ATRIAL FIBRILLATION DETECTION ON ELECTROCARDIOGRAMS WITH CONVOLUTIONAL NEURAL NETWORKS
Viktor Kifer
Ternopil Ivan Puluj National Technical University (Ukraine)
http://orcid.org/0000-0002-0621-9121
Natalia Zagorodna
zagorodna.n@gmail.comTernopil Ivan Puluj National Technical University (Ukraine)
http://orcid.org/0000-0002-1808-835X
Olena Hevko
Ternopil Ivan Puluj National Technical University (Ukraine)
http://orcid.org/0000-0003-1427-1699
Abstract
In this paper, we present our research which confirms the suitability of the convolutional neural network usage for the classification of single-lead ECG recordings. The proposed method was designed for classifying normal sinus rhythm, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy signals. The method combines manually selected features with the features learned by the deep neural network. The Physionet Challenge 2017 dataset of over 8500 ECG recordings was used for the model training and validation. The trained model reaches an average F1-score 0.71 in classifying normal sinus rhythm, AF and other rhythms respectively.
Keywords:
electrocardiography, machine learning, neural networksReferences
AliveCor ECG recording device. https://www.alivecor.com
Google Scholar
Clifford G, Liu C, Moody B, Silva I, Li Q, Johnson A, Mark. R.: AF classification from a short single lead ECG recording: the PhysioNet Computing in Cardiology challenge 2017. Computing in Cardiology 44, 2017, [DOI: 10.22489/CinC.2017.065-469].
DOI: https://doi.org/10.22489/CinC.2017.065-469
Google Scholar
Dilaveris P. E., Kennedy H. L.: Silent atrial fibrillation: epidemiology, diagnosis, and clinical impact. Clinical Cardiology 40(6), 413–418, 2017.
DOI: https://doi.org/10.1002/clc.22667
Google Scholar
Hernandez J., Carrasco-Ochoa J. A., Martínez-Trinidad J. F.: An Empirical Study of Oversampling and Undersampling for Instance Selection Methods on Imbalance Datasets. In: Ruiz-Shulcloper J., Sanniti di Baja G. (eds): Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2013. Lecture Notes in Computer Science, vol 8258. Springer, Berlin, Heidelberg 2013, [DOI: 10.1007/978-3-642-41822-8_33]
DOI: https://doi.org/10.1007/978-3-642-41822-8_33
Google Scholar
Himanshu S., Kumar J. S. J, Ashok V., Juliet A. V.: Advanced ECG Signal Processing using Virtual Instrument. International Journal on Recent Trends in Engineering & Technology 3(2), 2010, 111-114.
Google Scholar
Huang J., Chen B., Yao B., He W. ECG Arrhythmia Classification Using STFT-based Spectrogram and Convolutional Neural Network. EEE Access 7, 2019, 92871-92880.
DOI: https://doi.org/10.1109/ACCESS.2019.2928017
Google Scholar
Kohler B.-U., Hennig C., Orglmeister R.: The principles of software QRS Detection. IEEE Engineering in Medicine and Biology Magazine 21(1), 2002, 42-57, [DOI: 10.1109/51.993193].
DOI: https://doi.org/10.1109/51.993193
Google Scholar
Mikhled A., Daqrouq K.: ECG Signal Denoising by Wavelet Transform Thresholding. American Journal of Applied Sciences 5(3), 2008. 276-281.
DOI: https://doi.org/10.3844/ajassp.2008.276.281
Google Scholar
Park J., Lee S., Jeon M.: Atrial fibrillation detection by heart rate variability in Poincare plot. Biomed engineering online 8/38, 2009, 1-12.
DOI: https://doi.org/10.1186/1475-925X-8-38
Google Scholar
Petrenas A., Marozas V.: Low-complexity detection of atrial fibrillation in continuous long-term monitoring. Comput in Biology and Medicine 65, 2015, 184-191.
DOI: https://doi.org/10.1016/j.compbiomed.2015.01.019
Google Scholar
Rodenas-Garcia J., Garica M., Alcaraz R., Rieta J.: Wavelet Entropy Automatically Detects Episodes of Atrial Fibrillation from Single-Lead Electrocardiograms. Entropy 17, 2015, 6179-6199, [DOI: 10.3390/e17096179].
DOI: https://doi.org/10.3390/e17096179
Google Scholar
Simonyan K., Zisserman A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. Inter Conf on Learning Representations (ICLR), 2015. [arXiv preprint arXiv:1409.1556].
Google Scholar
Tziakouri M., Pitris C., Orphanidou C.: Classification of AF and Other Arrhythmias from a Short Segment of ECG Using Dynamic Time Warping. Comp in Cardio, 2017, 1-4.
DOI: https://doi.org/10.22489/CinC.2017.348-295
Google Scholar
Velayudhan A., Peter S.: Noise Analysis and Different Denoising Techniques of ECG Signal – A Survey. IOSR Journal of Electronics and Communication Engineering, 2016, 40-44
Google Scholar
Wang Z., Wan F., Wong C.M., Zhang L.: Adaptive Fourier decomposition based ECG denoising. Computers in Biology and Medicine 77, 2016, 195–205.
DOI: https://doi.org/10.1016/j.compbiomed.2016.08.013
Google Scholar
https://keras.io Keras documentation (available: 19.07.2019).
Google Scholar
https://numpy.org NumPy official documentation (available 01.07.2019).
Google Scholar
https://scikit-learn.org Scikit-Learn official website (available: 01.07.2019).
Google Scholar
https://www.python.org Python programming language (available 30.06.2019).
Google Scholar
https://www.scipy.org SciPy official documentation (available 01.07.2019).
Google Scholar
https://www.tensorflow.org Tensorflow official page (available: 19.07.2019).
Google Scholar
OMRON HCG801 HearnScan ECG recorder. https://www.omron-healthcare.com/en/products/electrocardiograph
Google Scholar
WIWE ECG recording device. https://shop.mywiwe.com/en/ecg-recording-105
Google Scholar
Authors
Viktor KiferTernopil Ivan Puluj National Technical University Ukraine
http://orcid.org/0000-0002-0621-9121
Authors
Natalia Zagorodnazagorodna.n@gmail.com
Ternopil Ivan Puluj National Technical University Ukraine
http://orcid.org/0000-0002-1808-835X
Authors
Olena HevkoTernopil Ivan Puluj National Technical University Ukraine
http://orcid.org/0000-0003-1427-1699
Statistics
Abstract views: 562PDF downloads: 242
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.