Advertisement

Anomaly Detection in Phonocardiogram Employing Deep Learning

  • V. G. SujadeviEmail author
  • K. P. Soman
  • R. Vinayakumar
  • A. U. Prem Sankar
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 711)

Abstract

Phonocardiogram (PCG) is the recording of heart sounds and murmurs. PCG compliments electrocardiogram in detection of heart diseases especially in the initial screenings due to its simplicity and low cost. Detecting abnormal heart sounds by algorithms is important for remote health monitoring and other scenarios where having an experienced physician is not possible. While several studies exist, we explore the possibility of detecting anomalies in heart sounds and murmurs using Deep-learning algorithms on well-known Physionet Dataset. We performed the experiments by employing various algorithms such as RNN, LSTM, GRU, B-RNN, B-LSTM and CNN. We achieved 80% accuracy in CNN 3 layer Deep learning model on the raw signals without performing any preprocessing methods. To our knowledge this is the highest reported accuracy that employs analyzing the raw PCG data.

Keywords

Phonocardiogram (PCG) Machine learning Deep learning 

Notes

Acknowledgements

We sincerely thank NVIDIA India for the K40 GPU card that was used in this study.

References

  1. 1.
    Barabasa, Constantin, Maria Jafari, and Mark D. Plumbley. “A robust method for S1/S2 heart sounds detection without ECG reference based on music beat tracking.” Electronics and Telecommunications (ISETC), 2012 10th International Symposium on. IEEE, 2012.Google Scholar
  2. 2.
    Chen, Tien-En, et al. “S1 and S2 heart sound recognition using deep neural networks.” IEEE Transactions on Biomedical Engineering 64.2 (2017): 372–380.Google Scholar
  3. 3.
    Jusak, Jusak, Ira Puspasari, and Pauladie Susanto. “Heart murmurs extraction using the complete Ensemble Empirical Mode Decomposition and the Pearson distance metric.” Information Communication Technology and Systems (ICTS), 2016 International Conference on. IEEE, 2016.Google Scholar
  4. 4.
    Stainton, Scott, Charalampos Tsimenidis, and Alan Murray. “Characteristics of phonocardiography waveforms that influence automatic feature recognition.” Computing in Cardiology Conference (CinC), 2016. IEEE, 2016.Google Scholar
  5. 5.
    Mondal, Ashok, et al. “A noise reduction technique based on nonlinear kernel function for heart sound analysis.” IEEE Journal of Biomedical and Health Informatics (2017).Google Scholar
  6. 6.
    Faradisa, Irmalia Suryani, et al. “Identification of phonocardiogram signal based on STFT and Marquart Lavenberg Backpropagation.” Intelligent Technology and Its Applications (ISITIA), 2016 International Seminar on. IEEE, 2016.Google Scholar
  7. 7.
    Chakir, Fatima, et al. “Phonocardiogram signals classification into normal heart sounds and heart murmur sounds.” Intelligent Systems: Theories and Applications (SITA), 2016 11th International Conference on. IEEE, 2016.Google Scholar
  8. 8.
    Thomas, Rijil, et al. “Heart sound segmentation using fractal decomposition.” Engineering in Medicine and Biology Society (EMBC), 2016 IEEE 38th Annual International Conference of the. IEEE, 2016.Google Scholar
  9. 9.
    Cheng, Xiefeng, et al. “Feature extraction and recognition methods based on phonocardiogram.” Digital Information Processing, Data Mining, and Wireless Communications (DIPDMWC), 2016 3rd International Conference on. IEEE, 2016.Google Scholar
  10. 10.
    Grzegorczyk, Iga, et al. “PCG classification using a neural network approach.” Computing in Cardiology Conference (CinC), 2016. IEEE, 2016.Google Scholar
  11. 11.
    Elman, Jeffrey L. “Finding structure in time.” Cognitive science 14.2 (1990): 179–211.CrossRefGoogle Scholar
  12. 12.
    Hochreiter, Sepp, and Jrgen Schmidhuber. “Long short-term memory.” Neural computation 9.8 (1997): 1735–1780.CrossRefGoogle Scholar
  13. 13.
    Graves, Alex, and Jrgen Schmidhuber. “Framewise phoneme classification with bidirectional LSTM and other neural network architectures.” Neural Networks 18.5 (2005): 602–610.CrossRefGoogle Scholar
  14. 14.
    Gers, Felix A., Nicol N. Schraudolph, and Jrgen Schmidhuber. “Learning precise timing with LSTM recurrent networks.” Journal of machine learning research 3.Aug (2002): 115–143.Google Scholar
  15. 15.
    LeCun, Yann, Yoshua Bengio, and Geoffrey Hinton. “Deep learning.” Nature 521.7553 (2015): 436–444.CrossRefGoogle Scholar
  16. 16.
    Kim, Yoon. “Convolutional neural networks for sentence classification.” arXiv preprint arXiv:1408.5882 (2014).
  17. 17.
    Liu, Chengyu, et al. “An open access database for the evaluation of heart sound algorithms.” Physiological Measurement 37.12 (2016): 2181.CrossRefGoogle Scholar
  18. 18.
    Abadi, Martn, et al. “TensorFlow: A system for large-scale machine learning.” Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI). Savannah, Georgia, USA. 2016.Google Scholar
  19. 19.
    Maaten, Laurens van der, and Geoffrey Hinton. “Visualizing data using t-SNE.” Journal of Machine Learning Research 9.Nov (2008): 2579–2605.Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • V. G. Sujadevi
    • 1
    Email author
  • K. P. Soman
    • 1
  • R. Vinayakumar
    • 1
  • A. U. Prem Sankar
    • 2
  1. 1.Center for Computational Engineering and Networking, Amrita School of Engineering, Amrita Vishwa VidyapeethamAmrita UniversityCoimbatoreIndia
  2. 2.Center for Cyber Security Systems and Networks, Amrita School of Engineering, Amrita Vishwa VidyapeethamAmrita UniversityAmritapuriIndia

Personalised recommendations