hypertension Society. We demonstrate that ambulatory electrocardiography- photoplethysmography signals acquired by mobile discrete devices can be used to estimate blood pressure.https://www.aimspress.com/article/doi/10.3934/mbe.2023045?viewType=HTMLnon-occluding blood pressurenoisy datamachine learningphotoplethysmographyelectrocardiography |
spellingShingle | Mark Kei Fong Wong Hao Hei Si Zhou Lim Eddie Yin-Kwee Ng Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset Mathematical Biosciences and Engineering non-occluding blood pressure noisy data machine learning photoplethysmography electrocardiography |
title | Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset |
title_full | Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset |
title_fullStr | Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset |
title_full_unstemmed | Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset |
title_short | Applied machine learning for blood pressure estimation using a small, real-world electrocardiogram and photoplethysmogram dataset |
title_sort | applied machine learning for blood pressure estimation using a small real world electrocardiogram and photoplethysmogram dataset |
topic | non-occluding blood pressure noisy data machine learning photoplethysmography electrocardiography |
url | https://www.aimspress.com/article/doi/10.3934/mbe.2023045?viewType=HTML |
work_keys_str_mv | AT markkeifongwong appliedmachinelearningforbloodpressureestimationusingasmallrealworldelectrocardiogramandphotoplethysmogramdataset AT haohei appliedmachinelearningforbloodpressureestimationusingasmallrealworldelectrocardiogramandphotoplethysmogramdataset AT sizhoulim appliedmachinelearningforbloodpressureestimationusingasmallrealworldelectrocardiogramandphotoplethysmogramdataset AT eddieyinkweeng appliedmachinelearningforbloodpressureestimationusingasmallrealworldelectrocardiogramandphotoplethysmogramdataset |