Diagnosis of left atrial and left ventricular hypertrophies using a deep neural network

This paper presents the results of the application of a convolutional neural network to diagnose left atrial and left ventricular hypertrophies by analyzing 12-lead electrocardiograms (ECG). During the study, a new unique dataset containing 64 thousand ECG records was collected and processed. Labels for the two classes under consideration, left ventricular hypertrophy and left atrial hypertrophy, were generated from the accompanying medical reports. A set of signals and obtained labels were used to train a deep convolutional neural network with residual blocks; the resulting model is capable of detecting left ventricular hypertrophy with F-score more than 0.82 and left atrial hypertrophy with F1-score over 0.78. In addition, the search for optimal neural network architecture was carried out and the experimental evaluation of the effect of including patient metadata into the model and signal preprocessing was conducted. Besides, the paper provides a comparative analysis of the difficulty of detecting left ventricular and left atrial hypertrophies in relation to the other two frequently occurring heart activity disorders, namely atrial fibrillation and left bundle branch block.

1. Gertsch Marc. The ECG: a two-step approach to diagnosis. Springer-Verlag Berlin Heidelberg, 2004, 615 p.

2. Kozłowski D. Method in the Chaos – a step-by-step approach to ECG interpretation. European Journal of Translational and Clinical Medicine, vol. 1, no. 1, pp. 74-90.

3. Donal Erwan et al. EACVI/EHRA Expert Consensus Document on the role of multi-modality imaging for the evaluation of patients with atrial fibrillation. European Heart Journal - Cardiovascular Imaging, vol. 17, no. 4, 2016, pp. 355–383.

4. Tsang T.S., Abhayaratna W.P., Barnes M.E. et al. Prediction of cardiovascular outcomes with left atrial size: is volume superior to area or diameter? Journal of the American College of Cardiology, vol. 47, no. 5, 2006, pp. 1018-1023.

5. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In Proc. of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1026-1034.

6. Amodei Dario et al. Deep speech 2: End-to-end speech recognition in English and Mandarin. In Proc. of the International conference on machine learning, 2016, pp. 173–182.

7. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin. Attention Is All You Need. In Proc. of the 31st Conference on Neural Information Processing Systems, 2017, pp. 5998-6008.

8. Bejnordi Babak Ehteshami et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. Journal of the American Medical Association, vol. 318, no. 22, 2017, pp. 2199-2210.

9. De Fauw Jeffrey, Ledsam Joseph R., Romera-Paredes Bernardino et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nature medicine, vol. 24, no. 9, 2018, pp. 1342–1350.

10. Hannun Awni Y., Rajpurkar Pranav, Haghpanahi Masoumeh et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nature medicine, vol. 25, no. 1, 2019, pp. 65-69.

11. Ribeiro Antônio H., Ribeiro Manoel Horta, Paixão Gabriela M.M. et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nature communications, vol. 11, no. 1, 2020, pp. 1–9

12. Smith Stephen W., Walsh Brooks, Grauer Ken et al. A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation. Journal of electrocardiology, vol. 52, 2019, pp. 88-95.

13. He Kaiming, Zhang Xiangyu, Ren Shaoqing, Sun Jian. Deep residual learning for image recognition. In Proc. of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778. 0

14. Ioffe Sergey, Szegedy Christian. Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167, 2015.

15. Srivastava Nitish, Hinton Geoffrey, Krizhevsky Alex et al. Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, vol. 15, no. 1, 2014, pp. 1929-1958.

16. Rumelhart David E., Hinton Geoffrey E., and Williams Ronald J. Learning representations by back-propagating errors. Nature, vol. 323, 1986, pp. 533-536.

17. Kingma Diederik P., Ba Jimmy. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.

18. Cleveland William S. Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association, vol. 74, no. 368, 1979, pp. 829-836.

19. Kania Michał, Fereniec Małgorzta, and Maniewski Roman. Wavelet denoising for multi-lead high resolution ECG signals. Measurement Science Review, vol. 7, no. 4, 2007, pp. 30-33.

20. Donoho David L., and Johnstone Iain M. Threshold selection for wavelet shrinkage of noisy data. In Proc. of the 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1994, pp. A24–A25.

21. Veloso Adriano, Wagner Meira, and Zaki Mohammed J. Lazy associative classification. In Proc. of the Sixth International Conference on Data Mining (ICDM’06), 2006, pp. 645–654.

22. Nguyen Duc Tam et al. Self: Learning to filter noisy labels with self-ensembling. arXiv preprint arXiv:1910.01842, 2019.

23. Huang Lang, Zhang Chao, and Zhang Hongyang. Self-Adaptive Training: beyond Empirical Risk Minimization. arXiv preprint arXiv:2002.10319, 2020.

24. Guryanova Valeriia. Online Augmentation for Quality Improvement of Neural Networks for Classification of Single-Channel Electrocardiograms. In Proc. of the International Conference on Analysis of Images, Social Networks and Texts, 2019, pp. 37–49.

25. Kiyasseh Dani, Zhu Tingting, and Clifton David A. CLOCS: Contrastive Learning of Cardiac Signals. arXiv preprint arXiv:2005.13249, 2020.