Assessment of the impact of non-architectural changes in the predictive model on the quality of ECG classification

Recording and analyzing 12-lead electrocardiograms is the most common procedure for detecting heart disease. Recently, various deep learning methods have been proposed for the automatic diagnosis by an electrocardiogram. The proposed methods can provide a second opinion for the doctor and help detect pathologies at an early stage. Various methods are proposed in the paper to improve the quality of prediction of ECG recording pathologies. Techniques include adding patient metadata, ECG noise reduction, and self-adaptive learning. The significance of data parameters in training a classification model is also explored. Among the considered parameters, the influence of various ECG leads, the length of the electrocardiogram and the volume of the training sample is studied. The experiments carried out show the relevance of the described approaches and offer an optimal estimate of the input data parameters.

1. V. Gulshan, L. Peng et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama, vol. 316, issue 22, 2016, pp. 2402-2410.

2. A. Esteva, B. Kuprel et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, vol. 542, issue 7639, 2017, pp. 115-118.

3. S. Singh, S.K. Pandey et al. Classification of ecg arrhythmia using recurrent neural networks. Procedia computer science, vol. 132, 2018, pp. 1290-1297.

4. T. Teijeiro, C. A. Garcıa et al. Arrhythmia classification from the abductive interpretation of short single-lead ecg records. In Proc. of the 2017 Computing in Cardiology (CinC), 2017, pp. 1-4.

5. J.A. Gutiérrez-Gnecchi, R. Morfin-Magaña et al. Dsp-based arrhythmia classification using wavelet transform and probabilistic neural network. Biomedical Signal Processing and Control, vol. 32, 2017, pp. 44-56.

6. M. Ramkumar, C.G. Babu et al. ECG cardiac arrhythmias classification using DWT, ICA and MLP neural networks. Journal of Physics: Conference Series, vol. 1831, 2021, article no. 012015.

7. H. Wang, H. Shi et al. A high-precision arrhythmia classification method based on dual fully connected neural network. Biomedical Signal Processing and Control, vol. 58, 2020, article no. 101874.

8. A. Krizhevsky, I. Sutskever, and G.E. Hinton. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, vol. 25, 2012, pp. 1097-1105.

9. S. Mousavi и F. Afghah. Inter-and intra-patient ecg heartbeat classification for arrhythmia detection: a sequence to sequence deep learning approach. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 1308-1312.

10. K. N. Rajesh и R. Dhuli. Classification of imbalanced ecg beats using re-sampling techniques and adaboost ensemble classifier. Biomedical Signal Processing and Control, vol. 41, 2018, 242-254.

11. I. Goodfellow, J. Pouget-Abadie et al. Generative adversarial nets. Advances in neural information processing systems, vol. 27, 2014, pp. 2672-2680.

12. A.M. Shaker, M. Tantawi et al. Generalization of convolutional neural networks for ecg classification using generative adversarial networks. IEEE Access, vol. 8, 2020, pp. 35592-35605.

13. Y. Xia, N. Wulan et al. Detecting atrial fibrillation by deep convolutional neural networks. Computers in biology and medicine, vol. 93, 2018, pp. 84-92.

14. V. Gliner, N. Keidar et al. Automatic classification of healthy and disease conditions from images or digital standard 12-lead electrocardiograms. Scientific Reports, vol. 10, issue 1, 2020, pp. 1-12.

15. A.Y. Hannun, P. Rajpurkar et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, vol. 25, issue 1, 2019, pp. 65-69.

16. A.H. Ribeiro, M.H. Ribeiro et al. Automatic diagnosis of the 12-lead ecg using a deep neural network. Nature communications, vol. 11, issue 1, pp. 1-9.

17. N. Strodthoff, P. Wagner, et al. Deep learning for ecg analysis: benchmarks and insights from ptb-xl. IEEE Journal of Biomedical and Health Informatics, vol. 25, issue 5, 2020, pp. 1519-1528.

18. L. Huang, C. Zhang и H. Zhang. Self-adaptive training: beyond empirical risk minimization. Advances in neural information processing systems, vol. 33, 2020, pp. 19365-19376.