Mining for diagnostic information in body surface potential maps: A comparison of feature selection techniques

Research output: Contribution to journalArticle

18 Citations (Scopus)

Abstract

BackgroundIn body surface potential mapping, increased spatial sampling is used to allow more accurate detection of a cardiac abnormality. Although diagnostically superior to more conventional electrocardiographic techniques, the perceived complexity of the Body Surface Potential Map (BSPM) acquisition process has prohibited its acceptance in clinical practice. For this reason there is an interest in striking a compromise between the minimum number of electrocardiographic recording sites required to sample the maximum electrocardiographic information.MethodsIn the current study, several techniques widely used in the domains of data mining and knowledge discovery have been employed to mine for diagnostic information in 192 lead BSPMs. In particular, the Single Variable Classifier (SVC) based filter and Sequential Forward Selection (SFS) based wrapper approaches to feature selection have been implemented and evaluated. Using a set of recordings from 116 subjects, the diagnostic ability of subsets of 3, 6, 9, 12, 24 and 32 electrocardiographic recording sites have been evaluated based on their ability to correctly asses the presence or absence of Myocardial Infarction (MI).ResultsIt was observed that the wrapper approach, using sequential forward selection and a 5 nearest neighbour classifier, was capable of choosing a set of 24 recording sites that could correctly classify 82.8% of BSPMs. Although the filter method performed slightly less favourably, the performance was comparable with a classification accuracy of 79.3%. In addition, experiments were conducted to show how (a) features chosen using the wrapper approach were specific to the classifier used in the selection model, and (b) lead subsets chosen were not necessarily unique.ConclusionIt was concluded that both the filter and wrapper approaches adopted were suitable for guiding the choice of recording sites useful for determining the presence of MI. It should be noted however that in this study recording sites have been suggested on their ability to detect disease and such sites may not be optimal for estimating body surface potential distributions.
LanguageEnglish
JournalBioMedical Engineering Online
Volume4
Issue number51
DOIs
Publication statusPublished - 2 Sep 2005

Fingerprint

Body Surface Potential Mapping
Myocardial Infarction
Data Mining
Equidae
Lead
Haemophilus influenzae type b-polysaccharide vaccine-diphtheria toxoid conjugate

Cite this

@article{b86d7f12a4f74821a4cbad48fcbd7b71,
title = "Mining for diagnostic information in body surface potential maps: A comparison of feature selection techniques",
abstract = "BackgroundIn body surface potential mapping, increased spatial sampling is used to allow more accurate detection of a cardiac abnormality. Although diagnostically superior to more conventional electrocardiographic techniques, the perceived complexity of the Body Surface Potential Map (BSPM) acquisition process has prohibited its acceptance in clinical practice. For this reason there is an interest in striking a compromise between the minimum number of electrocardiographic recording sites required to sample the maximum electrocardiographic information.MethodsIn the current study, several techniques widely used in the domains of data mining and knowledge discovery have been employed to mine for diagnostic information in 192 lead BSPMs. In particular, the Single Variable Classifier (SVC) based filter and Sequential Forward Selection (SFS) based wrapper approaches to feature selection have been implemented and evaluated. Using a set of recordings from 116 subjects, the diagnostic ability of subsets of 3, 6, 9, 12, 24 and 32 electrocardiographic recording sites have been evaluated based on their ability to correctly asses the presence or absence of Myocardial Infarction (MI).ResultsIt was observed that the wrapper approach, using sequential forward selection and a 5 nearest neighbour classifier, was capable of choosing a set of 24 recording sites that could correctly classify 82.8{\%} of BSPMs. Although the filter method performed slightly less favourably, the performance was comparable with a classification accuracy of 79.3{\%}. In addition, experiments were conducted to show how (a) features chosen using the wrapper approach were specific to the classifier used in the selection model, and (b) lead subsets chosen were not necessarily unique.ConclusionIt was concluded that both the filter and wrapper approaches adopted were suitable for guiding the choice of recording sites useful for determining the presence of MI. It should be noted however that in this study recording sites have been suggested on their ability to detect disease and such sites may not be optimal for estimating body surface potential distributions.",
author = "D Finlay and CD Nugent and Paul McCullagh and Norman Black",
year = "2005",
month = "9",
day = "2",
doi = "10.1186/1475-925X-4-51",
language = "English",
volume = "4",
journal = "BioMedical Engineering Online",
issn = "1475-925X",
publisher = "BioMed Central",
number = "51",

}

TY - JOUR

T1 - Mining for diagnostic information in body surface potential maps: A comparison of feature selection techniques

AU - Finlay, D

AU - Nugent, CD

AU - McCullagh, Paul

AU - Black, Norman

PY - 2005/9/2

Y1 - 2005/9/2

N2 - BackgroundIn body surface potential mapping, increased spatial sampling is used to allow more accurate detection of a cardiac abnormality. Although diagnostically superior to more conventional electrocardiographic techniques, the perceived complexity of the Body Surface Potential Map (BSPM) acquisition process has prohibited its acceptance in clinical practice. For this reason there is an interest in striking a compromise between the minimum number of electrocardiographic recording sites required to sample the maximum electrocardiographic information.MethodsIn the current study, several techniques widely used in the domains of data mining and knowledge discovery have been employed to mine for diagnostic information in 192 lead BSPMs. In particular, the Single Variable Classifier (SVC) based filter and Sequential Forward Selection (SFS) based wrapper approaches to feature selection have been implemented and evaluated. Using a set of recordings from 116 subjects, the diagnostic ability of subsets of 3, 6, 9, 12, 24 and 32 electrocardiographic recording sites have been evaluated based on their ability to correctly asses the presence or absence of Myocardial Infarction (MI).ResultsIt was observed that the wrapper approach, using sequential forward selection and a 5 nearest neighbour classifier, was capable of choosing a set of 24 recording sites that could correctly classify 82.8% of BSPMs. Although the filter method performed slightly less favourably, the performance was comparable with a classification accuracy of 79.3%. In addition, experiments were conducted to show how (a) features chosen using the wrapper approach were specific to the classifier used in the selection model, and (b) lead subsets chosen were not necessarily unique.ConclusionIt was concluded that both the filter and wrapper approaches adopted were suitable for guiding the choice of recording sites useful for determining the presence of MI. It should be noted however that in this study recording sites have been suggested on their ability to detect disease and such sites may not be optimal for estimating body surface potential distributions.

AB - BackgroundIn body surface potential mapping, increased spatial sampling is used to allow more accurate detection of a cardiac abnormality. Although diagnostically superior to more conventional electrocardiographic techniques, the perceived complexity of the Body Surface Potential Map (BSPM) acquisition process has prohibited its acceptance in clinical practice. For this reason there is an interest in striking a compromise between the minimum number of electrocardiographic recording sites required to sample the maximum electrocardiographic information.MethodsIn the current study, several techniques widely used in the domains of data mining and knowledge discovery have been employed to mine for diagnostic information in 192 lead BSPMs. In particular, the Single Variable Classifier (SVC) based filter and Sequential Forward Selection (SFS) based wrapper approaches to feature selection have been implemented and evaluated. Using a set of recordings from 116 subjects, the diagnostic ability of subsets of 3, 6, 9, 12, 24 and 32 electrocardiographic recording sites have been evaluated based on their ability to correctly asses the presence or absence of Myocardial Infarction (MI).ResultsIt was observed that the wrapper approach, using sequential forward selection and a 5 nearest neighbour classifier, was capable of choosing a set of 24 recording sites that could correctly classify 82.8% of BSPMs. Although the filter method performed slightly less favourably, the performance was comparable with a classification accuracy of 79.3%. In addition, experiments were conducted to show how (a) features chosen using the wrapper approach were specific to the classifier used in the selection model, and (b) lead subsets chosen were not necessarily unique.ConclusionIt was concluded that both the filter and wrapper approaches adopted were suitable for guiding the choice of recording sites useful for determining the presence of MI. It should be noted however that in this study recording sites have been suggested on their ability to detect disease and such sites may not be optimal for estimating body surface potential distributions.

U2 - 10.1186/1475-925X-4-51

DO - 10.1186/1475-925X-4-51

M3 - Article

VL - 4

JO - BioMedical Engineering Online

T2 - BioMedical Engineering Online

JF - BioMedical Engineering Online

SN - 1475-925X

IS - 51

ER -