Automated ECG Waveform Annotation Based on Stacked Long Short-Term Memory

Annisa Darmawahyuni; Siti Nurmaini; Muhammad Naufal Rachmatullah

doi:10.18495/comengapp.v9i2.341

[1] P. Sodmann, M. Vollmer, N. Nath, and L. Kaderali, “A convolutional neural network for ECG annotation as the basis for classification of cardiac rhythms,” Physiol. Meas., vol. 39, no. 10, p. 104005, 2018.
[2] A. Darmawahyuni, S. Nurmaini, W. Caesarendra, V. Bhayyu, M. N. Rachmatullah, and others, “Deep Learning with a Recurrent Network Structure in the Sequence Modeling of Imbalanced Data for ECG-Rhythm Classifier,” Algorithms, vol. 12, no. 6, p. 118, 2019.
[3] A. Darmawahyuni, “Coronary Heart Disease Interpretation Based on Deep Neural Network,” Comput. Eng. Appl. J., vol. 8, no. 1, 2019.
[4] M. A. C. Gil, “A new, simpler and better correction formula for the QT interval,” J. Am. Coll. Cardiol., vol. 61, no. 10 Supplement, p. E294, 2013.
[5] B. Vandenberk et al., “Which QT correction formulae to use for QT monitoring?,” J. Am. Heart Assoc., vol. 5, no. 6, p. e003264, 2016.
[6] N. Nuryani, M. Solikhah, A. S. Nugoho, A. Afdala, and E. Anzihory, “RR-Interval variance of electrocardiogram for atrial fibrillation detection,” in Journal of Physics: Conference Series, 2016, vol. 776, no. 1, p. 12105.
[7] I. Beraza and I. Romero, “Comparative study of algorithms for ECG segmentation,” Biomed. Signal Process. Control, vol. 34, pp. 166–173, 2017.
[8] S. Nurmaini, A. Gani, and others, “Cardiac Arrhythmias Classification Using Deep Neural Networks and Principle Component Analysis Algorithm.,” Int. J. Adv. Soft Comput. Its Appl., vol. 10, no. 2, 2018.
[9] Siti Nurmaini, Radiyati Umi Partan, Muhammad Naufal Rachmatullah, “Deep Neural Networks Classifiers on The Electrocardiogram Signal for Intelligent Interpretation System,” Sriwij. Int. Conf. Med. Sci., 2018.
[10] P. Laguna, R. Jané, and P. Caminal, “Automatic detection of wave boundaries in multilead ECG signals: Validation with the CSE database,” Comput. Biomed. Res., vol. 27, no. 1, pp. 45–60, 1994.
[11] M. Akhbari, M. B. Shamsollahi, O. Sayadi, A. A. Armoundas, and C. Jutten, “ECG segmentation and fiducial point extraction using multi hidden Markov model,” Comput. Biol. Med., vol. 79, pp. 21–29, 2016.
[12] A. Ghaffari, M. R. Homaeinezhad, M. Khazraee, and M. M. Daevaeiha, “Segmentation of holter ECG waves via analysis of a discrete wavelet-derived multiple skewness--kurtosis based metric,” Ann. Biomed. Eng., vol. 38, no. 4, pp. 1497–1510, 2010.
[13] M. V\’\itek, J. Hrubeš, and J. Kozumpl\’\ik, “A wavelet-based ECG delineation with improved P wave offset detection accuracy,” Anal. Biomed. Signals Images, vol. 20, pp. 160–165, 2010.
[14] C. R. Vázquez-Seisdedos, J. E. Neto, E. J. M. Reyes, A. Klautau, and R. C. L. de Oliveira, “New approach for T-wave end detection on electrocardiogram: Performance in noisy conditions,” Biomed. Eng. Online, vol. 10, no. 1, p. 77, 2011.
[15] P. Laguna, R. G. Mark, A. Goldberg, and G. B. Moody, “A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG,” in Computers in cardiology 1997, 1997, pp. 673–676.
[16] J. Wang, Y. Ye, X. Pan, and X. Gao, “Parallel-type fractional zero-phase filtering for ECG signal denoising,” Biomed. Signal Process. Control, vol. 18, pp. 36–41, 2015.
[17] R. Cohen, “Signal denoising using wavelets,” 2012.
[18] Z. Wang, J. Zhu, T. Yan, and L. Yang, “A new modified wavelet-based ECG denoising,” Comput. Assist. Surg., pp. 1–10, 2019.
[19] Ö. Yildirim, “A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification,” Comput. Biol. Med., vol. 96, pp. 189–202, 2018.
[20] Q. Qin, J. Li, L. Zhang, Y. Yue, and C. Liu, “Combining low-dimensional wavelet features and support vector machine for arrhythmia beat classification,” Sci. Rep., vol. 7, no. 1, p. 6067, 2017.
[21] M. Sharma and U. R. Acharya, “A new method to identify coronary artery disease with ECG signals and time-Frequency concentrated antisymmetric biorthogonal wavelet filter bank,” Pattern Recognit. Lett., vol. 125, pp. 235–240, 2019.
[22] K. Mourad and B. R. Fethi, “Efficient automatic detection of QRS complexes in ECG signal based on reverse biorthogonal wavelet decomposition and nonlinear filtering,” Measurement, vol. 94, pp. 663–670, 2016.
[23] R. Jozefowicz, W. Zaremba, and I. Sutskever, “An empirical exploration of recurrent network architectures,” in International Conference on Machine Learning, 2015, pp. 2342–2350.
[24] Y. Su, Y. Huang, and C.-C. J. Kuo, “Dependent Bidirectional RNN with Extended-long Short-term Memory,” 2018.

Abstract viewed - 1420 times
PDF downloaded - 1006 times

Affiliations

Annisa Darmawahyuni
Affiliation not stated

Siti Nurmaini
Affiliation not stated

Muhammad Naufal Rachmatullah
Affiliation not stated

Content Top

Automated ECG Waveform Annotation Based on Stacked Long Short-Term Memory

Annisa Darmawahyuni ,
Siti Nurmaini ,
Muhammad Naufal Rachmatullah

Vol 9 No 2 (2020)

DOI 10.18495/comengapp.v9i2.341

Submitted: May 30, 2020

Published: Jun 1, 2020

Abstract

The classification of electrocardiogram (ECG) waveform segmentation techniques can be difficult due to physiological variation of heart rate and different characteristics of the different ECG waves in terms of shape, frequency, amplitude, and duration. The P-wave, PR-segment, QRS-complex, ST-segment, and T-wave are extracted as the feature for classification algorithm to diagnose specified cardiac disorders. This requires the implementation of algorithms that identify specific points within the ECG wave. Some previous computational algorithms for automatic classification of ECG segmentation are proposed to overcome limitations of manual inspection of the ECG. This study presents new insight into the ECG semantic segmentation problem is surmounted by a deep learning approach for automatic ECG wave-form. Long short-term memory (LSTM) is proposed for this task. This experimental study has been performed for six different waveforms of ECG signal that represents cardiac disorders obtained from the Physionet: QT database. Overall, LSTM performance achieved accuracy, sensitivity, specificity, precision, F1-score, is 93.36%, 86.85%, 95.78%, 81.79%, and 83.09%, respectively.