Skip to main content
SpringerLink
Log in

An end-end arrhythmia diagnosis model based on deep learning neural network with multi-scale feature extraction

  • AI Note
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

This study presents an innovative end-to-end deep learning arrhythmia diagnosis model that aims to address the problems in arrhythmia diagnosis. The model performs pre-processing of the heartbeat signal by automatically and efficiently extracting time-domain, time-frequency-domain and multi-scale features at different scales. These features are imported into an adaptive online convolutional network-based classification inference module for arrhythmia diagnosis. Experimental results show that the AOCT-based deep learning neural network diagnostic module has excellent parallel computing and classification inference capabilities, and the overall performance of the model improves with increasing scales. In particular, when multi-scale features are used as inputs, the model is able to learn both time-frequency domain information and other rich information, thus significantly improving the performance of the end-to-end diagnostic model. The final results show that the AOCT-based deep learning neural network model has an average accuracy of 99.72%, a recall of 99.62%, and an F1 score of 99.3% in diagnosing four common heart diseases.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. Hong S et al (2019) Combining deep neural networks and engineered features for cardiac arrhythmia detection from ECG recordings. Physiol Meas 40(5):054009

    Article  PubMed  Google Scholar 

  2. Grune J, Yamazoe M, Nahrendorf M (2021) Electroimmunology and cardiac arrhythmia. Nat Reviews Cardiol 18(8):547–564

    Article  Google Scholar 

  3. Chen Q et al (2019) The value of baseline and arrhythmic ECG in the interpretation of arrhythmic mechanisms. Cardiac Electrophysiol Clin 11(2):219–238

    Article  Google Scholar 

  4. Gopinathannair R et al (2015) Arrhythmia-induced cardiomyopathies: mechanisms, recognition, and management. J Am Coll Cardiol 66(15):1714–1728

    Article  PubMed Central  PubMed  Google Scholar 

  5. Kim Y, Kwan et al (2022) Automatic cardiac arrhythmia classification using residual network combined with long short-term memory. IEEE Trans Instrum Meas 71:1–17

    Google Scholar 

  6. Baman JR et al (2022) Mobile health for arrhythmia diagnosis and management. J Gen Intern Med 1:1–10

    Google Scholar 

  7. Guess M, Zavanelli N, Woon-Hong Y (2022) Recent advances in materials and flexible sensors for arrhythmia detection. Materials 15(3):724

    Article  CAS  PubMed Central  PubMed  Google Scholar 

  8. Badr M et al (2022) Detection of heart arrhythmia on electrocardiogram using artificial neural networks. Comput Intell Neurosci. https://doi.org/10.1155/2022/1094830

    Article  PubMed Central  PubMed  Google Scholar 

  9. Ge D, Srinivasan N, Shankar M (2002) Cardiac arrhythmia classification using autoregressive modeling. Biomed Eng Online 1(1):1–12

    Article  Google Scholar 

  10. Mohonta S, Motin MA, Kumar DK (2022) Electrocardiogram based arrhythmia classification using wavelet transform with deep learning model. Sens Bio-Sensing Res 37:100502

    Article  Google Scholar 

  11. Ullah H et al (2022) An effective and lightweight deep electrocardiography arrhythmia recognition model using novel special and native structural regularization techniques on cardiac signal. J Healthcare Eng. https://doi.org/10.1155/2022/3408501

    Article  Google Scholar 

  12. Murawwat S et al (2022) Denoising and classification of arrhythmia using memd and ann. Alexandria Eng J 61(4):2807–2823

    Article  Google Scholar 

  13. Zhang Y et al (2023) Cardiac arrhythmia classification by time–frequency features inputted to the designed convolutional neural networks. Biomed Signal Process Control 79:104224

    Article  Google Scholar 

  14. Madan P et al (2022) A hybrid deep learning approach for ECG-based arrhythmia classification. Bioengineering 94:152

    Article  Google Scholar 

  15. Liu Y et al (2022) An efficient neural network-based method for patient-specific information involved arrhythmia detection. Knowl Based Syst 250:109021

    Article  Google Scholar 

  16. Keshun Y, Huizhong L (2023) Research on optimization of control parameters of gravity shaking table. Sci Rep 13.1 (2023):1133

    Google Scholar 

  17. Keshun Y, Wen C, Liu Huizhong (2023) Research on intelligent implementation of the beneficiation process of shaking table. Min Eng 199. https://doi.org/10.1016/j.mineng.2023.108108

  18. You K, Qiu G, Gu Y (2023) An efficient lightweight neural network using BiLSTM-SCN-CBAM with PCA-ICEEMDAN for diagnosing rolling bearing faults. Meas Sci Technol 34: 094001

  19. Ma S et al (2022) An effective data enhancement method for classification of ECG arrhythmia. Measurement 203:111978

    Article  Google Scholar 

  20. Le MD, Singh Rathour V, Truong QS et al (2021) Multi-module recurrent convolutional neural network with Transformer Encoder for ECG Arrhythmia classification. 2021 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI) 1–5. Athens, Greece doi:10.1109/BHI50953.2021.9508527

  21. Hu R, Chen J, Li, Zhou (2022) A transformer-based deep neural network for arrhythmia detection using continuous ECG signals. Comput Biol Med 144:105325

    Article  PubMed  Google Scholar 

  22. Houssein EH et al (2022) An automatic arrhythmia classification model based on improved marine predators algorithm and convolutions neural networks. Expert Syst Appl 187:115936

    Article  Google Scholar 

  23. Kıymaç E, Kaya Y (2023) A novel automated cnn arrhythmia classifier with memory-enhanced artificial hummingbird algorithm. Expert Syst Appl 213:119162

    Article  Google Scholar 

  24. Keshun Y, Huizhong L (2023) Intelligent deployment solution for tabling adapting deep learning in IEEE Access, vol 11. 22201–22208. https://doi.org/10.1109/ACCESS.2023.3234075.

  25. You K, Qiu G, Gu Y (2022) Rolling bearing fault diagnosis using hybrid neural network with principal component analysis. Sensors 22(22):8906

    Article  PubMed Central  PubMed  Google Scholar 

  26. Hammad M et al (2022) Deep learning models for arrhythmia detection in IoT healthcare applications. Comput Electr Eng 100:108011

    Article  Google Scholar 

  27. Moody GB, Roger G (2001) Mark. “The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol Mag 20(3):45–50

    Article  CAS  PubMed  Google Scholar 

  28. Liu C et al (2016) An open access database for the evaluation of heart sound algorithms. Physiol Meas 37(12):2181–2213. https://doi.org/10.1088/0967-3334/37/12/2181

    Article  PubMed Central  PubMed  Google Scholar 

  29. Goldberger A et al (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215–e220

    Article  CAS  PubMed  Google Scholar 

  30. Alqudah AM (2020) AOCT-NET: a convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images. Med Biol Eng Comput 58:41–53

    Article  PubMed  Google Scholar 

  31. Amin Ullah SM, Anwar M, Bilal (2020) Classification of arrhythmia by using deep learning with 2-d ecg spectral image representation. Remote Sens 12(10):1685

    Article  Google Scholar 

  32. Hammad M et al (2020) A multitier deep learning model for arrhythmia detection. IEEE Trans Instrum Meas 70:1–9

    Article  Google Scholar 

Download references

Funding

This study was supported by funding from (Ganzhou polytechnic, Jiangxi University of Technology, First Affiliated Hospital of Gannan Medical College). This funding source had no influence on the study design, data collection, analysis, or interpretation of the results.

Author information

Authors and Affiliations

  1. Ganzhou Polytechnic, Zhanggong District, Ganzhou City, 341099, Jiangxi Province, China

    Li Jiahao & Zen Bohua

  2. The First Affiliated Hospital of Gannan Medical College, No. 23, Qingnian Road, Ganzhou City, 341001, Jiangxi Province, China

    Luo Shuixian

  3. Jiangxi University of Science and Technology, 1958 Hakka Avenue, Ganzhou City, 341000, Jiangxi Province, China

    You Keshun

Authors
  1. Li Jiahao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Luo Shuixian
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. You Keshun
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zen Bohua
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to You Keshun.

Ethics declarations

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jiahao, L., Shuixian, L., Keshun, Y. et al. An end-end arrhythmia diagnosis model based on deep learning neural network with multi-scale feature extraction. Phys Eng Sci Med 46, 1341–1352 (2023). https://doi.org/10.1007/s13246-023-01286-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-023-01286-9

Keywords

Search

Navigation