Aortic blood pressure estimation: A hybrid machine-learning and cross-relation approach

dc.contributor.authorMagbool, Ahmed
dc.contributor.authorBahloul, Mohamed
dc.contributor.authorBallal, Tarig
dc.contributor.authorAl-Naffouri, Tareq Y.
dc.contributor.authorLaleg-Kirati, Taous-Meriem
dc.contributor.departmentComputational Bioscience Research Center (CBRC)
dc.contributor.departmentComputer, Electrical and Mathematical Science and Engineering (CEMSE) Division
dc.contributor.departmentElectrical and Computer Engineering
dc.contributor.departmentElectrical and Computer Engineering Program
dc.contributor.departmentEstimation, Modeling and ANalysis Group
dc.date.accepted2021-05-09
dc.date.accessioned2021-05-24T06:44:04Z
dc.date.available2021-05-24T06:44:04Z
dc.date.issued2021-05-23
dc.date.published-online2021-05-23
dc.date.published-print2021-07
dc.date.submitted2020-12-16
dc.description.abstractAortic blood pressure is a vital signal that provides valuable medical information about cardiovascular health condition. Noninvasive measurement of this signal is very challenging, which motivates several researchers to develop mathematical approaches over the years to estimate the aortic pressure from peripheral measurements. Most of these approaches are limited in their performance as they fail to recover important features of the blood pressure signal. To overcome this issue, we investigate the application of machine-learning methods to estimate the aortic blood pressure from peripheral signals. In the absence of reasonably large datasets, we rely on pre-validated virtual databases to train our machine-learning models. To avoid model bias due to the lack of diversity and variability in these databases, we propose a hybrid approach that combines machine-learning models with the cross-relation blind estimation approach. On top of that, a sparse representation, coupled with a dictionary-learning approach, is employed to emphasize the characteristics of the aortic pressure signals and generate more meaningful outputs. Our results show that the proposed hybrid approach offers a reduction in the root-mean-squared error compared to pure machine-learning models and improvement compared to the cross-relation method. The proposed approach also shows a noticeable potency in capturing fine features of the aortic blood pressure signal.
dc.description.sponsorshipThe research reported in this publication is supported by King Abdullah University of Science and Technology (KAUST).
dc.eprint.versionPost-print
dc.identifier.citationMagbool, A., Bahloul, M. A., Ballal, T., Al-Naffouri, T. Y., & Laleg-Kirati, T.-M. (2021). Aortic blood pressure estimation: A hybrid machine-learning and cross-relation approach. Biomedical Signal Processing and Control, 68, 102762. doi:10.1016/j.bspc.2021.102762
dc.identifier.doi10.1016/j.bspc.2021.102762
dc.identifier.issn1746-8094
dc.identifier.journalBiomedical Signal Processing and Control
dc.identifier.pages102762
dc.identifier.urihttp://hdl.handle.net/10754/669209
dc.identifier.volume68
dc.publisherElsevier BV
dc.relation.urlhttps://linkinghub.elsevier.com/retrieve/pii/S1746809421003591
dc.rightsNOTICE: this is the author’s version of a work that was accepted for publication in Biomedical Signal Processing and Control. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Biomedical Signal Processing and Control, [68, , (2021-05-23)] DOI: 10.1016/j.bspc.2021.102762 . © 2021. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.embargodate2023-05-23
dc.titleAortic blood pressure estimation: A hybrid machine-learning and cross-relation approach
dc.typeArticle
display.details.left<span><h5>Embargo End Date</h5>2023-05-23<br><br><h5>Type</h5>Article<br><br><h5>Authors</h5><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0002-5550-405X&spc.sf=dc.date.issued&spc.sd=DESC">Magbool, Ahmed</a> <a href="https://orcid.org/0000-0002-5550-405X" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Bahloul, Mohamed,equals">Bahloul, Mohamed</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.author=Ballal, Tarig,equals">Ballal, Tarig</a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0001-6955-4720&spc.sf=dc.date.issued&spc.sd=DESC">Al-Naffouri, Tareq Y.</a> <a href="https://orcid.org/0000-0001-6955-4720" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><a href="https://repository.kaust.edu.sa/search?query=orcid.id:0000-0001-5944-0121&spc.sf=dc.date.issued&spc.sd=DESC">Laleg-Kirati, Taous-Meriem</a> <a href="https://orcid.org/0000-0001-5944-0121" target="_blank"><img src="https://repository.kaust.edu.sa/server/api/core/bitstreams/82a625b4-ed4b-40c8-865a-d6a5225a26a4/content" width="16" height="16"/></a><br><br><h5>KAUST Department</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Computational Bioscience Research Center (CBRC),equals">Computational Bioscience Research Center (CBRC)</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division,equals">Computer, Electrical and Mathematical Science and Engineering (CEMSE) Division</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Electrical and Computer Engineering,equals">Electrical and Computer Engineering</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Electrical and Computer Engineering Program,equals">Electrical and Computer Engineering Program</a><br><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.department=Estimation, Modeling and ANalysis Group,equals">Estimation, Modeling and ANalysis Group</a><br><br><h5>Online Publication Date</h5>2021-05-23<br><br><h5>Print Publication Date</h5>2021-07<br><br><h5>Date</h5>2021-05-23<br><br><h5>Submitted Date</h5>2020-12-16</span>
display.details.right<span><h5>Abstract</h5>Aortic blood pressure is a vital signal that provides valuable medical information about cardiovascular health condition. Noninvasive measurement of this signal is very challenging, which motivates several researchers to develop mathematical approaches over the years to estimate the aortic pressure from peripheral measurements. Most of these approaches are limited in their performance as they fail to recover important features of the blood pressure signal. To overcome this issue, we investigate the application of machine-learning methods to estimate the aortic blood pressure from peripheral signals. In the absence of reasonably large datasets, we rely on pre-validated virtual databases to train our machine-learning models. To avoid model bias due to the lack of diversity and variability in these databases, we propose a hybrid approach that combines machine-learning models with the cross-relation blind estimation approach. On top of that, a sparse representation, coupled with a dictionary-learning approach, is employed to emphasize the characteristics of the aortic pressure signals and generate more meaningful outputs. Our results show that the proposed hybrid approach offers a reduction in the root-mean-squared error compared to pure machine-learning models and improvement compared to the cross-relation method. The proposed approach also shows a noticeable potency in capturing fine features of the aortic blood pressure signal.<br><br><h5>Citation</h5>Magbool, A., Bahloul, M. A., Ballal, T., Al-Naffouri, T. Y., & Laleg-Kirati, T.-M. (2021). Aortic blood pressure estimation: A hybrid machine-learning and cross-relation approach. Biomedical Signal Processing and Control, 68, 102762. doi:10.1016/j.bspc.2021.102762<br><br><h5>Acknowledgements</h5>The research reported in this publication is supported by King Abdullah University of Science and Technology (KAUST).<br><br><h5>Publisher</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.publisher=Elsevier BV,equals">Elsevier BV</a><br><br><h5>Journal</h5><a href="https://repository.kaust.edu.sa/search?spc.sf=dc.date.issued&spc.sd=DESC&f.journal=Biomedical Signal Processing and Control,equals">Biomedical Signal Processing and Control</a><br><br><h5>DOI</h5><a href="https://doi.org/10.1016/j.bspc.2021.102762">10.1016/j.bspc.2021.102762</a><br><br><h5>Additional Links</h5>https://linkinghub.elsevier.com/retrieve/pii/S1746809421003591</span>
kaust.personMagbool, Ahmed
kaust.personBahloul, Mohamed
kaust.personBallal, Tarig
kaust.personAl-Naffouri, Tareq Y.
kaust.personLaleg-Kirati, Taous-Meriem
orcid.authorMagbool, Ahmed::0000-0002-5550-405X
orcid.authorBahloul, Mohamed
orcid.authorBallal, Tarig
orcid.authorAl-Naffouri, Tareq Y.::0000-0001-6955-4720
orcid.authorLaleg-Kirati, Taous-Meriem::0000-0001-5944-0121
orcid.id0000-0001-5944-0121
orcid.id0000-0001-6955-4720
orcid.id0000-0002-5550-405X
refterms.dateFOA2021-05-24T07:37:40Z
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Aortic_Blood_Pressure_Estimation__A_HybridMachine_Learning_and_Cross_Relation_Approach_final.pdf
Size:
2.01 MB
Format:
Adobe Portable Document Format
Description:
Accepted manuscript