Automated diagnosis of ischemic heart disease using dilated discrete hermite functions

Raghavan Gopalakrishnan, Soumyadipta Acharya, Dale H. Mugler

Research output: Contribution to conferencePaper

Abstract

A novel method for extraction and classification of ischemie features from electrocardiograms, based on the Dilated Discrete Hermite expansion, is described. The discrete Hermite functions used for the expansion are eigenvectors of a symmetric tridiagonal matrix that commutes with the centered Fourier matrix. A choice of 50 Hermite coefficients and a dilation parameter were sufficient to reconstruct the ECG with all essential features preserved. The Performance was measured using Percentage RMS Difference (PRD). The 50 coefficients and the dilation parameter contain information about the shape of the ECG and a Committee Neural Network classifier with these 51 input parameters was trained to identify ischemie features. A sensitivity of 97% and a specificity of 94% was achieved. This technique can also be used for training neural networks to identify other abnormalities of the ECG.

Original languageEnglish (US)
Pages97-98
Number of pages2
StatePublished - Jun 22 2004
Externally publishedYes
EventProceedings of the IEEE 30th Annual Northeast Bioengineering Conference - Springfield, MA, United States
Duration: Apr 17 2004Apr 18 2004

Other

OtherProceedings of the IEEE 30th Annual Northeast Bioengineering Conference
CountryUnited States
CitySpringfield, MA
Period4/17/044/18/04

Fingerprint

Electrocardiography
Neural networks
Eigenvalues and eigenfunctions
Classifiers

ASJC Scopus subject areas

  • Bioengineering

Cite this

Gopalakrishnan, R., Acharya, S., & Mugler, D. H. (2004). Automated diagnosis of ischemic heart disease using dilated discrete hermite functions. 97-98. Paper presented at Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference, Springfield, MA, United States.

Automated diagnosis of ischemic heart disease using dilated discrete hermite functions. / Gopalakrishnan, Raghavan; Acharya, Soumyadipta; Mugler, Dale H.

2004. 97-98 Paper presented at Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference, Springfield, MA, United States.

Research output: Contribution to conferencePaper

Gopalakrishnan, R, Acharya, S & Mugler, DH 2004, 'Automated diagnosis of ischemic heart disease using dilated discrete hermite functions', Paper presented at Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference, Springfield, MA, United States, 4/17/04 - 4/18/04 pp. 97-98.
Gopalakrishnan R, Acharya S, Mugler DH. Automated diagnosis of ischemic heart disease using dilated discrete hermite functions. 2004. Paper presented at Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference, Springfield, MA, United States.
Gopalakrishnan, Raghavan ; Acharya, Soumyadipta ; Mugler, Dale H. / Automated diagnosis of ischemic heart disease using dilated discrete hermite functions. Paper presented at Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference, Springfield, MA, United States.2 p.
@conference{9be1176a33bf4961a379629d12c8eede,
title = "Automated diagnosis of ischemic heart disease using dilated discrete hermite functions",
abstract = "A novel method for extraction and classification of ischemie features from electrocardiograms, based on the Dilated Discrete Hermite expansion, is described. The discrete Hermite functions used for the expansion are eigenvectors of a symmetric tridiagonal matrix that commutes with the centered Fourier matrix. A choice of 50 Hermite coefficients and a dilation parameter were sufficient to reconstruct the ECG with all essential features preserved. The Performance was measured using Percentage RMS Difference (PRD). The 50 coefficients and the dilation parameter contain information about the shape of the ECG and a Committee Neural Network classifier with these 51 input parameters was trained to identify ischemie features. A sensitivity of 97{\%} and a specificity of 94{\%} was achieved. This technique can also be used for training neural networks to identify other abnormalities of the ECG.",
author = "Raghavan Gopalakrishnan and Soumyadipta Acharya and Mugler, {Dale H.}",
year = "2004",
month = "6",
day = "22",
language = "English (US)",
pages = "97--98",
note = "Proceedings of the IEEE 30th Annual Northeast Bioengineering Conference ; Conference date: 17-04-2004 Through 18-04-2004",

}

TY - CONF

T1 - Automated diagnosis of ischemic heart disease using dilated discrete hermite functions

AU - Gopalakrishnan, Raghavan

AU - Acharya, Soumyadipta

AU - Mugler, Dale H.

PY - 2004/6/22

Y1 - 2004/6/22

N2 - A novel method for extraction and classification of ischemie features from electrocardiograms, based on the Dilated Discrete Hermite expansion, is described. The discrete Hermite functions used for the expansion are eigenvectors of a symmetric tridiagonal matrix that commutes with the centered Fourier matrix. A choice of 50 Hermite coefficients and a dilation parameter were sufficient to reconstruct the ECG with all essential features preserved. The Performance was measured using Percentage RMS Difference (PRD). The 50 coefficients and the dilation parameter contain information about the shape of the ECG and a Committee Neural Network classifier with these 51 input parameters was trained to identify ischemie features. A sensitivity of 97% and a specificity of 94% was achieved. This technique can also be used for training neural networks to identify other abnormalities of the ECG.

AB - A novel method for extraction and classification of ischemie features from electrocardiograms, based on the Dilated Discrete Hermite expansion, is described. The discrete Hermite functions used for the expansion are eigenvectors of a symmetric tridiagonal matrix that commutes with the centered Fourier matrix. A choice of 50 Hermite coefficients and a dilation parameter were sufficient to reconstruct the ECG with all essential features preserved. The Performance was measured using Percentage RMS Difference (PRD). The 50 coefficients and the dilation parameter contain information about the shape of the ECG and a Committee Neural Network classifier with these 51 input parameters was trained to identify ischemie features. A sensitivity of 97% and a specificity of 94% was achieved. This technique can also be used for training neural networks to identify other abnormalities of the ECG.

UR - http://www.scopus.com/inward/record.url?scp=2942558810&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942558810&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:2942558810

SP - 97

EP - 98

ER -