Application of ensemble classifiers in accurate diagnosis of myocardial ischemia conditions

Usha Desai, C. Gurudas Nayak, G. Seshikala

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Myocardial ischemia (MI) is abnormal cardiac condition during which myocardium is deprived of blood and oxygen supply. It is the most prominent heart disease around the globe, and its prevalence increases with age factors. Accurate and timely identification and treatment of MI help to prevent from series of dreadful ischemic heart diseases such as heart attack and heart failure. However, the manual interpretation of electrocardiogram (ECG) for diagnosis of MI is tedious task for physicians. Hence, automated classification is very useful for diagnosis of MI condition. Our study presents an approach for automated diagnosis of MI condition using ECG beats. In this methodology, non-linearity in ECG is finely captured using higher-order statistics (HOS), and then, dimensionality is reduced. Confidence interval of features is verified using Student’s t-test (probability (p)-value <0.05). Decision Tree (DT) as the base classifier following different ensemble classifiers, viz. Adaboost (ADB), Bagging (BGG), Rotation Forest (ROF) and Random Forest (RAF) are subjected for diagnosis of normal sinus rhythm (NSR) against MI conditions. Among these, ROF is diagnosed with 99.51 ± 0.31 % accuracy, 98.82 ± 1.04 % sensitivity and 99.83 ± 0.15 % specificity. In this system, higher specificity rate defines precision in diagnosis of True Negative (TN) condition. Results achieved in this study are efficient with 0.9886 of Matthews correlation coefficient (MCC). Our proposed system is non-invasive and cost-efficient and helps in screening of MI, predominantly in rural and remote areas.

Original languageEnglish
Pages (from-to)245-253
Number of pages9
JournalProgress in Artificial Intelligence
Volume6
Issue number3
DOIs
Publication statusPublished - 01-09-2017

Fingerprint

Classifiers
Electrocardiography
Oxygen supply
Higher order statistics
Adaptive boosting
Decision trees
Screening
Blood
Students
Costs

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

@article{2fd17597c3154edc8fa43d9bbb4e48c3,
title = "Application of ensemble classifiers in accurate diagnosis of myocardial ischemia conditions",
abstract = "Myocardial ischemia (MI) is abnormal cardiac condition during which myocardium is deprived of blood and oxygen supply. It is the most prominent heart disease around the globe, and its prevalence increases with age factors. Accurate and timely identification and treatment of MI help to prevent from series of dreadful ischemic heart diseases such as heart attack and heart failure. However, the manual interpretation of electrocardiogram (ECG) for diagnosis of MI is tedious task for physicians. Hence, automated classification is very useful for diagnosis of MI condition. Our study presents an approach for automated diagnosis of MI condition using ECG beats. In this methodology, non-linearity in ECG is finely captured using higher-order statistics (HOS), and then, dimensionality is reduced. Confidence interval of features is verified using Student’s t-test (probability (p)-value <0.05). Decision Tree (DT) as the base classifier following different ensemble classifiers, viz. Adaboost (ADB), Bagging (BGG), Rotation Forest (ROF) and Random Forest (RAF) are subjected for diagnosis of normal sinus rhythm (NSR) against MI conditions. Among these, ROF is diagnosed with 99.51 ± 0.31 {\%} accuracy, 98.82 ± 1.04 {\%} sensitivity and 99.83 ± 0.15 {\%} specificity. In this system, higher specificity rate defines precision in diagnosis of True Negative (TN) condition. Results achieved in this study are efficient with 0.9886 of Matthews correlation coefficient (MCC). Our proposed system is non-invasive and cost-efficient and helps in screening of MI, predominantly in rural and remote areas.",
author = "Usha Desai and Nayak, {C. Gurudas} and G. Seshikala",
year = "2017",
month = "9",
day = "1",
doi = "10.1007/s13748-017-0120-x",
language = "English",
volume = "6",
pages = "245--253",
journal = "Progress in Artificial Intelligence",
issn = "2192-6352",
publisher = "Springer Nature",
number = "3",

}

Application of ensemble classifiers in accurate diagnosis of myocardial ischemia conditions. / Desai, Usha; Nayak, C. Gurudas; Seshikala, G.

In: Progress in Artificial Intelligence, Vol. 6, No. 3, 01.09.2017, p. 245-253.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Application of ensemble classifiers in accurate diagnosis of myocardial ischemia conditions

AU - Desai, Usha

AU - Nayak, C. Gurudas

AU - Seshikala, G.

PY - 2017/9/1

Y1 - 2017/9/1

N2 - Myocardial ischemia (MI) is abnormal cardiac condition during which myocardium is deprived of blood and oxygen supply. It is the most prominent heart disease around the globe, and its prevalence increases with age factors. Accurate and timely identification and treatment of MI help to prevent from series of dreadful ischemic heart diseases such as heart attack and heart failure. However, the manual interpretation of electrocardiogram (ECG) for diagnosis of MI is tedious task for physicians. Hence, automated classification is very useful for diagnosis of MI condition. Our study presents an approach for automated diagnosis of MI condition using ECG beats. In this methodology, non-linearity in ECG is finely captured using higher-order statistics (HOS), and then, dimensionality is reduced. Confidence interval of features is verified using Student’s t-test (probability (p)-value <0.05). Decision Tree (DT) as the base classifier following different ensemble classifiers, viz. Adaboost (ADB), Bagging (BGG), Rotation Forest (ROF) and Random Forest (RAF) are subjected for diagnosis of normal sinus rhythm (NSR) against MI conditions. Among these, ROF is diagnosed with 99.51 ± 0.31 % accuracy, 98.82 ± 1.04 % sensitivity and 99.83 ± 0.15 % specificity. In this system, higher specificity rate defines precision in diagnosis of True Negative (TN) condition. Results achieved in this study are efficient with 0.9886 of Matthews correlation coefficient (MCC). Our proposed system is non-invasive and cost-efficient and helps in screening of MI, predominantly in rural and remote areas.

AB - Myocardial ischemia (MI) is abnormal cardiac condition during which myocardium is deprived of blood and oxygen supply. It is the most prominent heart disease around the globe, and its prevalence increases with age factors. Accurate and timely identification and treatment of MI help to prevent from series of dreadful ischemic heart diseases such as heart attack and heart failure. However, the manual interpretation of electrocardiogram (ECG) for diagnosis of MI is tedious task for physicians. Hence, automated classification is very useful for diagnosis of MI condition. Our study presents an approach for automated diagnosis of MI condition using ECG beats. In this methodology, non-linearity in ECG is finely captured using higher-order statistics (HOS), and then, dimensionality is reduced. Confidence interval of features is verified using Student’s t-test (probability (p)-value <0.05). Decision Tree (DT) as the base classifier following different ensemble classifiers, viz. Adaboost (ADB), Bagging (BGG), Rotation Forest (ROF) and Random Forest (RAF) are subjected for diagnosis of normal sinus rhythm (NSR) against MI conditions. Among these, ROF is diagnosed with 99.51 ± 0.31 % accuracy, 98.82 ± 1.04 % sensitivity and 99.83 ± 0.15 % specificity. In this system, higher specificity rate defines precision in diagnosis of True Negative (TN) condition. Results achieved in this study are efficient with 0.9886 of Matthews correlation coefficient (MCC). Our proposed system is non-invasive and cost-efficient and helps in screening of MI, predominantly in rural and remote areas.

UR - http://www.scopus.com/inward/record.url?scp=85053505787&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053505787&partnerID=8YFLogxK

U2 - 10.1007/s13748-017-0120-x

DO - 10.1007/s13748-017-0120-x

M3 - Article

VL - 6

SP - 245

EP - 253

JO - Progress in Artificial Intelligence

JF - Progress in Artificial Intelligence

SN - 2192-6352

IS - 3

ER -