Dynamic spatiotemporal warping for the detection and location of myocardial infarctions

Chen Kan, Hui Yang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7% for separating MIs and HCs and an accuracy of 96.5% for anterior-related MIs and inferior-related MIs.

Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012
Pages1046-1051
Number of pages6
DOIs
StatePublished - 2012
Event2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012 - Seoul, Korea, Republic of
Duration: Aug 20 2012Aug 24 2012

Other

Other2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012
CountryKorea, Republic of
CitySeoul
Period8/20/128/24/12

Fingerprint

Lead
Oxygen supply
Blood vessels
Biomarkers
Electrocardiography
Muscle
Blood
Cells
Testing

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Kan, C., & Yang, H. (2012). Dynamic spatiotemporal warping for the detection and location of myocardial infarctions. In 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012 (pp. 1046-1051). [6386354] https://doi.org/10.1109/CoASE.2012.6386354
Kan, Chen ; Yang, Hui. / Dynamic spatiotemporal warping for the detection and location of myocardial infarctions. 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012. 2012. pp. 1046-1051
@inproceedings{ec93e4cd718a4791ad134a73f680e834,
title = "Dynamic spatiotemporal warping for the detection and location of myocardial infarctions",
abstract = "Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7{\%} for separating MIs and HCs and an accuracy of 96.5{\%} for anterior-related MIs and inferior-related MIs.",
author = "Chen Kan and Hui Yang",
year = "2012",
doi = "10.1109/CoASE.2012.6386354",
language = "English (US)",
isbn = "9781467304283",
pages = "1046--1051",
booktitle = "2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012",

}

Kan, C & Yang, H 2012, Dynamic spatiotemporal warping for the detection and location of myocardial infarctions. in 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012., 6386354, pp. 1046-1051, 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012, Seoul, Korea, Republic of, 8/20/12. https://doi.org/10.1109/CoASE.2012.6386354

Dynamic spatiotemporal warping for the detection and location of myocardial infarctions. / Kan, Chen; Yang, Hui.

2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012. 2012. p. 1046-1051 6386354.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Dynamic spatiotemporal warping for the detection and location of myocardial infarctions

AU - Kan, Chen

AU - Yang, Hui

PY - 2012

Y1 - 2012

N2 - Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7% for separating MIs and HCs and an accuracy of 96.5% for anterior-related MIs and inferior-related MIs.

AB - Myocardial infarction (MI), also known as heart attack, is the leading cause of death - about 452,000 per year - in US. It often occurs due to the occlusion of coronary arteries, thereby leading to the insufficient blood and oxygen supply that damage cardiac muscle cells. Because the blood vessels are all over the heart, MI can happen at different spatial locations (e.g., anterior and inferior portions) of the heart. The spatial location of diseases causes the variable excitation and propagation of cardiac electrical activities in space and time. Most of previous studies focused on the relationships between disease and time-domain biomarkers (e.g., QT interval, ST elevation/depression, heart rate) from 12-lead ECG signals. Few, if any, previous approaches have investigated how the spatial location of diseases will alter cardiac vectorcardiogram (VCG) signals in both space and time. This paper presents a novel warping approach to quantify the dissimilarity of disease-altered patterns in 3-lead spatiotemporal VCG signals. The hypothesis testing shows there are significant spatiotemporal differences between healthy controls (HC), MI-anterior, MI-anterior-septal, MI-anterior-lateral, MI-inferior, and MI-inferior-lateral. Further, we optimize the embedding of each functional recording as a feature vector in the high-dimensional space that preserves the dissimilarity distance matrix. This novel spatial embedding approach facilitates the construction of classification models and yields an accuracy of 94.7% for separating MIs and HCs and an accuracy of 96.5% for anterior-related MIs and inferior-related MIs.

UR - http://www.scopus.com/inward/record.url?scp=84872530159&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872530159&partnerID=8YFLogxK

U2 - 10.1109/CoASE.2012.6386354

DO - 10.1109/CoASE.2012.6386354

M3 - Conference contribution

SN - 9781467304283

SP - 1046

EP - 1051

BT - 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012

ER -

Kan C, Yang H. Dynamic spatiotemporal warping for the detection and location of myocardial infarctions. In 2012 IEEE International Conference on Automation Science and Engineering: Green Automation Toward a Sustainable Society, CASE 2012. 2012. p. 1046-1051. 6386354 https://doi.org/10.1109/CoASE.2012.6386354