Transient ST-segment episode detection for ECG beat classification

Suma C. Bulusu, Miad Faezipour, Vincent Ng, Mehrdad Nourani, Lakshman S. Tamil, Subhash Banerjee

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

15 Citations (Scopus)

Abstract

Sudden Cardiac Death (SCD) is an unexpected death caused by loss of heart function when the electrical impulses fired from the ventricles become irregular. Most common SCDs are caused by cardiac arrhythmias and coronary heart disease. They are mainly due to Acute Myocardial Infarction (AMI), myocardial ischaemia and cardiac arrhythmia. This paper aims at automating the recognition of ST-segment deviations and transient ST episodes which helps in the diagnosis of myocardial ischaemia and also classifying major cardiac arrhythmia. Our approach is based on the application of signal processing and artificial intelligence to the heart signal known as the ECG (Electrocardiogram). We propose an improved morphological feature vector including ST-segment information for heart beat classification by supervised learning using the support vector machine approach. Our system has been tested and yielded an accuracy of 93.33% for the ST episode detection on the European ST-T Database and 96.35% on MIT-BIH Arrhythmia Database for classifying six major groups, i.e. Normal, Ventricular, Atrial, Fusion, Right Bundle and Left Bundle Branch Block beats.

Original languageEnglish (US)
Title of host publicationProceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011
Pages121-124
Number of pages4
DOIs
StatePublished - 2011
Event2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011 - Bethesda, MD, United States
Duration: Apr 7 2011Apr 8 2011

Other

Other2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011
CountryUnited States
CityBethesda, MD
Period4/7/114/8/11

Fingerprint

death
artificial intelligence
heart disease
learning
Group

ASJC Scopus subject areas

  • Life-span and Life-course Studies

Cite this

Bulusu, S. C., Faezipour, M., Ng, V., Nourani, M., Tamil, L. S., & Banerjee, S. (2011). Transient ST-segment episode detection for ECG beat classification. In Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011 (pp. 121-124). [5754171] https://doi.org/10.1109/LISSA.2011.5754171

Transient ST-segment episode detection for ECG beat classification. / Bulusu, Suma C.; Faezipour, Miad; Ng, Vincent; Nourani, Mehrdad; Tamil, Lakshman S.; Banerjee, Subhash.

Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011. 2011. p. 121-124 5754171.

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

Bulusu, SC, Faezipour, M, Ng, V, Nourani, M, Tamil, LS & Banerjee, S 2011, Transient ST-segment episode detection for ECG beat classification. in Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011., 5754171, pp. 121-124, 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011, Bethesda, MD, United States, 4/7/11. https://doi.org/10.1109/LISSA.2011.5754171
Bulusu SC, Faezipour M, Ng V, Nourani M, Tamil LS, Banerjee S. Transient ST-segment episode detection for ECG beat classification. In Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011. 2011. p. 121-124. 5754171 https://doi.org/10.1109/LISSA.2011.5754171
Bulusu, Suma C. ; Faezipour, Miad ; Ng, Vincent ; Nourani, Mehrdad ; Tamil, Lakshman S. ; Banerjee, Subhash. / Transient ST-segment episode detection for ECG beat classification. Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011. 2011. pp. 121-124
@inproceedings{846e95f9748248d48901f269f949ef10,
title = "Transient ST-segment episode detection for ECG beat classification",
abstract = "Sudden Cardiac Death (SCD) is an unexpected death caused by loss of heart function when the electrical impulses fired from the ventricles become irregular. Most common SCDs are caused by cardiac arrhythmias and coronary heart disease. They are mainly due to Acute Myocardial Infarction (AMI), myocardial ischaemia and cardiac arrhythmia. This paper aims at automating the recognition of ST-segment deviations and transient ST episodes which helps in the diagnosis of myocardial ischaemia and also classifying major cardiac arrhythmia. Our approach is based on the application of signal processing and artificial intelligence to the heart signal known as the ECG (Electrocardiogram). We propose an improved morphological feature vector including ST-segment information for heart beat classification by supervised learning using the support vector machine approach. Our system has been tested and yielded an accuracy of 93.33{\%} for the ST episode detection on the European ST-T Database and 96.35{\%} on MIT-BIH Arrhythmia Database for classifying six major groups, i.e. Normal, Ventricular, Atrial, Fusion, Right Bundle and Left Bundle Branch Block beats.",
author = "Bulusu, {Suma C.} and Miad Faezipour and Vincent Ng and Mehrdad Nourani and Tamil, {Lakshman S.} and Subhash Banerjee",
year = "2011",
doi = "10.1109/LISSA.2011.5754171",
language = "English (US)",
isbn = "9781457704208",
pages = "121--124",
booktitle = "Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011",

}

TY - GEN

T1 - Transient ST-segment episode detection for ECG beat classification

AU - Bulusu, Suma C.

AU - Faezipour, Miad

AU - Ng, Vincent

AU - Nourani, Mehrdad

AU - Tamil, Lakshman S.

AU - Banerjee, Subhash

PY - 2011

Y1 - 2011

N2 - Sudden Cardiac Death (SCD) is an unexpected death caused by loss of heart function when the electrical impulses fired from the ventricles become irregular. Most common SCDs are caused by cardiac arrhythmias and coronary heart disease. They are mainly due to Acute Myocardial Infarction (AMI), myocardial ischaemia and cardiac arrhythmia. This paper aims at automating the recognition of ST-segment deviations and transient ST episodes which helps in the diagnosis of myocardial ischaemia and also classifying major cardiac arrhythmia. Our approach is based on the application of signal processing and artificial intelligence to the heart signal known as the ECG (Electrocardiogram). We propose an improved morphological feature vector including ST-segment information for heart beat classification by supervised learning using the support vector machine approach. Our system has been tested and yielded an accuracy of 93.33% for the ST episode detection on the European ST-T Database and 96.35% on MIT-BIH Arrhythmia Database for classifying six major groups, i.e. Normal, Ventricular, Atrial, Fusion, Right Bundle and Left Bundle Branch Block beats.

AB - Sudden Cardiac Death (SCD) is an unexpected death caused by loss of heart function when the electrical impulses fired from the ventricles become irregular. Most common SCDs are caused by cardiac arrhythmias and coronary heart disease. They are mainly due to Acute Myocardial Infarction (AMI), myocardial ischaemia and cardiac arrhythmia. This paper aims at automating the recognition of ST-segment deviations and transient ST episodes which helps in the diagnosis of myocardial ischaemia and also classifying major cardiac arrhythmia. Our approach is based on the application of signal processing and artificial intelligence to the heart signal known as the ECG (Electrocardiogram). We propose an improved morphological feature vector including ST-segment information for heart beat classification by supervised learning using the support vector machine approach. Our system has been tested and yielded an accuracy of 93.33% for the ST episode detection on the European ST-T Database and 96.35% on MIT-BIH Arrhythmia Database for classifying six major groups, i.e. Normal, Ventricular, Atrial, Fusion, Right Bundle and Left Bundle Branch Block beats.

UR - http://www.scopus.com/inward/record.url?scp=79956086850&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956086850&partnerID=8YFLogxK

U2 - 10.1109/LISSA.2011.5754171

DO - 10.1109/LISSA.2011.5754171

M3 - Conference contribution

AN - SCOPUS:79956086850

SN - 9781457704208

SP - 121

EP - 124

BT - Proceedings of the 2011 IEEE/NIH Life Science Systems and Applications Workshop, LiSSA 2011

ER -