Detection of heart murmurs using wavelet analysis and artificial neural networks

Nicholas Andrisevic, Khaled Ejaz, Fernando Rios-Gutierrez, Rocio Alba-Flores, Glenn Nordehn, Stanley G Burns

Research output: Contribution to journalArticle

29 Citations (Scopus)

Abstract

This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5% and a sensitivity of 64.7%.

Original languageEnglish (US)
Pages (from-to)899-904
Number of pages6
JournalJournal of Biomechanical Engineering
Volume127
Issue number6
DOIs
StatePublished - Nov 1 2005

Fingerprint

Heart Sounds
Heart Murmurs
Wavelet Analysis
Wavelet analysis
Neural networks
Acoustic waves
Heart Auscultation
Physicians' Offices
Primary Care Physicians
Principal Component Analysis
Primary Health Care
Principal component analysis
Research
Testing
Processing

Keywords

  • Artificial Neural Networks
  • Cardiovascular
  • Digital Image Processing
  • Heart Murmur
  • Medical Diagnostic Device
  • Wavelet Packet Analysis

Cite this

Detection of heart murmurs using wavelet analysis and artificial neural networks. / Andrisevic, Nicholas; Ejaz, Khaled; Rios-Gutierrez, Fernando; Alba-Flores, Rocio; Nordehn, Glenn; Burns, Stanley G.

In: Journal of Biomechanical Engineering, Vol. 127, No. 6, 01.11.2005, p. 899-904.

Research output: Contribution to journalArticle

Andrisevic, N, Ejaz, K, Rios-Gutierrez, F, Alba-Flores, R, Nordehn, G & Burns, SG 2005, 'Detection of heart murmurs using wavelet analysis and artificial neural networks', Journal of Biomechanical Engineering, vol. 127, no. 6, pp. 899-904. https://doi.org/10.1115/1.2049327
Andrisevic, Nicholas ; Ejaz, Khaled ; Rios-Gutierrez, Fernando ; Alba-Flores, Rocio ; Nordehn, Glenn ; Burns, Stanley G. / Detection of heart murmurs using wavelet analysis and artificial neural networks. In: Journal of Biomechanical Engineering. 2005 ; Vol. 127, No. 6. pp. 899-904.
@article{66cf08e2116542f3b564aed717a81d52,
title = "Detection of heart murmurs using wavelet analysis and artificial neural networks",
abstract = "This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5{\%} and a sensitivity of 64.7{\%}.",
keywords = "Artificial Neural Networks, Cardiovascular, Digital Image Processing, Heart Murmur, Medical Diagnostic Device, Wavelet Packet Analysis",
author = "Nicholas Andrisevic and Khaled Ejaz and Fernando Rios-Gutierrez and Rocio Alba-Flores and Glenn Nordehn and Burns, {Stanley G}",
year = "2005",
month = "11",
day = "1",
doi = "10.1115/1.2049327",
language = "English (US)",
volume = "127",
pages = "899--904",
journal = "Journal of Biomechanical Engineering",
issn = "0148-0731",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "6",

}

TY - JOUR

T1 - Detection of heart murmurs using wavelet analysis and artificial neural networks

AU - Andrisevic, Nicholas

AU - Ejaz, Khaled

AU - Rios-Gutierrez, Fernando

AU - Alba-Flores, Rocio

AU - Nordehn, Glenn

AU - Burns, Stanley G

PY - 2005/11/1

Y1 - 2005/11/1

N2 - This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5% and a sensitivity of 64.7%.

AB - This paper presents the algorithm and technical aspects of an intelligent diagnostic system for the detection of heart murmurs. The purpose of this research is to address the lack of effectively accurate cardiac auscultation present at the primary care physician office by development of an algorithm capable of operating within the hectic environment of the primary care office. The proposed algorithm consists of three main stages. First; denoising of input data (digital recordings of heart sounds), via Wavelet Packet Analysis. Second; input vector preparation through the use of Principal Component Analysis and block processing. Third; classification of the heart sound using an Artificial Neural Network. Initial testing revealed the intelligent diagnostic system can differentiate between normal healthy heart sounds and abnormal heart sounds (e.g., murmurs), with a specificity of 70.5% and a sensitivity of 64.7%.

KW - Artificial Neural Networks

KW - Cardiovascular

KW - Digital Image Processing

KW - Heart Murmur

KW - Medical Diagnostic Device

KW - Wavelet Packet Analysis

UR - http://www.scopus.com/inward/record.url?scp=27444437211&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27444437211&partnerID=8YFLogxK

U2 - 10.1115/1.2049327

DO - 10.1115/1.2049327

M3 - Article

C2 - 16438225

AN - SCOPUS:27444437211

VL - 127

SP - 899

EP - 904

JO - Journal of Biomechanical Engineering

JF - Journal of Biomechanical Engineering

SN - 0148-0731

IS - 6

ER -