Computer-assisted auscultation: Patent ductus arteriosus detection based on auditory time-frequency analysis

Po Hsun Sung, Reid Thompson, Jieh Neng Wang, Jhing Fa Wang, Ling Sheng Jang

Research output: Contribution to journalArticle

Abstract

This study presents a computer-assisted auscultation approach for patent ductus arteriosus (PDA) detection. PDA is a frequent congenital heart disease in neonates. The early detection of the PDA murmur from a neonate's heart sound is important to avoid the development of severe respiratory diseases in newborns. Computer-assisted auscultation has the potential to become a heart disease screening tool because it can improve the sensitivity and specificity of heart murmur detection. This study proposes an auditory time-frequency representation method (auditory spectrogram) to demonstrate the dynamic and non-stationary characteristics of heart murmurs. The auditory spectrogram is obtained using the proposed cochlear wavelet transform, which mimics the auditory response of the cochlea in the human auditory system. The auditory spectrogram can represent the heart sounds in the time-frequency domain to assist cardiac auscultation. Furthermore, the spectrum flux and spectrum centroid are used to characterize the configuration of the auditory spectrogram. The phonocardiogram data of 18 patients, including normal heart sounds, innocent murmurs, and PDA murmurs, are used in the blind test for algorithm effectiveness assessment. The results demonstrate that the proposed computer-assisted auscultation method can achieve a high sensitivity of 100 % and a specificity of 91.67 % for PDA detection. The developed method is robust, cost-effective, and convenient, making it effective for the enhancement of the accuracy of PDA detection.

Original languageEnglish (US)
Pages (from-to)76-85
Number of pages10
JournalJournal of Medical and Biological Engineering
Volume35
Issue number1
DOIs
StatePublished - Feb 1 2015

Fingerprint

Auscultation
Patent Ductus Arteriosus
Heart Sounds
Heart Murmurs
Cochlea
Newborn Infant
Acoustic waves
Heart Diseases
Heart Auscultation
Wavelet Analysis
Pulmonary diseases
Wavelet transforms
Screening
Costs and Cost Analysis
Sensitivity and Specificity
Fluxes

Keywords

  • Auditory time-frequency representation
  • Cochlear wavelet transform
  • Computer-assisted auscultation
  • Heart murmur
  • Patent ductus arteriosus (PDA)
  • Spectro-temporal feature

ASJC Scopus subject areas

  • Biomedical Engineering
  • Medicine(all)

Cite this

Computer-assisted auscultation : Patent ductus arteriosus detection based on auditory time-frequency analysis. / Sung, Po Hsun; Thompson, Reid; Wang, Jieh Neng; Wang, Jhing Fa; Jang, Ling Sheng.

In: Journal of Medical and Biological Engineering, Vol. 35, No. 1, 01.02.2015, p. 76-85.

Research output: Contribution to journalArticle

@article{67d9bc95a74046e49e8827cd5cf591a6,
title = "Computer-assisted auscultation: Patent ductus arteriosus detection based on auditory time-frequency analysis",
abstract = "This study presents a computer-assisted auscultation approach for patent ductus arteriosus (PDA) detection. PDA is a frequent congenital heart disease in neonates. The early detection of the PDA murmur from a neonate's heart sound is important to avoid the development of severe respiratory diseases in newborns. Computer-assisted auscultation has the potential to become a heart disease screening tool because it can improve the sensitivity and specificity of heart murmur detection. This study proposes an auditory time-frequency representation method (auditory spectrogram) to demonstrate the dynamic and non-stationary characteristics of heart murmurs. The auditory spectrogram is obtained using the proposed cochlear wavelet transform, which mimics the auditory response of the cochlea in the human auditory system. The auditory spectrogram can represent the heart sounds in the time-frequency domain to assist cardiac auscultation. Furthermore, the spectrum flux and spectrum centroid are used to characterize the configuration of the auditory spectrogram. The phonocardiogram data of 18 patients, including normal heart sounds, innocent murmurs, and PDA murmurs, are used in the blind test for algorithm effectiveness assessment. The results demonstrate that the proposed computer-assisted auscultation method can achieve a high sensitivity of 100 {\%} and a specificity of 91.67 {\%} for PDA detection. The developed method is robust, cost-effective, and convenient, making it effective for the enhancement of the accuracy of PDA detection.",
keywords = "Auditory time-frequency representation, Cochlear wavelet transform, Computer-assisted auscultation, Heart murmur, Patent ductus arteriosus (PDA), Spectro-temporal feature",
author = "Sung, {Po Hsun} and Reid Thompson and Wang, {Jieh Neng} and Wang, {Jhing Fa} and Jang, {Ling Sheng}",
year = "2015",
month = "2",
day = "1",
doi = "10.1007/s40846-015-0008-9",
language = "English (US)",
volume = "35",
pages = "76--85",
journal = "Journal of Medical and Biological Engineering",
issn = "1609-0985",
publisher = "Biomedical Engineering Society",
number = "1",

}

TY - JOUR

T1 - Computer-assisted auscultation

T2 - Patent ductus arteriosus detection based on auditory time-frequency analysis

AU - Sung, Po Hsun

AU - Thompson, Reid

AU - Wang, Jieh Neng

AU - Wang, Jhing Fa

AU - Jang, Ling Sheng

PY - 2015/2/1

Y1 - 2015/2/1

N2 - This study presents a computer-assisted auscultation approach for patent ductus arteriosus (PDA) detection. PDA is a frequent congenital heart disease in neonates. The early detection of the PDA murmur from a neonate's heart sound is important to avoid the development of severe respiratory diseases in newborns. Computer-assisted auscultation has the potential to become a heart disease screening tool because it can improve the sensitivity and specificity of heart murmur detection. This study proposes an auditory time-frequency representation method (auditory spectrogram) to demonstrate the dynamic and non-stationary characteristics of heart murmurs. The auditory spectrogram is obtained using the proposed cochlear wavelet transform, which mimics the auditory response of the cochlea in the human auditory system. The auditory spectrogram can represent the heart sounds in the time-frequency domain to assist cardiac auscultation. Furthermore, the spectrum flux and spectrum centroid are used to characterize the configuration of the auditory spectrogram. The phonocardiogram data of 18 patients, including normal heart sounds, innocent murmurs, and PDA murmurs, are used in the blind test for algorithm effectiveness assessment. The results demonstrate that the proposed computer-assisted auscultation method can achieve a high sensitivity of 100 % and a specificity of 91.67 % for PDA detection. The developed method is robust, cost-effective, and convenient, making it effective for the enhancement of the accuracy of PDA detection.

AB - This study presents a computer-assisted auscultation approach for patent ductus arteriosus (PDA) detection. PDA is a frequent congenital heart disease in neonates. The early detection of the PDA murmur from a neonate's heart sound is important to avoid the development of severe respiratory diseases in newborns. Computer-assisted auscultation has the potential to become a heart disease screening tool because it can improve the sensitivity and specificity of heart murmur detection. This study proposes an auditory time-frequency representation method (auditory spectrogram) to demonstrate the dynamic and non-stationary characteristics of heart murmurs. The auditory spectrogram is obtained using the proposed cochlear wavelet transform, which mimics the auditory response of the cochlea in the human auditory system. The auditory spectrogram can represent the heart sounds in the time-frequency domain to assist cardiac auscultation. Furthermore, the spectrum flux and spectrum centroid are used to characterize the configuration of the auditory spectrogram. The phonocardiogram data of 18 patients, including normal heart sounds, innocent murmurs, and PDA murmurs, are used in the blind test for algorithm effectiveness assessment. The results demonstrate that the proposed computer-assisted auscultation method can achieve a high sensitivity of 100 % and a specificity of 91.67 % for PDA detection. The developed method is robust, cost-effective, and convenient, making it effective for the enhancement of the accuracy of PDA detection.

KW - Auditory time-frequency representation

KW - Cochlear wavelet transform

KW - Computer-assisted auscultation

KW - Heart murmur

KW - Patent ductus arteriosus (PDA)

KW - Spectro-temporal feature

UR - http://www.scopus.com/inward/record.url?scp=84957959351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957959351&partnerID=8YFLogxK

U2 - 10.1007/s40846-015-0008-9

DO - 10.1007/s40846-015-0008-9

M3 - Article

AN - SCOPUS:84957959351

VL - 35

SP - 76

EP - 85

JO - Journal of Medical and Biological Engineering

JF - Journal of Medical and Biological Engineering

SN - 1609-0985

IS - 1

ER -