Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives
According to the WTO, there were 1.13 billion hypertension patients worldwide in 2015. The WTO encouraged people to check the blood pressure regularly because a large amount of patients do not have any symptoms. However, traditional cuff measurement results are not enough to represent the patient′s...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | Biosensors |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-6374/11/4/120 |
id |
doaj-5903335d8e3f48e4af9cb741541b8803 |
---|---|
record_format |
Article |
spelling |
doaj-5903335d8e3f48e4af9cb741541b88032021-04-13T23:00:37ZengMDPI AGBiosensors2079-63742021-04-011112012010.3390/bios11040120Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its DerivativesXiaoxiao Sun0Liang Zhou1Shendong Chang2Zhaohui Liu3Xi’an Institute of Optics and Precision Mechanics of CAS, Xi’an 710119, ChinaXi’an Institute of Optics and Precision Mechanics of CAS, Xi’an 710119, ChinaEAIT (Engineering, Architecture and Information Technology Department), University of Queensland, Brisbane 4072, AustraliaXi’an Institute of Optics and Precision Mechanics of CAS, Xi’an 710119, ChinaAccording to the WTO, there were 1.13 billion hypertension patients worldwide in 2015. The WTO encouraged people to check the blood pressure regularly because a large amount of patients do not have any symptoms. However, traditional cuff measurement results are not enough to represent the patient′s blood pressure status over a period of time. Therefore, there is an urgent need for portable, easy to operate, continuous measurement, and low-cost blood pressure measuring devices. In this paper, we adopted the convolutional neural network (CNN), based on the Hilbert–Huang Transform (HHT) method, to predict blood pressure (BP) risk level using photoplethysmography (PPG). Considering that the PPG′s first and second derivative signals are related to atherosclerosis and vascular elasticity, we created a dataset called PPG+; the images of PPG+ carry information on PPG and its derivatives. We built three classification experiments by collecting 582 data records (the length of each record is 10 s) from the Medical Information Mart for Intensive Care (MIMIC) database: NT (normotension) vs. HT (hypertension), NT vs. PHT (prehypertension), and (NT + PHT) vs. HT; the F1 scores of the PPG + experiments using AlexNet were 98.90%, 85.80%, and 93.54%, respectively. We found that, first, the dataset established by the HHT method performed well in the BP grade prediction experiment. Second, because the Hilbert spectra of the PPG are simple and periodic, AlexNet, which has only 8 layers, got better results. More layers instead increased the cost and difficulty of training.https://www.mdpi.com/2079-6374/11/4/120blood pressurephotoplethysmographyderivatives of PPGconvolutional neural networkensemble empirical mode decomposition |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xiaoxiao Sun Liang Zhou Shendong Chang Zhaohui Liu |
spellingShingle |
Xiaoxiao Sun Liang Zhou Shendong Chang Zhaohui Liu Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives Biosensors blood pressure photoplethysmography derivatives of PPG convolutional neural network ensemble empirical mode decomposition |
author_facet |
Xiaoxiao Sun Liang Zhou Shendong Chang Zhaohui Liu |
author_sort |
Xiaoxiao Sun |
title |
Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives |
title_short |
Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives |
title_full |
Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives |
title_fullStr |
Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives |
title_full_unstemmed |
Using CNN and HHT to Predict Blood Pressure Level Based on Photoplethysmography and Its Derivatives |
title_sort |
using cnn and hht to predict blood pressure level based on photoplethysmography and its derivatives |
publisher |
MDPI AG |
series |
Biosensors |
issn |
2079-6374 |
publishDate |
2021-04-01 |
description |
According to the WTO, there were 1.13 billion hypertension patients worldwide in 2015. The WTO encouraged people to check the blood pressure regularly because a large amount of patients do not have any symptoms. However, traditional cuff measurement results are not enough to represent the patient′s blood pressure status over a period of time. Therefore, there is an urgent need for portable, easy to operate, continuous measurement, and low-cost blood pressure measuring devices. In this paper, we adopted the convolutional neural network (CNN), based on the Hilbert–Huang Transform (HHT) method, to predict blood pressure (BP) risk level using photoplethysmography (PPG). Considering that the PPG′s first and second derivative signals are related to atherosclerosis and vascular elasticity, we created a dataset called PPG+; the images of PPG+ carry information on PPG and its derivatives. We built three classification experiments by collecting 582 data records (the length of each record is 10 s) from the Medical Information Mart for Intensive Care (MIMIC) database: NT (normotension) vs. HT (hypertension), NT vs. PHT (prehypertension), and (NT + PHT) vs. HT; the F1 scores of the PPG + experiments using AlexNet were 98.90%, 85.80%, and 93.54%, respectively. We found that, first, the dataset established by the HHT method performed well in the BP grade prediction experiment. Second, because the Hilbert spectra of the PPG are simple and periodic, AlexNet, which has only 8 layers, got better results. More layers instead increased the cost and difficulty of training. |
topic |
blood pressure photoplethysmography derivatives of PPG convolutional neural network ensemble empirical mode decomposition |
url |
https://www.mdpi.com/2079-6374/11/4/120 |
work_keys_str_mv |
AT xiaoxiaosun usingcnnandhhttopredictbloodpressurelevelbasedonphotoplethysmographyanditsderivatives AT liangzhou usingcnnandhhttopredictbloodpressurelevelbasedonphotoplethysmographyanditsderivatives AT shendongchang usingcnnandhhttopredictbloodpressurelevelbasedonphotoplethysmographyanditsderivatives AT zhaohuiliu usingcnnandhhttopredictbloodpressurelevelbasedonphotoplethysmographyanditsderivatives |
_version_ |
1721528451945463808 |