Abstract

Early detection of Myocardial Infarction (MI) and Congestive Heart Failure (CHF) Cardiovascular Diseases (CVDs) are challenging diseases for cardiologist practioners to reduce the mortality rate. This paper deals with the design and development of an automated Ensemble Classification system using optimized Heterogeneous Features set viz. Morphological/Structural and Statistical Non Linear features of Electrocardiogram (ECG) Signal. ECG is non-invasive and vital clinical therapeutic agent deployed for taking intelligent health care prediction of MI and CHF. In this approach, the ensembles of classifiers are performed by taking into account diversity and accuracy of multi classifiers in intelligible hybridization manner with majority voting technique in ECG pattern recognition. Proposed methodology achieved the maximum Accuracy, Sensitivity, Specificity of 99.75%, 99.72%, 99.85% respectively, along with Precision, Recall and F1-Score statistical indices ranging from 0.9 to 1 value, taking into account 300 patient’s ECG signals collected from diverse databases. The time required for execution of the system is 0.55 seconds. Computation time is reduced to greater extend with directly evaluation of the features from the ECG signal analyzed on the morphological and statistical domain, so, the detection of R-peaks are eliminated with the proper selection of derivative levels.

References

• A. J. Moss and S. Stern, Noninvasive Electro cardiology, C. A. of Holter, Ed. London, Philadel- phia, W.B. Saunder, 1996.
• R. S. Khadpur, Handbook of Biomedical Instrumentation. Tata McGraw Hill, 2010.
• N. Safdarian , N.J. Dabanloo , G. Attarodi ,A new pattern recognition method for detection and localization of myocardial infarction using T-wave integral and total integral as extracted features from one cycle of ECG signal, J. Biomed. Sci. Eng. 7 (2014) 818–824.
• L. Sun , Y. Lu , K. Yang , S. Li , ECG analysis using multiple instance learning for myocardial infarction detection, IEEE Trans. Biomed. Eng. 59 (12) (2012).
• Mohit Kumar, Ram Bilas Pachori, U. Rajendra Acharya, “Use of Accumulated Entropies for Automated Detection of Congestive Heart Failure in Flexible Analytic Wavelet Transform Framework Based on Short-Term HRV Signals”, MDPI, Entropy 2017, 19, 92; doi:10.3390/e19030092, 2017.
• R.K. Tripathy, Mario R.A. Paternina, Juan G. Arrieta, Alejandro Zamora-Méndez, Ganesh R. Naik, “Automated detection of congestive heart failure from electrocardiogram signal using Stockwell transform and hybrid classification scheme”, Elsevier, Computer Methods and Programs in Biomedicine 173 (2019), pp. 53–65.
• Mihaela, Ernesto Iadanzab, Sebastiano Massaroc, Leandro Pecchiaa, “A convolutional neural network approach to detect congestive heart failure”, Science Direct, Biomedical Signal Processing and Control 55 (2020) 101597.
• Sushree Satvatee Swain, Dipti Patra, Yengkhom Omesh Singh, “Automated detection of myocardial infarction in ECG using modified Stockwell transform and phase distribution pattern from time-frequency analysis”, Science Direct, Bio-cybernetics and Biomedical Engineering, 40, June (2020), pp. 1174-1189.
• Kamal Jafarian, VahabVahdat, Seyed mohammad Salehi, Mohammad sadegh Mobin, “Automating detection and localization of myocardial infarction using shallow and end-to-end deep neural networks”, Science Direct, Applied Soft Computing Journal 93, May (2020) 106383.
• Ashok Kumar Dohare, Vinod Kumar, Ritesh Kumar, “Detection of myocardial infarction in 12 lead ECG using support vector machine”, Elsevier, Applied Soft Computing 64 (2018),pp. 138–147.
• A. L. Goldberger, L.A .N. Amaral, L. Glass, J.M. Hausdorff, P.C.H Ivanov, R.G. Mark, J.E. Mietus, G.B. Moody, C.K. Peng, H.E. Stanley, “PhysioBank, physioToolkit, and physioNet: components of a new research resource for complex physiologic signals”, Circulation 101 (23) (2000) , pp. 215–220.
• Goldberger AL, Rigney DR, Mietus J, Antman EM, Greenwald S. Nonlinear dynamics in sudden cardiac death syndrome: heartrate oscillations bifurcations. Experientia 1988 Dec 1; 44 (11–12):983–987.
• J.S.Karnewar, Dr.V.K.Shandilya, “Automated Detection of Myocardial Infarction and Dilated Cardiomyopathy using Machine Learning”, Turkish Journal of Physiotherapy and Rehabilitation; 32(3) ISSN 2651-4451 | e-ISSN 2651-446X, December 2021.
• M.A. Awal, S.S. Mostafa, M. Ahmad, M.A. Rashid, “An adaptive level dependent wavelet thresholding for ECG denoising”, Bio cybernetics Biomed. Eng.34 (2014), pp. 238–249.
• R.G. Afkhami, G. Azarnia, M.A. Tinati, Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals, Pattern Recogn. Lett. 70 (2016) pp.45–51.
• Baek HJ, Cho CH, Cho J, Woo JM. Reliability of ultra-short-term analysis as a surrogate of standard 5-min analysis of heart rate variability. Telemed J E Health (2015) 21:404–14.
• T. Woloszynski, M. Kurzynski, P. Podsiadlo, G. Stachowiak, A measure of competence based on random classification for dynamic ensemble selection, Information Fusion 13 (3) (2012) 207–213.
• Batra, A. and Jawa, V. (2016). Classification of Arrhythmia using Conjunction of Machine Learning Algorithms and ECG Diagnostic Criteria, International Journal of Biology and Biomedicine, vo1.1, pp.1-7.
• B. Krawczyk, M. Wozniak, Privacy preserving models of k-NN algorithm, in: R. Burduk, M. Kurzynski, M. Wozniak, A. Zolnierek (Eds.), Computer Recognition Systems 4, Advances in Intelligent and Soft Computing, vol. 95, Springer, Berlin/Heidelberg, 2011, pp. 207–217.
• D. Ruta, B. Gabrys, Classifier selection for majority voting, Information Fusion 6 (1) (2005) 63–81.
• R. Banfield, L. Hall, K. Bowyer, W. Kegelmeyer, Ensemble diversity measures and their application to thinning, Information Fusion 6 (1) (2005) 49–62.
• Markoulidakis Rallis, “Multiclass Confusion Matrix Reduction Method and Its Application”, MDPI, Technologies 2021, 9(4).