An Innovative Approach for the Prediction of Future Arrhythmia through T-wave Alternans on Surface Electrocardiogram (ECG)
DOI:
https://doi.org/10.51253/pafmj.v73i6.4846Keywords:
Arrhythmia, Electrocardiogram, Python, MATLAB, T-waveAbstract
Objective: To explore the techniques for predicting risk-causing arrhythmia in cardiac patients.
Study Design: Prospective longitudinal Study
Place and Duration of Study: Armed Forces Institute of Cardiology, Rawalpindi Pakistan, and Government College
University, Faisalabad from Jul to Oct 2017.
Methodology: The Electrocardiograms of 24-hour Holter monitoring were collected from the Electrophysiology Department. Electrocardiogram data was collected in the portable document format that was further transformed into Image format for computational analysis. Administrative data were analysed in multiple episodes of cardiac arrhythmogenesis. Data were classified by using a Convolutional Neural Network (CNN) based on computing the results of selected T-waves in three consecutive peaks within each cardiac cycle of patients.
Results: One hundred twenty-six patients diagnosed with arrhythmia were selected. The mean episode of premature
ventricular contractions in participants was 21.5±30. The mean duration of significant ECG episodes was 3.33±9.65 (seconds). The accuracy and precision rate of the classifier was about 81% for the overall significance of data that exhibited the risk of causing future life-threatening arrhythmia.
Conclusion: This study introduces an innovative approach based on clinical paradigms that may help prevent the upcoming
cardiac arrhythmogenesis events.
Downloads
Metrics
References
Trongtorsak A, Thangjui S, Chaisidhivej N, Sharma A,Ariyachaipanich A. A Premature Ventricular Contraction
Associated With Transient Worsening Pulsus Alternans: A CaseReport. Cureus 2021; 13(12): e20284.https://doi.org/10.7759/cureus.20284.
Antzelevitch C, Burashnikov A. Overview of basic mechanismsof cardiac arrhythmia. Card Electrophysiol Clin 2011; 3(1): 23-45.https://doi.org/10.1016%2Fj.ccep.2010.10.012
Sahambi J, Tandon S, Bhatt R. Using wavelet transforms for ECGcharacterization. An on-line digital signal processing system.IEEE Eng Med Biol 1997; 16(1): 77-83.https://doi.org/10.1109/51.566158
Lauder B, Schwerin B, McConnell M, editors. Using dynamictime warping for noise robust ecg r-peak detection. 13th
International Conference on Signal Processing andCommunication Systems (ICSPCS); 2019: IEEE.https://doi.org/10.1109/ICSPCS47537.2019.9008758
Kelwade J, Salankar S. Prediction of cardiac arrhythmia usingartificial neural network. Int J Comp Appl 2015; 115(20): 30-35.
http://doi.org/10.5120/20270-2679
Zhang C, Wang G, Zhao J, Gao P, Lin J, Yang H, et al. editors.Patient-specific ECG classification based on recurrent neural
networks and clustering technique. 13th IASTED InternationalConference on Biomedical Engineering (BioMed); 2017: IEEE.
http://doi.org/10.2316/P.2017.852-029
Ghassemi MM, Moody BE, Lehman L-WH, Song C, Li Q, Sun H,et al., editors. You snooze, you win: the physionet/computing incardiology challenge. 2018 Computing in Cardiology Conference(CinC); 2018: IEEE. https://doi.org/10.22489%2Fcinc.2018.049
Martínez JP, Olmos SJIToBE. Methodological principles of Twave alternans analysis: a unified framework. Transact Biomed
Eng 2005; 52(4): 599-613.https://doi.org/10.1109/tbme.2005.844025
Li T, Zhou M. ECG Classification Using Wavelet Packet Entropyand Random Forests. Entropy 2016; 18(8): 285.
https://doi.org/10.3390/e18080285
Garg DK, Thakur D, Sharma S, Bhardwaj S. ECG paper recordsdigitization through image processing techniques. Entropy 2012;48(13): 35-38. http://doi.org/10.5120/7411-0485
Lin C-W, Chang Y, Lin C-CK, Tsai L-M, Chen J-Y, editors.Development of an AI-based non-invasive Pulse AudioGram
monitoring device for arrhythmia screening. IEEE HealthcareInnovations and Point of Care Technologies (HI-POCT); 2017:
IEEE. http://doi.org/10.1109/HIC.2017.8227579
Aro AL, Kenttä TV, Huikuri HV. Microvolt T-wavealternans: where are we now? Arrhythmia Electrophysiol Rev
; 5(1): 37–40. https://doi.org/10.15420/aer.2015.28.1
Vavrinsky E, Subjak J, Donoval M, Wagner A, Zavodnik T,Svobodova H. Application of Modern Multi-Sensor Holter in
Diagnosis and Treatment. Sensors 2020; 20(9): 2663.https://doi.org/10.3390/s20092663
Bayer J, Lalani G, Vigmond E, Narayan S, TrayanovaNJHR. Mechanisms linking electrical alternans and clinical
ventricular arrhythmia in human heart failure. Heart Rhythm2016; 13(9): 1922-1931.https://doi.org/10.1016/j.hrthm.2016.05.017
García M, Ródenas J, Alcaraz R, Rieta J. Application of therelative wavelet energy to heart rate independent detection of
atrial fibrillation. Compt Methods Programs Biomed 2016; 131:157-168. https://doi.org/10.1016/j.cmpb.2016.04.009
Holmgren WF, Hansen CW, Mikofski M. pvlib python: a pythonpackage for modeling solar energy systems. J Open Source Softw2018; 3(29): 884. http://doi.org/10.21105/joss.0088417 Walczak S. Artificial neural networks. Encyclopedia ofInformation Science and Technology, Fourth Edition: IGI Global;2018. p. 120-131.https://doi: 10.4018/978-1-5225-7368-5.ch004
Huang J, Chen B, Yao B, He W. "ECG Arrhythmia ClassificationUsing STFT-Based Spectrogram and Convolutional Neural
Network," in IEEE Access 2019(7): 92871-92880.http://doi.org/10.1109/ACCESS.2019.2928017
Viloria A, Lezama OBP, Varela N. Bayesian classifier applied tohigher education dropout. Procedia Comput Sci 2019; 160: 573-577. https://doi.org/10.1016/j.procs.2019.11.045
Downloads
Published
How to Cite
Issue
Section
