Abstract
Introduction: A progressive and flourishing technological advancement occurs across the communities working on a domain that needs clinical training and Technology Transfer. There is an essentiality for the evolution of advanced concepts in the Classification of healthcare, particularly in relation to arrhythmia detection towards clinical operations. Being the forerunner among the emerging areas in science and technology, this field demands an extensive practical and verification research. These innovative technological progress has significantly contributed to highquality, on-time, acceptable and affordable healthcare.
Materials & Methods: This paper approaches a novel method of Detecting and classifying the cardiac arrhythmias using deep learning model for classification of electrocardiogram (ECG) signals. This method is based on using Cubic Wavelet Transform for analyzing the ECG signals and extracting the parameters related to dangerous cardiac arrhythmias.
Results & Discussion: In these parameters are used as input to these classifier, five most important types of ECG signals they are Normal Sinus Rhythm (NSR), Atrial Fibrillation (AF), Pre- Ventricular Contraction (PVC), Ventricular Fibrillation (VF), and Ventricular Flutter (VFLU). By using the deep learning algorithm to recognition and classification capabilities across a broad area of biomedical engineering. The performance of the deep learning model was evaluated in terms of training performance and classification accuracies. The classification accuracy of 99.24% is achieved. Good accuracy of ECG patterns is achievable only over a large number of files.
Conclusion: These difficulties have necessitated us to develop a new detection scheme, which gives a high level of accuracy, low false positive and low false-negative statistics.
Keywords: ECG, feature extraction, segmentation, prediction, five cardiac arrhythmias, diagnosis, deep learning.
Graphical Abstract
[http://dx.doi.org/10.1109/TBME.1985.325532] [PMID: 3997178]
[http://dx.doi.org/10.1109/TBME.1986.325695] [PMID: 3817849]
[http://dx.doi.org/10.1109/10.740882] [PMID: 9932341]
[http://dx.doi.org/10.1109/18.57199]
[http://dx.doi.org/10.1007/978-3-319-67262-5_17]
[http://dx.doi.org/10.1109/EMBC.2015.7320186]
[http://dx.doi.org/10.1109/DeSE.2011.67]
[http://dx.doi.org/10.1145/2932707]
[http://dx.doi.org/10.1038/s41598-017-09837-3] [PMID: 28874683 ]