Automated detection of cardiac arrhythmia using deep learning techniques
Authors: 
Swapna G, Soman K P, Vinayakumar RAuthors Info & Claims
Swapna G, Soman K P, Vinayakumar RAuthors Info & ClaimsAbstract
Cardiac arrhythmia is a condition where heart beat is irregular. The goal of this paper is to apply deep learning techniques in the diagnosis of cardiac arrhythmia using ECG signals with minimal possible data pre-processing. We employ convolutional neural network (CNN), recurrent structures such as recurrent neural network (RNN), long short-term memory (LSTM) and gated recurrent unit (GRU) and hybrid of CNN and recurrent structures to automatically detect the abnormality. Unlike the conventional analysis methods, deep learning algorithms don’t have feature extraction based analysis methods. The optimal parameters for deep learning techniques are chosen by conducting various trails of experiments. All trails of experiments are run for 1000 epochs with learning rate in the range [0.01-0.5]. We obtain five-fold cross validation accuracy of 0.834 in distinguishing normal and abnormal (cardiac arrhythmia) ECG with CNN-LSTM. Moreover, the accuracy obtained by other hybrid architectures of deep learning algorithms is comparable to the CNN-LSTM.
References
[1]
Naser Safdarian, Nader Jafarnia, Gholamreza 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., Journal of Biomedical Science and Engineering 7 (10) (2014) 818–824.
[2]
Sharma L.N., Tripathy R.K., Samarendra Dandapat, Multiscale energy and eigenspace approach to detection and localization of myocardial infarction., IEEE Transactions on biomedical engineering 62 (7) (2015) 1827–1837.
[3]
Rajendra Acharya U., Hamildo Fujita, VidyaK Sudarshan, Shu Lih Oh, Muhammad Adam, Automated detection and localization of myocardial infarction using electrocardiogram: A comparative study of different leads., Knowledge-Based Systems 99 (2016) 146–156.
[4]
Rajendra Acharya U., Hamildo Fujita, Shu Lih Oh, Yuki Hagiwara, Jen Hong Tan, Muhammad Adam, Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals., Information Sciences 415 (2017) 190–198.
[5]
Tahsin Reasat and Celia Shahnaz. (2017) “Detection of inferior myocardial infarction using shallow convolutional neural networks.” arXiv preprint arXiv:1710.01115.
[6]
Babak Mohammadzadeh-Asl and Seyed Kamaledin Setarehdan. (2006) “Neural network based arrhythmia classification using Heart Rate Variability signal.” In 14th EuropeanSignal Processing Conferencepages 1-4.
[7]
Abhinav-Vishwa Lal M.K., Dixit S, Vardwaj P, Clasification of arrhythmic ECG data using machine learning techniques., International Journal of Interactive Multimedia and Artificial Intelligence 1 (4) (2011) 67–70.
[8]
Goutham Swapna, DhanjooN Ghista, Roshan Joy Martis, AlvinPC Ang, Subbhuraam Vinitha Sree, ECG signal generation and heart rate variability signal extraction: Signal Processing, Feature detection, and their correlation with cardiac diseases., Journal of Mechanics in Medicine and Biology 12 (4) (2012) 1240012.
[9]
Sujadevi V.G., Soman K.P., and Vinayakumar R. (2017) “Real-time detection of atrial fibrillation from short time single lead ECG traces using recurrent neural networks.” in The International Symposium on Intelligent Systems Technologies and Applications pages 212–221 Springer.
[10]
Rahul K. Pathinarupothi, Vinayakumar R., Ekanath Rangan, Gopalakrishnan E., and Soman. K.P. (2017) “ Instantaneous heart rate as a robust feature for sleep apnea severity detection using deep learning.” in IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)pages 293-296.
[11]
AryL. Goldberger, LuisA.N. Amaral, Leon Glass, JeffreyM. Hausdorff, PlamenCh. Ivanov, RogerG. Mark, JosephE. Mietus, GeorgeB. Moody, Chung-Kang Peng, H. Eugene Stanley, PhysioBank, PhysioToolkit, and PhysioNet., Circulation 101 (23) (2000) 215–220.
[12]
JeffreyL. Elman, Finding structure in time., Cognitive Science 14 (2) (1990) 179–211.
[13]
Sepp Hochreiter, Jürgen Schmidhuber, Long short-term memory., Neural Computation 9 (8) (1997) 1735–1780.
[14]
FelixA. Gers, JürgenA. Schmidhuber, FredA. Cummins, “Learning to Forget: Continual prediction with LSTM, “Neural Computation 12 (10) (1999) 2451–2471.
[15]
FelixA. Gers, NicolN. Schraudolph, Jürgen Schmidhuber, Learning precise timing with LSTM recurrent networks., The Journal of Machine Learning Research 3 (Aug) (2002) 115–143.
[16]
Kyunghyun Cho, Bart van Merrienboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. (2014) “Learning phrase representations using RNN encoder-decoder for statistical machine translation.” arXiv preprint arXiv:1406.1078.
[17]
François Chollet et al (2015) Keras.
[18]
Martín Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, TensorFlow: A system for large-scale machine learning., OSDI, 2016, pp. 265–283. In, volume 16.
[19]
Paul J. Werbos. (1990) “Backpropagation through time: what it does and how to do it.” Proceedings of the IEEE 78(10): 1550-1560.
[20]
Reza Moazzezi. (2011) “Change-based population coding.” PhD thesis, UCL (University College London)..
Index Terms
- Automated detection of cardiac arrhythmia using deep learning techniques
Index terms have been assigned to the content through auto-classification.
Recommendations
Automated detection of diabetes using CNN and CNN-LSTM network and heart rate signals
AbstractDiabetes mellitus, commonly known as diabetes, is a disease that affects a vast majority of people globally. Diabetes cannot be cured; it can only be kept under control. In this paper, diabetes is diagnosed by the analysis of Heart Rate ...
The Study of Fast-Beating ECG QRS Detection Based on Deep Learning Models
ICBSP '22: Proceedings of the 2022 7th International Conference on Biomedical Imaging, Signal ProcessingThe QRS complex is one of the most distinctive features of ECG signals, and it can play an essential role in understanding heart rate (HR) and identifying heart diseases. Although many deep learning models applied to QRS detection have shown good ...
Inter-patient automated arrhythmia classification: A new approach of weight capsule and sequence to sequence combination
Highlights- We proposed a weight capsule model, using weight capsule network combined with sequence to sequence model, which can effectively alleviate the deficiency and ...
Abstract ObjectiveWe propose a new capsule network to compensate for the information loss in the deep convolutional networks in previous studies, and to improve the performance of arrhythmia classification.
...
Comments
Information & Contributors
Information
Published In
Copyright © 2018.
Publisher
Elsevier Science Publishers B. V.
Netherlands
Publication History
Published: 27 February 2024
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 28 Dec 2024