Classification of vascular function in upper limb using bilateral photoplethysmographic signals

Nastaran Hesam Shariati, Edmond Zahedi, Hassan Mansouri Jajai

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Bilateral PPG signals have been used for comparative study of two groups of healthy (free from any cardiovascular risk factors) and diabetic (as cardiovascular disease risk group) subjects in the age-matched range 40-50 years. The peripheral blood pulsations were recorded simultaneously from right and left index fingers for 90 s. Pulses have been modeled with the ARX440 model in the interval of 300 sample points with 100 sample points overlap between segments. Model parameters of three segments based on the highest fitness (higher than 80%) of modeled segments were retained for each subject. Subsequently, principal component analysis (PCA) was applied to the parameters of retained segments to eliminate the existing correlation among parameters and provide uncorrelated variables. The first principal component (contains 78.2% variance of data) was significantly greater in diabetic than in control groups (P < 0.0001, 0.74 ± 2.01 versus -0.53 ± 1.66). In addition the seventh principal component, which contains 0.02% of the data variance, was significantly lower in diabetic than in control groups (P < 0.05, -0.007 ± 0.03 versus 0.005 ± 0.03). Finally, linear discrimination analysis (LDA) was used to classify the subjects. The classification was done using the robust leaving-one-subject-out method. LDA could classify the subjects with 71.7% sensitivity and 70.2% specificity while the male subjects resulted in a highly acceptable result for the sensitivity (81%). The present study showed that PPG signals can be used for vascular function assessment and may find further application for detection of vascular changes before onset of clinical diseases.

Original languageEnglish
Pages (from-to)365-374
Number of pages10
JournalPhysiological Measurement
Volume29
Issue number3
DOIs
Publication statusPublished - 1 Mar 2008
Externally publishedYes

Fingerprint

Upper Extremity
Blood Vessels
Control Groups
Principal Component Analysis
Principal component analysis
Fingers
Blood
Cardiovascular Diseases
Sensitivity and Specificity

Keywords

  • ARX modeling
  • Linear discrimination
  • Photoplethysmographic
  • Principal component analysis

ASJC Scopus subject areas

  • Biophysics

Cite this

Classification of vascular function in upper limb using bilateral photoplethysmographic signals. / Shariati, Nastaran Hesam; Zahedi, Edmond; Jajai, Hassan Mansouri.

In: Physiological Measurement, Vol. 29, No. 3, 01.03.2008, p. 365-374.

Research output: Contribution to journalArticle

Shariati, Nastaran Hesam ; Zahedi, Edmond ; Jajai, Hassan Mansouri. / Classification of vascular function in upper limb using bilateral photoplethysmographic signals. In: Physiological Measurement. 2008 ; Vol. 29, No. 3. pp. 365-374.
@article{316304ce93894218816a9379b7f00f7e,
title = "Classification of vascular function in upper limb using bilateral photoplethysmographic signals",
abstract = "Bilateral PPG signals have been used for comparative study of two groups of healthy (free from any cardiovascular risk factors) and diabetic (as cardiovascular disease risk group) subjects in the age-matched range 40-50 years. The peripheral blood pulsations were recorded simultaneously from right and left index fingers for 90 s. Pulses have been modeled with the ARX440 model in the interval of 300 sample points with 100 sample points overlap between segments. Model parameters of three segments based on the highest fitness (higher than 80{\%}) of modeled segments were retained for each subject. Subsequently, principal component analysis (PCA) was applied to the parameters of retained segments to eliminate the existing correlation among parameters and provide uncorrelated variables. The first principal component (contains 78.2{\%} variance of data) was significantly greater in diabetic than in control groups (P < 0.0001, 0.74 ± 2.01 versus -0.53 ± 1.66). In addition the seventh principal component, which contains 0.02{\%} of the data variance, was significantly lower in diabetic than in control groups (P < 0.05, -0.007 ± 0.03 versus 0.005 ± 0.03). Finally, linear discrimination analysis (LDA) was used to classify the subjects. The classification was done using the robust leaving-one-subject-out method. LDA could classify the subjects with 71.7{\%} sensitivity and 70.2{\%} specificity while the male subjects resulted in a highly acceptable result for the sensitivity (81{\%}). The present study showed that PPG signals can be used for vascular function assessment and may find further application for detection of vascular changes before onset of clinical diseases.",
keywords = "ARX modeling, Linear discrimination, Photoplethysmographic, Principal component analysis",
author = "Shariati, {Nastaran Hesam} and Edmond Zahedi and Jajai, {Hassan Mansouri}",
year = "2008",
month = "3",
day = "1",
doi = "10.1088/0967-3334/29/3/007",
language = "English",
volume = "29",
pages = "365--374",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "IOP Publishing Ltd.",
number = "3",

}

TY - JOUR

T1 - Classification of vascular function in upper limb using bilateral photoplethysmographic signals

AU - Shariati, Nastaran Hesam

AU - Zahedi, Edmond

AU - Jajai, Hassan Mansouri

PY - 2008/3/1

Y1 - 2008/3/1

N2 - Bilateral PPG signals have been used for comparative study of two groups of healthy (free from any cardiovascular risk factors) and diabetic (as cardiovascular disease risk group) subjects in the age-matched range 40-50 years. The peripheral blood pulsations were recorded simultaneously from right and left index fingers for 90 s. Pulses have been modeled with the ARX440 model in the interval of 300 sample points with 100 sample points overlap between segments. Model parameters of three segments based on the highest fitness (higher than 80%) of modeled segments were retained for each subject. Subsequently, principal component analysis (PCA) was applied to the parameters of retained segments to eliminate the existing correlation among parameters and provide uncorrelated variables. The first principal component (contains 78.2% variance of data) was significantly greater in diabetic than in control groups (P < 0.0001, 0.74 ± 2.01 versus -0.53 ± 1.66). In addition the seventh principal component, which contains 0.02% of the data variance, was significantly lower in diabetic than in control groups (P < 0.05, -0.007 ± 0.03 versus 0.005 ± 0.03). Finally, linear discrimination analysis (LDA) was used to classify the subjects. The classification was done using the robust leaving-one-subject-out method. LDA could classify the subjects with 71.7% sensitivity and 70.2% specificity while the male subjects resulted in a highly acceptable result for the sensitivity (81%). The present study showed that PPG signals can be used for vascular function assessment and may find further application for detection of vascular changes before onset of clinical diseases.

AB - Bilateral PPG signals have been used for comparative study of two groups of healthy (free from any cardiovascular risk factors) and diabetic (as cardiovascular disease risk group) subjects in the age-matched range 40-50 years. The peripheral blood pulsations were recorded simultaneously from right and left index fingers for 90 s. Pulses have been modeled with the ARX440 model in the interval of 300 sample points with 100 sample points overlap between segments. Model parameters of three segments based on the highest fitness (higher than 80%) of modeled segments were retained for each subject. Subsequently, principal component analysis (PCA) was applied to the parameters of retained segments to eliminate the existing correlation among parameters and provide uncorrelated variables. The first principal component (contains 78.2% variance of data) was significantly greater in diabetic than in control groups (P < 0.0001, 0.74 ± 2.01 versus -0.53 ± 1.66). In addition the seventh principal component, which contains 0.02% of the data variance, was significantly lower in diabetic than in control groups (P < 0.05, -0.007 ± 0.03 versus 0.005 ± 0.03). Finally, linear discrimination analysis (LDA) was used to classify the subjects. The classification was done using the robust leaving-one-subject-out method. LDA could classify the subjects with 71.7% sensitivity and 70.2% specificity while the male subjects resulted in a highly acceptable result for the sensitivity (81%). The present study showed that PPG signals can be used for vascular function assessment and may find further application for detection of vascular changes before onset of clinical diseases.

KW - ARX modeling

KW - Linear discrimination

KW - Photoplethysmographic

KW - Principal component analysis

UR - http://www.scopus.com/inward/record.url?scp=41049114035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=41049114035&partnerID=8YFLogxK

U2 - 10.1088/0967-3334/29/3/007

DO - 10.1088/0967-3334/29/3/007

M3 - Article

C2 - 18367811

AN - SCOPUS:41049114035

VL - 29

SP - 365

EP - 374

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 3

ER -