Advertisement

A novel hybrid network of fusing rhythmic and morphological features for atrial fibrillation detection on mobile ECG signals

  • Xiaomao Fan
  • Zhejing Hu
  • Ruxin Wang
  • Liyan Yin
  • Ye Li
  • Yunpeng CaiEmail author
Original Article
  • 123 Downloads

Abstract

Atrial fibrillation (AF) is one of the most common arrhythmia diseases, the incidence of which is ascendant with age increase. What’s more, AF is a high-risk factor for stroke, ischemia myocardial and other malignant cardiovascular diseases, which would threaten people’s life significantly. Using a mobile device to screen AF segments is an effective way to reduce the mortality and morbidity of malignant cardiovascular diseases. However, most of existing AF detection methods mainly centered on clinical resting ECG signals and were incapable of processing mobile ECG signals with low signal-to-noise ratio which collected by mobile devices. In this paper, we take advantage of a fully convolutional network variant named U-Net for heart rhythmic information capturing by locating R peak positions as well as calculating RR intervals and a 34-layer residual network for waveform morphological features capturing from ECG signals. Combining both rhythmic information and waveform morphological features, two-layer fully connected networks are employed successively to discriminate AF, normal sinus rhythm , and other abnormal rhythm (other). The extensive experimental results show that our proposed AF our proposed AF screening framework named FRM-CNN can achieve \(F_{1}\) value of 85.08 ± 0.99% and accuracy of \(87.22 \pm 0.71\)% on identifying AF segments well without handcraft engineering. Compared with the cutting-edge AF detection methods, the FRM-CNN has more superior performance on monitoring people’s health conditions with mobile devices.

Keywords

Atrial fibrillation Arrhythmia detection Fully convolutional network Residual network Location of R peak position 

Notes

Acknowledgements

This paper was supported in part of Major Special Project of Guangdong Province (2017B030308007), Discipline Layout Research (JCYJ20180703145202065), and National Science Foundation (61771465, 61702497).

Compliance with ethical standards

Conflict of interest

All of the authors declare that they have no conflict of interest.

References

  1. 1.
    Camm AJ, Kirchhof P, Lip GYH et al (2010) Guidelines for the management of atrial fibrillation. Eur Heart J 31(19):2369–2429CrossRefGoogle Scholar
  2. 2.
    Rahman F, Kwan GF, Benjamin EJ (2014) Global epidemiology of atrial fibrillation. Nat Rev Cardiol 11(11):639CrossRefGoogle Scholar
  3. 3.
    Heeringa J, van der Kuip DAM, Hofman A et al (2006) Prevalence, incidence and lifetime risk of atrial fibrillation: the Rotterdam study. Eur Heart J 27(8):949–953CrossRefGoogle Scholar
  4. 4.
    Hassan AR et al (2016) Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating. Biocybern Biomed Eng 36(1):256–266CrossRefGoogle Scholar
  5. 5.
    Hassan AR et al (2017) An expert system for automated identification of obstructive sleep apnea from single-lead ECG using random under sampling boosting. Neurocomputing 235:122–130CrossRefGoogle Scholar
  6. 6.
    Hassan AR et al (2016) Computer-aided obstructive sleep apnea identification using statistical features in the EMD domain and extreme learning machine. Biomed Phys Eng Exp 2(3):035003MathSciNetCrossRefGoogle Scholar
  7. 7.
    Hassan AR (2015) Automatic screening of obstructive sleep apnea from single-lead electrocardiogram. In: 2015 international conference on electrical engineering and information communication technology (ICEEICT). IEEEGoogle Scholar
  8. 8.
    Hassan AR (2015) A comparative study of various classifiers for automated sleep apnea screening based on single-lead electrocardiogram. In: 2015 International conference on electrical and electronic engineering (ICEEE). IEEEGoogle Scholar
  9. 9.
    Guidera SA, Steinberg JS (1993) The signal-averaged P wave duration: a rapid and noninvasive marker of risk of atrial fibrillation. J Am Coll Cardiol 21(7):1645–1651CrossRefGoogle Scholar
  10. 10.
    Mehta S, Lingayat N, Sanghvi S (2009) Detection and delineation of P and T waves in 12-lead electrocardiograms. Exp Syst 26(1):125–143CrossRefGoogle Scholar
  11. 11.
    Dilaveris PE, Gialafos JE (2001) P-wave dispersion: a novel predictor of paroxysmal atrial fibrillation. Ann Noninvasive Electrocardiol 6(2):159–165CrossRefGoogle Scholar
  12. 12.
    Aytemir K et al (2000) P wave dispersion on 12-lead electrocardiography in patients with paroxysmal atrial fibrillation. Pacing Clin Electrophysiol 23(7):1109–1112CrossRefGoogle Scholar
  13. 13.
    Zhou X et al (2014) Automatic online detection of atrial fibrillation based on symbolic dynamics and Shannon entropy. Biomed Eng Online 13(1):18CrossRefGoogle Scholar
  14. 14.
    Huang C et al (2011) A novel method for detection of the transition between atrial fibrillation and sinus rhythm. IEEE Trans Biomed Eng 58(4):1113–1119CrossRefGoogle Scholar
  15. 15.
    Tateno K, Glass L (2000) A method for detection of atrial fibrillation using RR intervals. Comput Cardiol 27:391–394Google Scholar
  16. 16.
    Lian J, Wang L, Muessig D (2011) A simple method to detect atrial fibrillation using RR intervals. Am J Cardiol 107(10):1494–1497CrossRefGoogle Scholar
  17. 17.
    Dash S et al (2009) Automatic real time detection of atrial fibrillation. Ann Biomed Eng 37(9):1701–1709CrossRefGoogle Scholar
  18. 18.
    Billeci L et al (2017) Detection of AF and other rhythms Using RR variability and ECG spectral measures. Computing 44:1Google Scholar
  19. 19.
    Dai H, Jiang S, Li Y (2013) Atrial activity extraction from single lead ECG recordings: evaluation of two novel methods. Comput Biol Med 43(3):176–183CrossRefGoogle Scholar
  20. 20.
    Fan X et al (2018) Multiscaled fusion of deep convolutional neural networks for screening atrial fibrillation from single lead short ECG recordings. IEEE J Biomed Health Inform 22(6):1744–1753CrossRefGoogle Scholar
  21. 21.
    Pourbabaee B, Mehrsan Javan R, Khashayar K (2017) Deep convolutional neural networks and learning ecg features for screening paroxysmal atrial fibrillation patients. IEEE Trans Syst Man Cybern Syst 99:1–10Google Scholar
  22. 22.
    Daqrouq K et al (2014) Neural network and wavelet average framing percentage energy for atrial fibrillation classification. Comput Methods Prog Biomed 113(3):919–926CrossRefGoogle Scholar
  23. 23.
    Yıldırım Ö et al (2018) Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med 102:411–420CrossRefGoogle Scholar
  24. 24.
    Hannun AY, Rajpurkar P, Haghpanahi M et al (2019) Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 25(1):65CrossRefGoogle Scholar
  25. 25.
    Acharya UR et al (2017) Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inf Sci 405:81–90CrossRefGoogle Scholar
  26. 26.
    Andreotti F et al (2017) Comparing feature-based classifiers and convolutional neural networks to detect arrhythmia from short segments of ECG. Computing 44:1Google Scholar
  27. 27.
    Chandra BS et al (2017) Atrial fibrillation detection using convolutional neural networks. Computing 44:1Google Scholar
  28. 28.
    Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3431–3440Google Scholar
  29. 29.
    Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention. Springer, Cham, pp 234–241Google Scholar
  30. 30.
    Zhang H et al (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl 1–20.  https://doi.org/10.1007/s00521-018-3579-x
  31. 31.
    Zhang H et al (2016) Object-level video advertising: an optimization framework. IEEE Trans Ind Inform 13(2):520–531CrossRefGoogle Scholar
  32. 32.
    Ji Y, Zhang H, Jonathan Wu QM (2018) Salient object detection via multi-scale attention CNN. Neurocomputing 322:130–140CrossRefGoogle Scholar
  33. 33.
    Goldberger AL et al (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215–e220CrossRefGoogle Scholar
  34. 34.
    He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
  35. 35.
    Pan J, Tompkins W (1985) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 32(3):230–236CrossRefGoogle Scholar
  36. 36.
    Arzeno N, Deng Z, Poon C (2008) Analysis of first-derivative based QRS detection algorithms. IEEE Trans Biomed Eng 55(2):478–484CrossRefGoogle Scholar
  37. 37.
    Moraes J et al (2002) A QRS complex detection algorithm using electrocardiogram leads. In: Computers in cardiology. IEEE, pp 205–208Google Scholar
  38. 38.
    Elgendi M et al (2008) A robust QRS complex detection algorithm using dynamic thresholds. In: International symposium on computer science and its applications. IEEE, pp 153–158Google Scholar
  39. 39.
    Vollmer M, Sodmann P, Caanitz L et al (2017) Can supervised learning be used to classify cardiac rhythms? Computing 44:1Google Scholar
  40. 40.
    Kropf M, Hayn D, Schreier G (2017) ECG classification based on time and frequency domain features using random forests. Computing 44:1Google Scholar
  41. 41.
    Datta S, Puri C, Mukherjee A et al (2017) Identifying normal, AF and other abnormal ECG rhythms using a cascaded binary classifier. Computing 44:1Google Scholar
  42. 42.
    Plesinger F, Nejedly P, Viscor I et al (2017) Automatic detection of atrial fibrillation and other arrhythmias in Holter ECG recordings using rhythm features and neural networks. Computing 44:1Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Xiaomao Fan
    • 1
  • Zhejing Hu
    • 2
  • Ruxin Wang
    • 2
  • Liyan Yin
    • 2
  • Ye Li
    • 2
  • Yunpeng Cai
    • 2
    Email author
  1. 1.School of Data ScienceCity University of Hong KongKowloonChina
  2. 2.Chinese Academy of SciencesShenzhen Institutes of Advanced TechnologyShenzhenChina

Personalised recommendations