TY - GEN
T1 - An efficient technique for automated diagnosis of cardiac rhythms using electrocardiogram
AU - Desai, Usha
AU - Nayak, C. Gurudas
AU - Seshikala, G.
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/1/5
Y1 - 2017/1/5
N2 - Electrocardiogram (ECG) is the most reliable and low-cost diagnostic tool to evaluate the patients with cardiac arrhythmias. Manual diagnosis of arrhythmia beats is very tedious due to the nonlinear and complex nature of ECG. The current paper, describes pattern recognition and machine learning-based approach for computer-Aided detection of five classes of ECG arrhythmia beats using Discrete Cosine Transform (DCT) coefficients. Further, methodology comprises dimensionality reduction using Independent Component Analysis (ICA), ten-fold cross-validation and diagnosis using Support Vector Machine (SVM) quadratic kernel function. Using ANOVA clinically (p<0.05) and statistically (F-value) significant features are selected and reliability of accuracy is measured by Cohen's kappa (κ) statistic. Large database of 110,093 heartbeats from 48 records of MIT-BIH Arrhythmia Database recommended by ANSI/AAMI EC57:1998, which are grouped into five classes of arrhythmia beats viz. Non-ectopic (N), Ventricular ectopic (V), Supraventricular ectopic (S), Fusion (F) and Unknown (U) are classified with class-specific accuracy of 98.75%, 89.38%, 82.2%, 47.04% and 90.57%, respectively and an overall accuracy of 95.98%. The developed methodology is an efficient tool, which has intensive applications in early diagnosis, mass screening of cardiac health and in cardiac theoretic devices such as pacemaker systems.
AB - Electrocardiogram (ECG) is the most reliable and low-cost diagnostic tool to evaluate the patients with cardiac arrhythmias. Manual diagnosis of arrhythmia beats is very tedious due to the nonlinear and complex nature of ECG. The current paper, describes pattern recognition and machine learning-based approach for computer-Aided detection of five classes of ECG arrhythmia beats using Discrete Cosine Transform (DCT) coefficients. Further, methodology comprises dimensionality reduction using Independent Component Analysis (ICA), ten-fold cross-validation and diagnosis using Support Vector Machine (SVM) quadratic kernel function. Using ANOVA clinically (p<0.05) and statistically (F-value) significant features are selected and reliability of accuracy is measured by Cohen's kappa (κ) statistic. Large database of 110,093 heartbeats from 48 records of MIT-BIH Arrhythmia Database recommended by ANSI/AAMI EC57:1998, which are grouped into five classes of arrhythmia beats viz. Non-ectopic (N), Ventricular ectopic (V), Supraventricular ectopic (S), Fusion (F) and Unknown (U) are classified with class-specific accuracy of 98.75%, 89.38%, 82.2%, 47.04% and 90.57%, respectively and an overall accuracy of 95.98%. The developed methodology is an efficient tool, which has intensive applications in early diagnosis, mass screening of cardiac health and in cardiac theoretic devices such as pacemaker systems.
UR - https://www.scopus.com/pages/publications/85015026248
UR - https://www.scopus.com/inward/citedby.url?scp=85015026248&partnerID=8YFLogxK
U2 - 10.1109/RTEICT.2016.7807770
DO - 10.1109/RTEICT.2016.7807770
M3 - Conference contribution
AN - SCOPUS:85015026248
T3 - 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings
SP - 5
EP - 8
BT - 2016 IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 1st IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2016
Y2 - 20 May 2016 through 21 May 2016
ER -