Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram
Abstract Cuffless blood pressure measurement enables unobtrusive and continuous monitoring that can be integrated with wearable devices to extend healthcare to non-hospital settings. Most of the current research has focused on the estimation of blood pressure based on pulse transit time or pulse arr...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-10-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-22205-0 |
_version_ | 1798029889117356032 |
---|---|
author | Rafael Gonzalez-Landaeta Brenda Ramirez Jose Mejia |
author_facet | Rafael Gonzalez-Landaeta Brenda Ramirez Jose Mejia |
author_sort | Rafael Gonzalez-Landaeta |
collection | DOAJ |
description | Abstract Cuffless blood pressure measurement enables unobtrusive and continuous monitoring that can be integrated with wearable devices to extend healthcare to non-hospital settings. Most of the current research has focused on the estimation of blood pressure based on pulse transit time or pulse arrival time using ECG or peripheral cardiac pulse signals as proximal time references. This study proposed the use of a phonocardiogram (PCG) and ballistocardiogram (BCG), two signals detected noninvasively, to estimate systolic blood pressure (SBP). For this, the PCG and the BCG were simultaneously measured in 21 volunteers in the rest, activity, and post-activity conditions. Different features were considered based on the relationships between these signals. The intervals between S1 and S2 of the PCG and the I, J, and K waves of the BCG were statistically analyzed. The IJ and JK slopes were also estimated as additional features to train the machine-learning algorithm. The intervals S1-J, S1-K, S1-I, J-S2, and I-S2 were negatively correlated with changes in SBP (p-val < 0.01). The features were used as explanatory variables for a regressor based on the Random Forest. It was possible to estimate the systolic blood pressure with a mean error of 3.3 mmHg with a standard deviation of ± 5 mmHg. Therefore, we foresee that this proposal has potential applications for wearable devices that use low-cost embedded systems. |
first_indexed | 2024-04-11T19:31:23Z |
format | Article |
id | doaj.art-fafa14cb90ca4eecbfd05c3b0084a00b |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-11T19:31:23Z |
publishDate | 2022-10-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-fafa14cb90ca4eecbfd05c3b0084a00b2022-12-22T04:06:59ZengNature PortfolioScientific Reports2045-23222022-10-0112111010.1038/s41598-022-22205-0Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogramRafael Gonzalez-Landaeta0Brenda Ramirez1Jose Mejia2Department of Electrical and Computer Engineering, Autonomous University of Ciudad JuarezDepartment of Electrical and Computer Engineering, Autonomous University of Ciudad JuarezDepartment of Electrical and Computer Engineering, Autonomous University of Ciudad JuarezAbstract Cuffless blood pressure measurement enables unobtrusive and continuous monitoring that can be integrated with wearable devices to extend healthcare to non-hospital settings. Most of the current research has focused on the estimation of blood pressure based on pulse transit time or pulse arrival time using ECG or peripheral cardiac pulse signals as proximal time references. This study proposed the use of a phonocardiogram (PCG) and ballistocardiogram (BCG), two signals detected noninvasively, to estimate systolic blood pressure (SBP). For this, the PCG and the BCG were simultaneously measured in 21 volunteers in the rest, activity, and post-activity conditions. Different features were considered based on the relationships between these signals. The intervals between S1 and S2 of the PCG and the I, J, and K waves of the BCG were statistically analyzed. The IJ and JK slopes were also estimated as additional features to train the machine-learning algorithm. The intervals S1-J, S1-K, S1-I, J-S2, and I-S2 were negatively correlated with changes in SBP (p-val < 0.01). The features were used as explanatory variables for a regressor based on the Random Forest. It was possible to estimate the systolic blood pressure with a mean error of 3.3 mmHg with a standard deviation of ± 5 mmHg. Therefore, we foresee that this proposal has potential applications for wearable devices that use low-cost embedded systems.https://doi.org/10.1038/s41598-022-22205-0 |
spellingShingle | Rafael Gonzalez-Landaeta Brenda Ramirez Jose Mejia Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram Scientific Reports |
title | Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram |
title_full | Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram |
title_fullStr | Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram |
title_full_unstemmed | Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram |
title_short | Estimation of systolic blood pressure by Random Forest using heart sounds and a ballistocardiogram |
title_sort | estimation of systolic blood pressure by random forest using heart sounds and a ballistocardiogram |
url | https://doi.org/10.1038/s41598-022-22205-0 |
work_keys_str_mv | AT rafaelgonzalezlandaeta estimationofsystolicbloodpressurebyrandomforestusingheartsoundsandaballistocardiogram AT brendaramirez estimationofsystolicbloodpressurebyrandomforestusingheartsoundsandaballistocardiogram AT josemejia estimationofsystolicbloodpressurebyrandomforestusingheartsoundsandaballistocardiogram |