Classification of normal and ischemia from BSPM by neural network approach

Gang Sun; Cecil W. Thomas; Jerome Liebman; Yoram Rudy; Yehuda Reich; Donatella Stilli; Emilio Macchi

Classification of normal and ischemia from BSPM by neural network approach

Gang Sun, Cecil W. Thomas, Jerome Liebman, Yoram Rudy, Yehuda Reich, Donatella Stilli, Emilio Macchi

Department of Biomedical Engineering

Research output: Contribution to conference › Paper › peer-review

8 Scopus citations

Abstract

Body surface potential mapping (BSPM) techniques have improved diagnosis of ischemia patients with normal resting ECG. The authors report BSPM data from 32 normal and 24 ischemia patients (all adults). The studies included: (1) separability of normal and ischemia from QRS integral maps (represented by normalized K-L expansion) by a two-layer forward network method; (2) evaluation of classification performance versus the number of representing eigenvectors; and (3) distribution and relationship of normal and ischemia QRS integral maps. Results show that ischemia and normal were distributed very close to each other, but can be well separated. Only ten expansion coefficients were needed to reach a 98% classification rate evaluated by a resubstitution method and an 82% classification rate by a cross-validation method.

Original language	English
Pages	1504-1505
Number of pages	2
State	Published - 1988
Event	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society - New Orleans, LA, USA Duration: Nov 4 1988 → Nov 7 1988

Conference

Conference	Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society
City	New Orleans, LA, USA
Period	11/4/88 → 11/7/88

Cite this

@conference{0e6b259b33f6424da9ce1b22a5048809,

title = "Classification of normal and ischemia from BSPM by neural network approach",

abstract = "Body surface potential mapping (BSPM) techniques have improved diagnosis of ischemia patients with normal resting ECG. The authors report BSPM data from 32 normal and 24 ischemia patients (all adults). The studies included: (1) separability of normal and ischemia from QRS integral maps (represented by normalized K-L expansion) by a two-layer forward network method; (2) evaluation of classification performance versus the number of representing eigenvectors; and (3) distribution and relationship of normal and ischemia QRS integral maps. Results show that ischemia and normal were distributed very close to each other, but can be well separated. Only ten expansion coefficients were needed to reach a 98% classification rate evaluated by a resubstitution method and an 82% classification rate by a cross-validation method.",

author = "Gang Sun and Thomas, {Cecil W.} and Jerome Liebman and Yoram Rudy and Yehuda Reich and Donatella Stilli and Emilio Macchi",

year = "1988",

language = "English",

pages = "1504--1505",

note = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society ; Conference date: 04-11-1988 Through 07-11-1988",

}

TY - CONF

T1 - Classification of normal and ischemia from BSPM by neural network approach

AU - Sun, Gang

AU - Thomas, Cecil W.

AU - Liebman, Jerome

AU - Rudy, Yoram

AU - Reich, Yehuda

AU - Stilli, Donatella

AU - Macchi, Emilio

PY - 1988

Y1 - 1988

N2 - Body surface potential mapping (BSPM) techniques have improved diagnosis of ischemia patients with normal resting ECG. The authors report BSPM data from 32 normal and 24 ischemia patients (all adults). The studies included: (1) separability of normal and ischemia from QRS integral maps (represented by normalized K-L expansion) by a two-layer forward network method; (2) evaluation of classification performance versus the number of representing eigenvectors; and (3) distribution and relationship of normal and ischemia QRS integral maps. Results show that ischemia and normal were distributed very close to each other, but can be well separated. Only ten expansion coefficients were needed to reach a 98% classification rate evaluated by a resubstitution method and an 82% classification rate by a cross-validation method.

AB - Body surface potential mapping (BSPM) techniques have improved diagnosis of ischemia patients with normal resting ECG. The authors report BSPM data from 32 normal and 24 ischemia patients (all adults). The studies included: (1) separability of normal and ischemia from QRS integral maps (represented by normalized K-L expansion) by a two-layer forward network method; (2) evaluation of classification performance versus the number of representing eigenvectors; and (3) distribution and relationship of normal and ischemia QRS integral maps. Results show that ischemia and normal were distributed very close to each other, but can be well separated. Only ten expansion coefficients were needed to reach a 98% classification rate evaluated by a resubstitution method and an 82% classification rate by a cross-validation method.

UR - http://www.scopus.com/inward/record.url?scp=0024176560&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0024176560

SP - 1504

EP - 1505

T2 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 4 November 1988 through 7 November 1988

ER -

Classification of normal and ischemia from BSPM by neural network approach

Abstract

Conference

Other files and links

Fingerprint

Cite this