Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

In-Distribution and Out-of-Distribution Self-supervised ECG Representation Learning for Arrhythmia Detection (2304.06427v2)

Published 13 Apr 2023 in cs.LG, cs.AI, and eess.SP

Abstract: This paper presents a systematic investigation into the effectiveness of Self-Supervised Learning (SSL) methods for Electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel analysis of the data distributions on three popular ECG-based arrhythmia datasets: PTB-XL, Chapman, and Ribeiro. To the best of our knowledge, our study is the first to quantitatively explore and characterize these distributions in the area. We then perform a comprehensive set of experiments using different augmentations and parameters to evaluate the effectiveness of various SSL methods, namely SimCRL, BYOL, and SwAV, for ECG representation learning, where we observe the best performance achieved by SwAV. Furthermore, our analysis shows that SSL methods achieve highly competitive results to those achieved by supervised state-of-the-art methods. To further assess the performance of these methods on both In-Distribution (ID) and Out-of-Distribution (OOD) ECG data, we conduct cross-dataset training and testing experiments. Our comprehensive experiments show almost identical results when comparing ID and OOD schemes, indicating that SSL techniques can learn highly effective representations that generalize well across different OOD datasets. This finding can have major implications for ECG-based arrhythmia detection. Lastly, to further analyze our results, we perform detailed per-disease studies on the performance of the SSL methods on the three datasets.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (44)
  1. J. H. Medicine, “Electrocardiogram.” Retrieved on January 13, 2023 from https://www.hopkinsmedicine.org/health/treatment-tests-and-therapies/electrocardiogram/, 2021.
  2. T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” in International Conference on Machine Learning, 2020.
  3. Z. Lan, M. Chen, S. Goodman, K. Gimpel, P. Sharma, and R. Soricut, “Albert: A lite bert for self-supervised learning of language representations,” in International Conference on Learning Representations, 2019.
  4. J. Ren, P. J. Liu, E. Fertig, J. Snoek, R. Poplin, M. Depristo, J. Dillon, and B. Lakshminarayanan, “Likelihood ratios for out-of-distribution detection,” Advances in Neural Information Processing Systems, pp. 14707–14718, 2019.
  5. W. Liu, X. Wang, J. Owens, and Y. Li, “Energy-based out-of-distribution detection,” Advances in Neural Information Processing Systems, 2020.
  6. K. Ahuja, E. Caballero, D. Zhang, J.-C. Gagnon-Audet, Y. Bengio, I. Mitliagkas, and I. Rish, “Invariance principle meets information bottleneck for out-of-distribution generalization,” Advances in Neural Information Processing Systems, 2021.
  7. A. Baevski, Y. Zhou, A. Mohamed, and M. Auli, “wav2vec 2.0: A framework for self-supervised learning of speech representations,” Advances in Neural Information Processing Systems, 2020.
  8. P. Sarkar and A. Etemad, “Self-supervised ecg representation learning for emotion recognition,” IEEE Transactions on Affective Computing, vol. 13, no. 3, pp. 1541–1554, 2020.
  9. P. Sarkar and A. Etemad, “Self-supervised learning for ecg-based emotion recognition,” in IEEE International Conference on Acoustics, Speech and Signal Processing, 2020.
  10. P. Sarkar, S. Lobmaier, B. Fabre, D. González, A. Mueller, M. G. Frasch, M. C. Antonelli, and A. Etemad, “Detection of maternal and fetal stress from the electrocardiogram with self-supervised representation learning,” Scientific Reports, 2021.
  11. D. Kiyasseh, T. Zhu, and D. Clifton, “Crocs: Clustering and retrieval of cardiac signals based on patient disease class, sex, and age,” Advances in Neural Information Processing Systems, 2021.
  12. S. Soltanieh, A. Etemad, and J. Hashemi, “Analysis of augmentations for contrastive ecg representation learning,” in International Joint Conference on Neural Networks, 2022.
  13. J. Y. Cheng, H. Goh, K. Dogrusoz, O. Tuzel, and E. Azemi, “Subject-aware contrastive learning for biosignals,” arXiv preprint arXiv:2007.04871, 2020.
  14. X. Lan, D. Ng, S. Hong, and M. Feng, “Intra-inter subject self-supervised learning for multivariate cardiac signals,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2022.
  15. B. Gopal, R. Han, G. Raghupathi, A. Ng, G. Tison, and P. Rajpurkar, “3kg: contrastive learning of 12-lead electrocardiograms using physiologically-inspired augmentations,” in Machine Learning for Health, 2021.
  16. D. Kiyasseh, T. Zhu, and D. A. Clifton, “Clocs: Contrastive learning of cardiac signals across space, time, and patients,” in International Conference on Machine Learning, 2021.
  17. J. Oh, H. Chung, J.-m. Kwon, D.-g. Hong, and E. Choi, “Lead-agnostic self-supervised learning for local and global representations of electrocardiogram,” in Conference on Health, Inference, and Learning, 2022.
  18. D. Kiyasseh, T. Zhu, and D. Clifton, “Pcps: Patient cardiac prototypes to probe ai-based medical diagnoses, distill datasets, and retrieve patients,” Transactions on Machine Learning Research, pp. 2835–8856, 2023.
  19. C. Luo, G. Wang, Z. Ding, H. Chen, and F. Yang, “Segment origin prediction: A self-supervised learning method for electrocardiogram arrhythmia classification,” in International Conference of the IEEE Engineering in Medicine & Biology Society, 2021.
  20. Y. Zhou, G. Zhao, J. Li, G. Sun, X. Qian, B. Moody, R. G. Mark, and L.-w. H. Lehman, “A contrastive learning approach for icu false arrhythmia alarm reduction,” Scientific Reports, 2022.
  21. T. Mehari and N. Strodthoff, “Self-supervised representation learning from 12-lead ecg data,” Computers in Biology and Medicine, 2022.
  22. B. T. Lee, S. T. Kong, Y. Song, and Y. Lee, “Self-supervised learning with electrocardiogram delineation for arrhythmia detection,” in International Conference of the IEEE Engineering in Medicine & Biology Society, 2021.
  23. H. Zhang, W. Liu, J. Shi, S. Chang, H. Wang, J. He, and Q. Huang, “Maefe: Masked autoencoders family of electrocardiogram for self-supervised pretraining and transfer learning,” IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1–15, 2022.
  24. K. Sohn, “Improved deep metric learning with multi-class n-pair loss objective,” Advances in Neural Information Processing Systems, pp. 1857–1865, 2016.
  25. J.-B. Grill, F. Strub, F. Altché, C. Tallec, P. Richemond, E. Buchatskaya, C. Doersch, B. Avila Pires, Z. Guo, M. Gheshlaghi Azar, et al., “Bootstrap your own latent-a new approach to self-supervised learning,” Advances in Neural Information Processing Systems, 2020.
  26. M. Caron, I. Misra, J. Mairal, P. Goyal, P. Bojanowski, and A. Joulin, “Unsupervised learning of visual features by contrasting cluster assignments,” Advances in Neural Information Processing Systems, 2020.
  27. M. Cuturi, “Sinkhorn distances: Lightspeed computation of optimal transport,” Advances in Neural Information Processing Systems, pp. 2292–2300, 2013.
  28. P. Wagner, N. Strodthoff, R.-D. Bousseljot, D. Kreiseler, F. I. Lunze, W. Samek, and T. Schaeffter, “Ptb-xl, a large publicly available electrocardiography dataset,” Scientific Data, 2020.
  29. J. Zheng, J. Zhang, S. Danioko, H. Yao, H. Guo, and C. Rakovski, “A 12-lead electrocardiogram database for arrhythmia research covering more than 10,000 patients,” Scientific Data, 2020.
  30. A. H. Ribeiro, M. H. Ribeiro, G. M. Paixão, D. M. Oliveira, P. R. Gomes, J. A. Canazart, M. P. Ferreira, C. R. Andersson, P. W. Macfarlane, W. Meira Jr, et al., “Automatic diagnosis of the 12-lead ecg using a deep neural network,” Nature Communications, 2020.
  31. N. Strodthoff, P. Wagner, T. Schaeffter, and W. Samek, “Deep learning for ecg analysis: Benchmarks and insights from ptb-xl,” IEEE Journal of Biomedical and Health Informatics, 2020.
  32. G. D. Clifford, C. Liu, B. Moody, H. L. Li-wei, I. Silva, Q. Li, A. Johnson, and R. G. Mark, “Af classification from a short single lead ecg recording: The physionet/computing in cardiology challenge 2017,” in Computing in Cardiology, 2017.
  33. I. Christov, V. Krasteva, I. Simova, T. Neycheva, and R. Schmid, “Multi-parametric analysis for atrial fibrillation classification in ecg,” in Computing in Cardiology, 2017.
  34. R. Kher, “Signal processing techniques for removing noise from ecg signals,” Biomedical Engineering and Research, 2019.
  35. D. Hendrycks and K. Gimpel, “A baseline for detecting misclassified and out-of-distribution examples in neural networks,” in International Conference on Learning Representations, 2016.
  36. H. Wang, Z. Li, L. Feng, and W. Zhang, “Vim: Out-of-distribution with virtual-logit matching,” in Conference on Computer Vision and Pattern Recognition, 2022.
  37. Z. Zhang and X. Xiang, “Decoupling maxlogit for out-of-distribution detection,” in Conference on Computer Vision and Pattern Recognition, 2023.
  38. L. McInnes, J. Healy, and J. Melville, “Umap: Uniform manifold approximation and projection for dimension reduction,” arXiv preprint arXiv:1802.03426, 2018.
  39. M. Pastore and A. Calcagni, “Measuring distribution similarities between samples: a distribution-free overlapping index,” Frontiers in Psychology, 2019.
  40. A. Vágner, L. Farkas, and I. Juhász, “Clustering and visualization of ecg signals,” in Third International Conference on Software, Services and Semantic Technologies, 2011.
  41. Y.-C. Yeh, C. W. Chiou, and H.-J. Lin, “Analyzing ecg for cardiac arrhythmia using cluster analysis,” Expert Systems with Applications, 2012.
  42. H. He, Y. Tan, and J. Xing, “Unsupervised classification of 12-lead ecg signals using wavelet tensor decomposition and two-dimensional gaussian spectral clustering,” Knowledge-Based Systems, 2019.
  43. W. Falcon and K. Cho, “A framework for contrastive self-supervised learning and designing a new approach,” arXiv preprint arXiv:2009.00104, 2020.
  44. M. Bahaz and R. Benzid, “Efficient algorithm for baseline wander and powerline noise removal from ecg signals based on discrete fourier series,” Australasian Physical and Engineering Sciences in Medicine, 2018.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Sahar Soltanieh (2 papers)
  2. Javad Hashemi (5 papers)
  3. Ali Etemad (118 papers)
Citations (8)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now