Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

Michael R. Jennings; Pardis Biglarbeigi; Raymond R. Bond; Rob Brisk; Daniel Guldenring; Alan Kennedy; James McLaughlin; Dewar D. Finlay

doi:10.22489/CinC.2020.245

Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

Michael R. Jennings, Pardis Biglarbeigi, Raymond R. Bond, Rob Brisk, Daniel Guldenring, Alan Kennedy, James McLaughlin, Dewar D. Finlay

Science and Engineering Office

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Background: We have previously reported on the potential of patch-based ECG leads to observe changes typical during ischaemia. In this study we aim to assess the utility of patch-based leads in the detection of these changes.

Method: Body surface potential maps (BSPM) from subjects (n=45) undergoing elective percutaneous coronary angioplasty (PTCA) were used. The short spaced lead (SSL), that was previously identified as having the greatest ST-segment change between baseline and peak balloon inflation (PBI), was selected as the basis for a patch based lead system. A feature set of J-point amplitudes for all bipolar leads available within the same 100 mm region were included (n=6). Current 12-lead ECG criteria were applied to 12-lead ECGs for the same subjects to benchmark performance.

Results: The previously identified single SSL achieved sensitivity and specificity of 87% and 71% respectively using a Naive Bayes classifier. Adding other combinations of leads to this did not improve performance significantly. The 12-lead ECG performance was 62/93% (sensi-tivity/specificity).

Conclusion: This study suggests that short spaced leads can be sensitive to ischaemic ECG changes. However, due to the short distance between leads, they lack the specificity of the 12-lead ECG.

Original language	English
Title of host publication	2020 Computing in Cardiology (CinC)
Publisher	IEEE
Number of pages	4
Volume	47
ISBN (Electronic)	9781728173825
ISBN (Print)	9781728111056
DOIs	https://doi.org/10.22489/CinC.2020.245
Publication status	Published - 13 Sept 2020
Event	CinC 2020: Computing in Cardiology - Rimini, Italy Duration: 13 Sept 2020 → 16 Sept 2020

Publication series

Name
ISSN (Print)	2325-8861
ISSN (Electronic)	2325-887X

Conference

Conference	CinC 2020
Country/Territory	Italy
City	Rimini
Period	13/09/20 → 16/09/20

Keywords

Electric potential
Machine learning
Electrocardiography
Lead
Sensitivity and specificity
Myocardium
Naive Bayes methods

ASJC Scopus subject areas

General Computer Science
Cardiology and Cardiovascular Medicine

Access to Document

10.22489/CinC.2020.245

Cite this

@inproceedings{15fa971308574f2bb6814af693bb7e8b,

title = "Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes",

abstract = "Background: We have previously reported on the potential of patch-based ECG leads to observe changes typical during ischaemia. In this study we aim to assess the utility of patch-based leads in the detection of these changes.Method: Body surface potential maps (BSPM) from subjects (n=45) undergoing elective percutaneous coronary angioplasty (PTCA) were used. The short spaced lead (SSL), that was previously identified as having the greatest ST-segment change between baseline and peak balloon inflation (PBI), was selected as the basis for a patch based lead system. A feature set of J-point amplitudes for all bipolar leads available within the same 100 mm region were included (n=6). Current 12-lead ECG criteria were applied to 12-lead ECGs for the same subjects to benchmark performance.Results: The previously identified single SSL achieved sensitivity and specificity of 87% and 71% respectively using a Naive Bayes classifier. Adding other combinations of leads to this did not improve performance significantly. The 12-lead ECG performance was 62/93% (sensi-tivity/specificity).Conclusion: This study suggests that short spaced leads can be sensitive to ischaemic ECG changes. However, due to the short distance between leads, they lack the specificity of the 12-lead ECG.",

keywords = "Electric potential, Machine learning, Electrocardiography, Lead, Sensitivity and specificity, Myocardium, Naive Bayes methods",

author = "Jennings, {Michael R.} and Pardis Biglarbeigi and Bond, {Raymond R.} and Rob Brisk and Daniel Guldenring and Alan Kennedy and James McLaughlin and Finlay, {Dewar D.}",

note = "Funding Information: This project is part of the Eastern Corridor Medical Engineering centre (ECME). It is supported by the European Union{\textquoteright}s INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB).; CinC 2020 : Computing in Cardiology ; Conference date: 13-09-2020 Through 16-09-2020",

year = "2020",

month = sep,

day = "13",

doi = "10.22489/CinC.2020.245",

language = "English",

isbn = "9781728111056",

volume = "47",

publisher = "IEEE",

booktitle = "2020 Computing in Cardiology (CinC)",

}

Jennings, MR, Biglarbeigi, P, Bond, RR, Brisk, R, Guldenring, D, Kennedy, A, McLaughlin, J & Finlay, DD 2020, Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes. in 2020 Computing in Cardiology (CinC). vol. 47, 9344392, IEEE, CinC 2020, Rimini, Italy, 13/09/20. https://doi.org/10.22489/CinC.2020.245

TY - GEN

T1 - Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

AU - Jennings, Michael R.

AU - Biglarbeigi, Pardis

AU - Bond, Raymond R.

AU - Brisk, Rob

AU - Guldenring, Daniel

AU - Kennedy, Alan

AU - McLaughlin, James

AU - Finlay, Dewar D.

N1 - Funding Information: This project is part of the Eastern Corridor Medical Engineering centre (ECME). It is supported by the European Union’s INTERREG VA Programme, managed by the Special EU Programmes Body (SEUPB).

PY - 2020/9/13

Y1 - 2020/9/13

N2 - Background: We have previously reported on the potential of patch-based ECG leads to observe changes typical during ischaemia. In this study we aim to assess the utility of patch-based leads in the detection of these changes.Method: Body surface potential maps (BSPM) from subjects (n=45) undergoing elective percutaneous coronary angioplasty (PTCA) were used. The short spaced lead (SSL), that was previously identified as having the greatest ST-segment change between baseline and peak balloon inflation (PBI), was selected as the basis for a patch based lead system. A feature set of J-point amplitudes for all bipolar leads available within the same 100 mm region were included (n=6). Current 12-lead ECG criteria were applied to 12-lead ECGs for the same subjects to benchmark performance.Results: The previously identified single SSL achieved sensitivity and specificity of 87% and 71% respectively using a Naive Bayes classifier. Adding other combinations of leads to this did not improve performance significantly. The 12-lead ECG performance was 62/93% (sensi-tivity/specificity).Conclusion: This study suggests that short spaced leads can be sensitive to ischaemic ECG changes. However, due to the short distance between leads, they lack the specificity of the 12-lead ECG.

AB - Background: We have previously reported on the potential of patch-based ECG leads to observe changes typical during ischaemia. In this study we aim to assess the utility of patch-based leads in the detection of these changes.Method: Body surface potential maps (BSPM) from subjects (n=45) undergoing elective percutaneous coronary angioplasty (PTCA) were used. The short spaced lead (SSL), that was previously identified as having the greatest ST-segment change between baseline and peak balloon inflation (PBI), was selected as the basis for a patch based lead system. A feature set of J-point amplitudes for all bipolar leads available within the same 100 mm region were included (n=6). Current 12-lead ECG criteria were applied to 12-lead ECGs for the same subjects to benchmark performance.Results: The previously identified single SSL achieved sensitivity and specificity of 87% and 71% respectively using a Naive Bayes classifier. Adding other combinations of leads to this did not improve performance significantly. The 12-lead ECG performance was 62/93% (sensi-tivity/specificity).Conclusion: This study suggests that short spaced leads can be sensitive to ischaemic ECG changes. However, due to the short distance between leads, they lack the specificity of the 12-lead ECG.

KW - Electric potential

KW - Machine learning

KW - Electrocardiography

KW - Lead

KW - Sensitivity and specificity

KW - Myocardium

KW - Naive Bayes methods

UR - http://www.scopus.com/inward/record.url?scp=85100931231&partnerID=8YFLogxK

U2 - 10.22489/CinC.2020.245

DO - 10.22489/CinC.2020.245

M3 - Conference contribution

AN - SCOPUS:85100931231

SN - 9781728111056

VL - 47

BT - 2020 Computing in Cardiology (CinC)

PB - IEEE

T2 - CinC 2020

Y2 - 13 September 2020 through 16 September 2020

ER -

Machine Learning Approach to Assess the Performance of Patch Based Leads in the Detection of Ischaemic Electrocardiogram Changes

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this