Deep learning approaches for continuous blood pressure estimation from photoplethysmography signal

Q4 Engineering
R. Vanithamani, S. Sri Jayabharathi, S. Pavithra, E. Smily Jeya Jothi
{"title":"Deep learning approaches for continuous blood pressure estimation from photoplethysmography signal","authors":"R. Vanithamani,&nbsp;S. Sri Jayabharathi,&nbsp;S. Pavithra,&nbsp;E. Smily Jeya Jothi","doi":"10.1016/j.measen.2025.101866","DOIUrl":null,"url":null,"abstract":"<div><h3>Introduction</h3><div>Monitoring continuous Blood Pressure (BP) signals is essential as BP can vary rapidly. However, current Photoplethysmography (PPG)-based methods for estimating BP need to be more accurate and provide predictions for Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP).</div></div><div><h3>Materials and methods</h3><div>Full cycle of PPG waveform is considered to estimate SBP and DBP values. This study recommends deep learning techniques, including Temporal Convolutional Network (TCN), Long-Short Term Memory (LSTM), TCN-LSTM, and Autoencoder-LSTM, to estimate SBP and DBP.</div></div><div><h3>Results</h3><div>According to the outcomes, the proposed framework estimates continuous BP precisely utilizing PPG signals. Specifically, the Autoencoder-LSTM algorithm achieved a Mean Average Error (MAE) of 1.05 and 0.92 for SBP and DBP and a Standard Deviation (SD) of 1.89 and 1.05 for SBP and DBP, respectively, indicating that the model is suitable for estimating these values from PPG signals. The Autoencoder-LSTM approach produced a Mean Average Error (MAE) of 1.05 and 0.92 for SBP and DBP, respectively, as well as a Standard Deviation (SD) of 1.89 and 1.05, demonstrating that the model can estimate these values using PPG signals.</div></div><div><h3>Conclusion</h3><div>This paper evaluates an algorithm that estimates BP continuously using the PPG signal. Autoencoder-LSTM is suitable for estimating continuous BP values since MAE and SD values are low for SBP and DBP.</div></div>","PeriodicalId":34311,"journal":{"name":"Measurement Sensors","volume":"39 ","pages":"Article 101866"},"PeriodicalIF":0.0000,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement Sensors","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2665917425000601","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"Engineering","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction

Monitoring continuous Blood Pressure (BP) signals is essential as BP can vary rapidly. However, current Photoplethysmography (PPG)-based methods for estimating BP need to be more accurate and provide predictions for Systolic Blood Pressure (SBP) and Diastolic Blood Pressure (DBP).

Materials and methods

Full cycle of PPG waveform is considered to estimate SBP and DBP values. This study recommends deep learning techniques, including Temporal Convolutional Network (TCN), Long-Short Term Memory (LSTM), TCN-LSTM, and Autoencoder-LSTM, to estimate SBP and DBP.

Results

According to the outcomes, the proposed framework estimates continuous BP precisely utilizing PPG signals. Specifically, the Autoencoder-LSTM algorithm achieved a Mean Average Error (MAE) of 1.05 and 0.92 for SBP and DBP and a Standard Deviation (SD) of 1.89 and 1.05 for SBP and DBP, respectively, indicating that the model is suitable for estimating these values from PPG signals. The Autoencoder-LSTM approach produced a Mean Average Error (MAE) of 1.05 and 0.92 for SBP and DBP, respectively, as well as a Standard Deviation (SD) of 1.89 and 1.05, demonstrating that the model can estimate these values using PPG signals.

Conclusion

This paper evaluates an algorithm that estimates BP continuously using the PPG signal. Autoencoder-LSTM is suitable for estimating continuous BP values since MAE and SD values are low for SBP and DBP.
基于光容积脉搏波信号的连续血压估计的深度学习方法
由于血压变化很快,监测连续的血压(BP)信号是必要的。然而,目前基于光容积脉搏图(PPG)的血压估计方法需要更准确,并提供收缩压(SBP)和舒张压(DBP)的预测。材料和方法采用全周期的PPG波形来估计收缩压和舒张压值。本研究推荐深度学习技术,包括时间卷积网络(TCN)、长短期记忆(LSTM)、TCN-LSTM和自动编码器-LSTM,来估计收缩压和舒张压。结果该框架利用PPG信号精确估计连续BP。其中,Autoencoder-LSTM算法对收缩压和DBP的平均误差(Mean Average Error, MAE)分别为1.05和0.92,对收缩压和DBP的标准差(Standard Deviation, SD)分别为1.89和1.05,表明该模型适合从PPG信号中估计这些值。Autoencoder-LSTM方法对收缩压和舒张压的平均误差(MAE)分别为1.05和0.92,标准差(SD)为1.89和1.05,表明该模型可以使用PPG信号估计这些值。结论本文评价了一种利用PPG信号连续估计BP的算法。自编码器- lstm适合估计连续BP值,因为收缩压和舒张压的MAE和SD值较低。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Measurement Sensors
Measurement Sensors Engineering-Industrial and Manufacturing Engineering
CiteScore
3.10
自引率
0.00%
发文量
184
审稿时长
56 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信