Skip to main content
SpringerLink
Log in

Rhythm Analysis During Cardio-Pulmonary Resuscitation with Convolutional and Recurrent Neural Networks Using ECG and Optional Impedance Input

  • Conference paper
  • First Online:
Recent Contributions to Bioinformatics and Biomedical Sciences and Engineering (BioInfoMed 2022)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 658))

Included in the following conference series:

  • 122 Accesses

Abstract

Chest compressions (CC) during cardiopulmonary resuscitation (CPR) produce strong artifacts in the electrocardiogram (ECG) via defi-pads. Heart rhythm can hardly be determined visually, but also by the shock-advisory algorithms in automated external defibrillators (AED). This study aims to investigate the potential of deep neural networks (DNN) as a powerful unsupervised feature extraction and classification algorithm that can give a shock advisory decision during CPR, regardless the CC fraction in the analysis interval. Our research objective is focused on detecting whether the rhythm is shockable or non-shockable from the primary raw ECG input, but also to verify the hypothesis that the secondary impedance (IMP) channel, which is generally modulated by the thorax movements and correlated to CC artifacts may contribute to performance. We designed 7 DNN architectures for processing of one (ECG) or two (ECG, IMP) input channels, involving fully-convolutional or convolutional-recurrent layers (LSTM or BiLSTM). In 30:2 compression-to-ventilation CPR during out-of-hospital cardiac arrest, the start of the CC period preceding the regular AED rhythm analysis was used as a time anchor to extract 62987 CPR strips (ECG, IMP) at 5 offsets (–10 s, –5 s, 0 s, +5 s, +10 s), thus representative of different CC durations in the analysis interval (10 s). They are divided patient-wise to training/test datasets: 1797/1747 ventricular fibrillations (VF), 730/768 normal sinus rhythms (NSR), 8583/8226 other non-shockable rhythms (ONR), 21609/19527 asystoles. Comparative study rejects the hypothesis that the impedance contributes to efficiency of rhythm analysis during CPR, considering that DNNs with two (ECG, IMP) inputs have specificity drop up to 3% points for non-shockable rhythms compared to one (ECG) input. The use of a recurrent layer after fully-convolutional architecture adds about 1% improvement in VF sensitivity (93.8%), keeping compatible specificity for Asystole (95.6%), NSR (99.2%), ONR (96.8%). The applied deep learning strategy justifies that convolutional-recurrent DNN architectures with a single ECG input are able to satisfy AHA recommendations for rhythm analysis with an arbitrary CC fraction distribution during CPR.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Fitzgibbon, E., Berger, R., Tsitlik, J., Halperin, H.: Determination of the noise source in the electrocardiogram during cardiopulmonary resuscitation. Crit. Care Med. 30, S148–S153 (2002)

    Article  Google Scholar 

  2. Olasveengen, T., Semeraro, F., Ristagno, G., et al.: European resuscitation council guidelines 2021: basic life support. Resus 161, 98–114 (2021)

    Google Scholar 

  3. Isasi, I., Irusta, U., Rad, A., et al.: Automatic cardiac rhythm classification with concurrent manual chest compressions. IEEE Access 7, 115147–115159 (2019)

    Article  Google Scholar 

  4. Isasi, I., Irusta, U., Elola, A., et al: A robust machine learning architecture for a reliable ECG rhythm analysis during CPR. In: 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 1903–1907, Berlin, Germany (2019)

    Google Scholar 

  5. Isasi, I., Irusta, U., Aramendi, E., Idris, A., Sörnmo, L.: Restoration of the electrocardiogram during mechanical cardiopulmonary resuscitation. Physiol. Meas. 41, 105006 (2020)

    Article  Google Scholar 

  6. Irusta, U., Ruiz, J., de Gauna, S., Eftestøl, T., Kramer-Johansen, J.: A least mean-square filter for the estimation of the cardiopulmonary resuscitation artifact based on the frequency of the compressions. IEEE Trans. Biomed. Eng. 56, 1052–1062 (2009)

    Article  Google Scholar 

  7. Ayala, U., Irusta, U., Ruiz, J., et al.: A reliable method for rhythm analysis during cardiopulmonary resuscitation. Biomed. Res. Int. 2014, 872470 (2014)

    Article  Google Scholar 

  8. Ruiz, J., Irusta, U., De Gauna, S., Eftestøl, T.: Cardiopulmonary resuscitation artefact suppression using a Kalman filter and the frequency of chest compressions as the reference signal. Resus 81, 1087–1094 (2010)

    Google Scholar 

  9. Aramendi, E., Ayala, U., Irusta, U., Alonso, E., Eftestøl, T., Kramer-Johansen, J.: Suppression of the cardiopulmonary resuscitation artefacts using the instantaneous chest compression rate extracted from the thoracic impedance. Resus 83, 692–698 (2012)

    Google Scholar 

  10. Babaeizadeh, S., Firoozabadi, R., Han, C., Helfenbein, E.: Analyzing cardiac rhythm in the presence of chest compression artifact for automated shock advisory. J. Electrocardiol. 47, 798–803 (2014)

    Article  Google Scholar 

  11. Gong, Y., Gao, P., Wei, L., Dai, C., Zhang, L., Li, Y.: An enhanced adaptive filtering method for suppressing cardiopulmonary resuscitation artifact. IEEE Trans. Biomed. Eng. 64, 471–478 (2016)

    Article  Google Scholar 

  12. Berger, R., Palazzolo, J., Halperin, H.: Rhythm discrimination during uninterrupted CPR using motion artifact reduction system. Resus 75, 145–152 (2007)

    Google Scholar 

  13. Tan, Q., Freeman, G., Geheb, F., Bisera, J.: Electrocardiographic analysis during uninterrupted cardiopulmonary resuscitation. Crit. Care Med. 36, S409–S412 (2008)

    Article  Google Scholar 

  14. Rheinberger, K., Steinberger, T., Unterkofler, K., Baubin, M., Klotz, A., Amann, A.: Removal of CPR artifacts from the ventricular fibrillation ECG by adaptive regression on lagged reference signals. IEEE Trans. Biomed. Eng. 55, 130–137 (2007)

    Article  Google Scholar 

  15. Krasteva, V., Jekova, I., Dotsinsky, I., Didon, J.P.: Shock advisory system for heart rhythm analysis during cardiopulmonary resuscitation using a single ECG input of automated external defibrillators. Annals Biomed. Eng. 38, 1326–1336 (2010)

    Article  Google Scholar 

  16. Amann, A., Klotz, A., Niederklapfer, T., et al.: Reduction of CPR artifacts in the ventricular fibrillation ECG by coherent line removal. Biomed. Eng. Online 9, 2 (2010)

    Article  Google Scholar 

  17. De Gauna, S., Ruiz, J., Irusta, U., Aramendi, E., Eftestøl, T., Kramer-Johansen, J.: A method to remove CPR artefacts from human ECG using only the recorded ECG. Resus 76, 271–278 (2008)

    Google Scholar 

  18. Hajeb-Mohammadalipour, S., Cascella, A., Valentine, M., Chon, K.H.: Automated condition-based suppression of the CPR artifact in ECG data to make a reliable shock decision for AEDs during CPR. Sensors 21, 8210 (2021)

    Article  Google Scholar 

  19. Li, Y., Bisera, J., Geheb, F., Tang, W., Weil, M.: Identifying potentially shockable rhythms without interrupting cardiopulmonary resuscitation. Crit. Care Med. 36, 198–203 (2008)

    Article  Google Scholar 

  20. Fumagalli, F., Silver, A., Tan, Q., Zaidi, N., Ristagno, G.: Cardiac rhythm analysis during ongoing cardiopulmonary resuscitation using the analysis during compressions with fast reconfirmation technology. Heart Rhythm 15, 248–255 (2018)

    Article  Google Scholar 

  21. Hu, Y., Tang, H., Liu, C., et al.: The performance of a new shock advisory algorithm to reduce interruptions during CPR. Resus 143, 1–9 (2019)

    Google Scholar 

  22. de Graaf, C., Beesems, S., Oud, S., et al.: Analyzing the heart rhythm during chest compressions: performance and clinical value of a new AED algorithm. Resus 162, 320–328 (2021)

    Google Scholar 

  23. Didon, J.P., Menetre, S., Jekova, I., Stoyanov, T., Krasteva, V.: Analyze whilst compressing algorithm for detection of ventricular fibrillation during CPR: a comparative performance evaluation for automated external defibrillators. Resus 160, 94–102 (2021)

    Google Scholar 

  24. Ayala, U., Irusta, U., Kramer-Johansen, J., et al.: Automatic detection of chest compression pauses for rhythm analysis during 30:2 CPR in an ALS scenario. Resus 85S, S9 (2014)

    Google Scholar 

  25. González-Otero, D., Ruiz de Gauna, S., Ruiz, J., Ayala, U., Alonso, E.: Automatic detection of chest compression pauses using the transthoracic impedance signal. Comput. Cardiol. 39, 21–24 (2012)

    Google Scholar 

  26. Didon, J.P., Krasteva, V., Ménétré, S., Stoyanov, T., Jekova, I.: Shock advisory system with minimal delay triggering after end of chest compressions: Accuracy and gained hands-off time. Resus 82S, S8–S15 (2011)

    Google Scholar 

  27. Jekova, I., Krasteva, V.: Optimization of end-to-end convolutional neural networks for analysis of out-of-hospital cardiac arrest rhythms during cardiopulmonary resuscitation. Sensors 21, 4105 (2021)

    Article  Google Scholar 

  28. Isasi, I., Irusta, U., Aramendi, E., Eftestøl, T., Kramer-Johansen, J., Wik, L.: Rhythm analysis during cardiopulmonary resuscitation using convolutional neural networks. Entropy 22, 595 (2020)

    Article  Google Scholar 

  29. Isasi, I., Irusta, U., Aramendi, E., Olsen, J.-Å., Wik, L.: Detection of shockable rhythms using convolutional neural networks during chest compressions provided by a load distributing band. Comput. Cardiol. 47, 1–4 (2020). https://doi.org/10.22489/CinC.2020.045

    Article  Google Scholar 

  30. Hajeb, M., Cascella, A., Valentine, M., Chon, K.: Deep neural network approach for continuous ECG-based automated external defibrillator shock advisory system during cardiopulmonary resuscitation. J. Am. Heart Assoc. 10, e019065 (2021)

    Article  Google Scholar 

  31. Irusta, U., Ruiz, J., Aramendi, E., Ruiz de Gauna, S., Ayala, U., Alonso, E.: A high-temporal resolution algorithm to discriminate shockable from nonshockable rhythms in adults and children. Resus 83, 1090–1097 (2012)

    Google Scholar 

  32. Krasteva, V., Ménétré, S., Didon, J.-P., Jekova, I.: Fully convolutional deep neural networks with optimized hyperparameters for detection of shockable and non-shockable rhythms. Sensors 20, 2875 (2020)

    Article  Google Scholar 

  33. Skjeflo, G.W., Nordseth, T., Loennechen, J.P., Bergum, D., Skogvoll, E.: ECG changes during resuscitation of patients with initial pulseless electrical activity are associated with return of spontaneous circulation. Resus 127, 31–36 (2018)

    Google Scholar 

  34. Koster, R., et al.: European resuscitation council guidelines for resuscitation 2010 section 2. Adult basic life support and use of automated external defibrillators. Resus 81, 1277–1292 (2010)

    Google Scholar 

  35. Automatic External Defibrillation: Recommendations for specifying and reporting arrhythmia analysis algorithm performance, incorporating new waveforms, and enhancing safety. Circulation 95, 1677–1682 (1997)

    Google Scholar 

  36. Roeder, L.: Netron, Visualizer for neural network, deep learning, and machine learning models. Comput. Softw. (2017). https://doi.org/10.5281/zenodo.5854962

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported by the Bulgarian National Science Fund, grant number KП-06-H42/3 “Computer aided diagnosis of cardiac arrhythmias based on machine learning and deep neural networks”.

Author information

Authors and Affiliations

  1. Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Acad. G, Bonchev str. bl. 105, 1113, Sofia, Bulgaria

    Vessela Krasteva & Irena Jekova

Authors
  1. Vessela Krasteva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Irena Jekova
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Irena Jekova .

Editor information

Editors and Affiliations

  1. Faculty of Technical Sciences, “Prof. Assen Zlatarov” University, Bourgas, Bulgaria

    Sotir Sotirov

  2. Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria

    Tania Pencheva

  3. Polish Academy of Sciences, Systems Research Institute, Warsaw, Poland

    Janusz Kacprzyk

  4. Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria

    Krassimir T. Atanassov

  5. Faculty of Technical Sciences, “Prof. Assen Zlatarov” University, Bourgas, Bulgaria

    Evdokia Sotirova

  6. Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria

    Simeon Ribagin

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Krasteva, V., Jekova, I. (2023). Rhythm Analysis During Cardio-Pulmonary Resuscitation with Convolutional and Recurrent Neural Networks Using ECG and Optional Impedance Input. In: Sotirov, S., Pencheva, T., Kacprzyk, J., Atanassov, K.T., Sotirova, E., Ribagin, S. (eds) Recent Contributions to Bioinformatics and Biomedical Sciences and Engineering. BioInfoMed 2022. Lecture Notes in Networks and Systems, vol 658. Springer, Cham. https://doi.org/10.1007/978-3-031-31069-0_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-31069-0_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-31068-3

  • Online ISBN: 978-3-031-31069-0

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation