Advanced search
2 files | 9.55 MB Add to list
Author
Organization
Abstract
Electrocardiogram signals are often used in medicine. An important aspect of analyzing this data is identifying and classifying the type of beat. This classification is often done through an automated algorithm. Recent advancements in neural networks and deep learning have led to high classification accuracy. However, adoption of neural network models into clinical practice is limited due to the black-box nature of the classification method. In this work, the use of variational auto encoders to learn human-interpretable encodings for the beat types is analyzed. It is demonstrated that using this method, an interpretable and explainable representation of normal and paced beats can be achieved with neural networks.
Keywords
interpretable model, ECG beat classification, deep learning, disentangled variational auto encoder, CLASSIFICATION

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 500.49 KB
  • 7494 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 9.05 MB

Citation

Please use this url to cite or link to this publication:

MLA
Van Steenkiste, Tom, et al. “Interpretable ECG Beat Embedding Using Disentangled Variational Auto-Encoders.” 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), IEEE, 2019, pp. 373–78, doi:10.1109/CBMS.2019.0008.
APA
Van Steenkiste, T., Deschrijver, D., & Dhaene, T. (2019). Interpretable ECG beat embedding using disentangled variational auto-encoders. 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 373–378. https://doi.org/10.1109/CBMS.2019.0008
Chicago author-date
Van Steenkiste, Tom, Dirk Deschrijver, and Tom Dhaene. 2019. “Interpretable ECG Beat Embedding Using Disentangled Variational Auto-Encoders.” In 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 373–78. IEEE. https://doi.org/10.1109/CBMS.2019.0008.
Chicago author-date (all authors)
Van Steenkiste, Tom, Dirk Deschrijver, and Tom Dhaene. 2019. “Interpretable ECG Beat Embedding Using Disentangled Variational Auto-Encoders.” In 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 373–378. IEEE. doi:10.1109/CBMS.2019.0008.
Vancouver
1.
Van Steenkiste T, Deschrijver D, Dhaene T. Interpretable ECG beat embedding using disentangled variational auto-encoders. In: 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS). IEEE; 2019. p. 373–8.
IEEE
[1]
T. Van Steenkiste, D. Deschrijver, and T. Dhaene, “Interpretable ECG beat embedding using disentangled variational auto-encoders,” in 2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), Cordoba, Spain, 2019, pp. 373–378.
@inproceedings{8621488,
  abstract     = {{Electrocardiogram signals are often used in medicine. An important aspect of analyzing this data is identifying and classifying the type of beat. This classification is often done through an automated algorithm. Recent advancements in neural networks and deep learning have led to high classification accuracy. However, adoption of neural network models into clinical practice is limited due to the black-box nature of the classification method. In this work, the use of variational auto encoders to learn human-interpretable encodings for the beat types is analyzed. It is demonstrated that using this method, an interpretable and explainable representation of normal and paced beats can be achieved with neural networks.}},
  author       = {{Van Steenkiste, Tom and Deschrijver, Dirk and Dhaene, Tom}},
  booktitle    = {{2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS)}},
  isbn         = {{9781728122861}},
  issn         = {{2372-9198}},
  keywords     = {{interpretable model,ECG beat classification,deep learning,disentangled variational auto encoder,CLASSIFICATION}},
  language     = {{eng}},
  location     = {{Cordoba, Spain}},
  pages        = {{373--378}},
  publisher    = {{IEEE}},
  title        = {{Interpretable ECG beat embedding using disentangled variational auto-encoders}},
  url          = {{http://dx.doi.org/10.1109/CBMS.2019.0008}},
  year         = {{2019}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: