Skip to main content
SpringerLink
Log in

Multi-class 12-lead ECG automatic diagnosis based on a novel subdomain adaptive deep network

  • Article
  • Published:
Science China Technological Sciences Aims and scope Submit manuscript

Abstract

Arrhythmia is a common type of cardiovascular disease, which has become the leading cause of global deaths. Recently, automatic 12-lead ECG diagnosis system based on numerous labelled data has attracted increasing attention. However, labelling 12-lead ECG recordings is a complex and time-consuming task for clinicians. And then, the existence of data distribution differences limits the direct cross domain use of the trained model. Enlighted by subdomain adaptation methods, this paper designs a novel subdomain adaptative deep network (SADN) for excavating diagnosis knowledge from source domain dataset. Firstly, convolutional layer, residual blocks and SE-Residual blocks are utilized for extracting meaningful deep features automatically. Additionally, feature classifier uses these deep features for obtaining the final diagnosis predictions. Further, designing a novel loss function with local maximum mean discrepancy is utilized for restricting data distribution discrepancy from different datasets. Finally, the Clinical Outcomes in Digital ECG and 1st China Physiological Signal Challenge datasets are utilized for evaluating the superiority of SADN, which presents that SADN enhances algorithm performance on the unlabelled target domain dataset. Further, compared the existing methods, the proposed network structure acquires better performance with a F1-macro of 89.43% and a F1-macro1 of 87.09%. Besides, among the 4 kinds of ECG abnormalities, the diagnostic effect of the SADN is better than that of cardiology residents. Thus, SADN has promising potential as an auxiliary diagnostic tool for the clinical environment.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Mendis S, Puska P, Norrving B, et al. Global Atlas on Cardiovascular Disease Prevention and Control. Geneva: World Health Organization, 2011

    Google Scholar 

  2. Mehra R. Global public health problem of sudden cardiac death. J ElectroCardiol, 2007, 40: S118–S122

    Article  Google Scholar 

  3. Stamkopoulos T, Diamantaras K, Maglaveras N, et al. ECG analysis using nonlinear PCA neural networks for ischemia detection. IEEE Trans Signal Process, 1998, 46: 3058–3067

    Article  Google Scholar 

  4. Leijdekkers P, Gay V. A self-test to detect a heart attack using a mobile phone and wearable sensors. In: Proceedings of the 21st IEEE International Symposium on Computer-Based Medical Systems. Jyvaskyla: 2008. 93–98

  5. Goldstein D S. The electrocardiogram in stroke: Relationship to pathophysiological type and comparison with prior tracings. Stroke, 1979, 10: 253–259

    Article  Google Scholar 

  6. Ladavich S, Ghoraani B. Rate-independent detection of atrial fibrillation by statistical modeling of atrial activity. BioMed Signal Process Control, 2015, 18: 274–281

    Article  Google Scholar 

  7. Huang C, Ye S, Chen H, et al. A novel method for detection of the transition between atrial fibrillation and sinus rhythm. IEEE Trans Biomed Eng, 2011, 58: 1113–1119

    Article  Google Scholar 

  8. García M, Ródenas J, Alcaraz R, et al. Application of the relative wavelet energy to heart rate independent detection of atrial fibrillation. Comput Methods Programs Biomed, 2016, 131: 157–168

    Article  Google Scholar 

  9. Rodríguez R, Mexicano A, Bila J, et al. Feature extraction of electrocardiogram signals by applying adaptive threshold and principal component analysis. J Appl Res Tech, 2015, 13: 261–269

    Article  Google Scholar 

  10. Huang H, Liu J, Zhu Q, et al. A new hierarchical method for interpatient heartbeat classification using random projections and RR intervals. Biomed Eng Online, 2014, 13: 90

    Article  Google Scholar 

  11. Perlman O, Katz A, Amit G, et al. Supraventricular tachycardia classification in the 12-lead ECG using atrial waves detection and a clinically based tree scheme. IEEE J Biomed Health Inform, 2016, 20: 1513–1520

    Article  Google Scholar 

  12. Yin J, Xiao P X, Li J, et al. Parameters analysis of sample entropy, permutation entropy and permutation ratio entropy for RR interval time series. Inf Processing Manage, 2020, 57: 102283

    Article  Google Scholar 

  13. Schläpfer J, Wellens H J. Computer-interpreted electrocardiograms. J Am College Cardiol, 2017, 70: 1183–1192

    Article  Google Scholar 

  14. Jin Y, Li Z, Qin C, et al. A novel attentional deep neural network-based assessment method for ECG quality. Biomed Signal Process Control, 2022, doi: https://doi.org/10.1016/j.bspc.2022.104064

  15. Li J, Si Y, Xu T, et al. Deep convolutional neural network based ecg classification system using information fusion and one-hot encoding techniques. Math Problems Eng, 2018, 2018: 1–10

    Google Scholar 

  16. Zhai X, Tin C. Automated ECG classification using dual heartbeat coupling based on convolutional neural network. IEEE Access, 2018, 6: 27465–27472

    Article  Google Scholar 

  17. Sellami A, Hwang H. A robust deep convolutional neural network with batch-weighted loss for heartbeat classification. Expert Syst Appl, 2019, 122: 75–84

    Article  Google Scholar 

  18. Oh S L, Ng E Y K, Tan R S, et al. Automated diagnosis of arrhythmia using combination of CNN and LSTM techniques with variable length heart beats. Comput Biol Med, 2018, 102: 278–287

    Article  Google Scholar 

  19. Lainscak M, Dagres N, Filippatos G S, et al. Atrial fibrillation in chronic non-cardiac disease: Where do we stand? Int J Cardiol, 2008, 128: 311–315

    Article  Google Scholar 

  20. Jin Y, Qin C, Huang Y, et al. Multi-domain modeling of atrial fibrillation detection with twin attentional convolutional long short-term memory neural networks. Knowledge-Based Syst, 2020, 193: 105460

    Article  Google Scholar 

  21. Xia Y, Wulan N, Wang K, et al. Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med, 2018, 93: 84–92

    Article  Google Scholar 

  22. He R, Wang K, Zhao N, et al. Automatic detection of atrial fibrillation based on continuous wavelet transform and 2D convolutional neural networks. Front Physiol, 2018, 9

  23. Fujita H, Cimr D. Computer Aided detection for fibrillations and flutters using deep convolutional neural network. Inf Sci, 2019, 486: 231–239

    Article  Google Scholar 

  24. Fujita H, Cimr D. Decision support system for arrhythmia prediction using convolutional neural network structure without preprocessing. Appl Intell, 2019, 49: 3383–3391

    Article  Google Scholar 

  25. Acharya U R, Fujita H, Lih O S, et al. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inf Sci, 2017, 405: 81–90

    Article  Google Scholar 

  26. Hannun A Y, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 2019, 25: 65–69

    Article  Google Scholar 

  27. Acharya U R, Suri J S, Spaan J A E, et al. Advances in Cardiac Signal Processing. New York: Springer, 2007

    Book  MATH  Google Scholar 

  28. Goldberger A, Goldberger Z, Shvilkin A. Clinical Electrocardiography: A Simplified Approach. St. Louis: Saunders, 2012

    Google Scholar 

  29. Pan S J, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng, 2010, 22: 1345–1359

    Article  Google Scholar 

  30. Quionero-Candela J, Sugiyama M, Schwaighofer A, et al. Dataset Shift in Machine Learning. Cambridge: MIT Press, 2009

    Google Scholar 

  31. Zhang C, Zhao Q. Deep discriminative domain adaptation. Inf Sci, 2021, 575: 599–610

    Article  MathSciNet  Google Scholar 

  32. Johnson R, Zhang T. Semi-supervised convolutional neural networks for text categorization via region Embedding. Adv Neural Inf Process Syst, 2015, 28: 919–927

    Google Scholar 

  33. Yang B, Lei Y, Jia F, et al. An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearings. Mech Syst Signal Process, 2019, 122: 692–706

    Article  Google Scholar 

  34. Jin Y, Qin C, Tao J, et al. An accurate and adaptative cutterhead torque prediction method for shield tunneling machines via adaptative residual long-short term memory network. Mech Syst Signal Process, 2022, 165: 108312

    Article  Google Scholar 

  35. Wang G, Chen M, Ding Z, et al. Inter-patient ECG arrhythmia heartbeat classification based on unsupervised domain adaptation. Neurocomputing, 2021, 454: 339–349

    Article  Google Scholar 

  36. Feng P, Fu J, Ge Z, et al. Unsupervised semantic-aware adaptive feature fusion network for arrhythmia detection. Inf Sci, 2022, 582: 509–528

    Article  MathSciNet  Google Scholar 

  37. Ammour N. Atrial fibrillation detection with a domain adaptation neural network approach. In: Proceedings of the 2018 5th International Conference on Computational Science and Computational Intelligence. Las Vegas: IEEE, 2018. 738–743

    Google Scholar 

  38. Jin Y, Qin C, Liu J, et al. A novel domain adaptive residual network for automatic atrial fibrillation detection. Knowledge-Based Syst, 2020, 203: 106122

    Article  Google Scholar 

  39. Ribeiro A H, Ribeiro M H, Paixão G M M, et al. Automatic diagnosis of the 12-lead ECG using a deep neural network. Nat Commun, 2020, 11: 1760

    Article  Google Scholar 

  40. Liu F, Liu C, Zhao L, et al. An open access database for evaluating the algorithms of electrocardiogram rhythm and morphology abnormality detection. J Med Imag Hlth Inform, 2018, 8: 1368–1373

    Article  Google Scholar 

  41. Hagiwara Y, Fujita H, Oh S L, et al. Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review. Inf Sci, 2018, 467: 99–114

    Article  Google Scholar 

  42. Martis R J, Acharya U R, Min L C. ECG beat classification using PCA, LDA, ICA and discrete wavelet transform. BioMed Signal Processing Control, 2013, 8: 437–448

    Article  Google Scholar 

  43. Fukushima K. Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybernetics, 1980, 36: 193–202

    Article  MATH  Google Scholar 

  44. Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition. Proc IEEE, 1998, 86: 2278–2324

    Article  Google Scholar 

  45. Jin Y, Qin C, Huang Y, et al. Actual bearing compound fault diagnosis based on active learning and decoupling attentional residual network. Measurement, 2021, 173: 108500

    Article  Google Scholar 

  46. Qin C, Jin Y, Tao J, et al. DTCNNMI: A deep twin convolutional neural networks with multi-domain inputs for strongly noisy diesel engine misfire detection. Measurement, 2021, 180: 109548

    Article  Google Scholar 

  47. Jin Y, Liu J, Liu Y, et al. A novel interpretable method based on duallevel attentional deep neural network for actual multilabel arrhythmia detection. IEEE Trans Instrum Meas, 2022, 71: 1–11

    Google Scholar 

  48. Yuan J H, Wu Y, Lu X, et al. Recent advances in deep learning based sentiment analysis. Sci China Tech Sci, 2020, 63: 1947–1970

    Article  Google Scholar 

  49. Lu G, Wang Y B, Xu H X, et al. Deep multimodal learning for municipal solid waste sorting. Sci China Tech Sci, 2022, 65: 324–335

    Article  Google Scholar 

  50. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, 2016. 770–778

  51. Hu J, Shen L, Albanie S, et al. Squeeze-and-excitation networks. IEEE Trans Pattern Analy Machine Intell, 2020, 42: 2011–2023

    Article  Google Scholar 

  52. Long M, Cao Y, Wang J, et al. Learning transferable features with deep adaptation networks. Proc ICML, 2015, 37: 97–105

    Google Scholar 

  53. Tzeng E, Hoffman J, Zhang N, et al. Deep domain confusion: Maximizing for domain invariance.. arXiv: 1412.3474

  54. Zhu Y, Zhuang F, Wang J, et al. Deep subdomain adaptation network for image classification. IEEE Trans Neural Networks Learn Syst, 2020, 32: 1713–1722

    Article  MathSciNet  Google Scholar 

  55. Kingma D P, Ba J. Adam: A method for stochastic optimization. arXiv: 1412.6980

  56. Yang Y, Jin L, Pan Z. ECG arrhythmia heartbeat classification using deep learning networks. In: Proceedings of the Cloud Computing 10th EAI International Conference. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering (LNICST 363). Qufu, 2020. 175–189

  57. Shaker AM, Tantawi M, Shedeed HA, et al. Heartbeat classification using 1D convolutional neural networks. In: Proceedings of the international Conference on Advanced Intelligent Systems and Informatics. Cairo, 2020. 502–511

  58. Guo X, Wang Q, Zheng J. An intelligent computer-aided diagnosis approach for atrial fibrillation detection based on multi-scale convolution kernel and Squeeze-and-Excitation network. BioMed Signal Processing Control, 2021, 68: 102778

    Article  Google Scholar 

  59. Jin Y, Qin C, Liu J, et al. A novel incremental and interactive method for actual heartbeat classification with limited additional labeled samples. IEEE Trans Instrum Meas, 2021, 70: 1–12

    Google Scholar 

  60. Qin C, Shi G, Tao J, et al. An adaptive hierarchical decomposition-based method for multi-step cutterhead torque forecast of shield machine. Mech Syst Signal Process, 2022, 175: 109148

    Article  Google Scholar 

  61. Qin C, Xiao D, Tao J, et al. Concentrated velocity synchronous linear chirplet transform with application to robotic drilling chatter monitoring. Measurement, 2022, 194: 111090

    Article  Google Scholar 

  62. Di Z Y, Shao H D, Xiang J W. Ensemble deep transfer learning driven by multisensor signals for the fault diagnosis of bevel-gear cross-operation conditions. Sci China Tech Sci, 2021, 64: 481–492

    Article  Google Scholar 

  63. Wang Q W, Gu Y F, Yang M, et al. Multi-attribute smooth graph convolutional network for multispectral points classification. Sci China Tech Sci, 2021, 64: 2509–2522

    Article  Google Scholar 

  64. Cai G R, Yang S M, Du J, et al. Convolution without multiplication: A general speed up strategy for CNNs. Sci China Tech Sci, 2021, 64: 2627–2639

    Article  Google Scholar 

  65. Cheng S Y, Chu B F, Zhong B N, et al. DRNet: Towards fast, accurate and practical dish recognition. Sci China Tech Sci, 2021, 64: 2651–2661

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China

    YanRui Jin, ZhiYuan Li, YunQing Liu, JinLei Liu, ChengJin Qin & ChengLiang Liu

  2. Department of Cardiology, Shanghai First People’s Hospital Affiliated to Shanghai Jiao Tong University, Shanghai, 200080, China

    LiQun Zhao

Authors
  1. YanRui Jin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. ZhiYuan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. YunQing Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. JinLei Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. ChengJin Qin
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. LiQun Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. ChengLiang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to ChengJin Qin or ChengLiang Liu.

Additional information

This work was supported by the National Key R&D Program of China (Grant No. 2018YFB1307005), the State Key Laboratory of Mechanical System and Vibration (Grant No. MSVZD202103), and Shanghai Municipal Science and Technology Major Project (Grant No. 2021SHZDZX0102).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jin, Y., Li, Z., Liu, Y. et al. Multi-class 12-lead ECG automatic diagnosis based on a novel subdomain adaptive deep network. Sci. China Technol. Sci. 65, 2617–2630 (2022). https://doi.org/10.1007/s11431-022-2080-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11431-022-2080-6

Search

Navigation