Skip to main content
SpringerLink
Log in

Deep learning classification of capnography waveforms: secondary analysis of the PRODIGY study

  • Original Research
  • Published:
Journal of Clinical Monitoring and Computing Aims and scope Submit manuscript

Abstract

Capnography monitors trigger high priority ‘no breath’ alarms when CO2 measurements do not exceed a given threshold over a specified time-period. False alarms occur when the underlying breathing pattern is stable, but the alarm is triggered when the CO2 value reduces even slightly below the threshold. True ‘no breath’ events can be falsely classified as breathing if waveform artifact causes an aberrant spike in CO2 values above the threshold. The aim of this study was to determine the accuracy of a deep learning approach to classifying segments of capnography waveforms as either ‘breath’ or ‘no breath’. A post hoc secondary analysis of data from 9 North American sites included in the PRediction of Opioid-induced Respiratory Depression In Patients Monitored by capnoGraphY (PRODIGY) study was conducted. We used a convolutional neural network to classify 15 s capnography waveform segments drawn from a random sample of 400 participants. Loss was calculated over batches of 32 using the binary cross-entropy loss function with weights updated using the Adam optimizer. Internal-external validation was performed by iteratively fitting the model using data from all but one hospital and then assessing its performance in the remaining hospital. The labelled dataset consisted of 10,391 capnography waveform segments. The neural network’s accuracy was 0.97, precision was 0.97 and recall was 0.96. Performance was consistent across hospitals in internal-external validation. The neural network could reduce false capnography alarms. Further research is needed to compare the frequency of alarms derived from the neural network with the standard approach.

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
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Abbreviations

AUROC:

Area under the receiver operating characteristics curve 

ETCO2 :

End-tidal carbon dioxide

CO2:

Carbon dioxide

References

  1. Drew BJ, Harris P, Zegre-Hemsey JK, et al. Insights into the problem of alarm fatigue with physiologic monitor devices: a comprehensive observational study of consecutive intensive care unit patients. PLoS ONE. 2014;9(10):e110274.

    Article  PubMed  PubMed Central  Google Scholar 

  2. Winters BD, Cvach MM, Bonafide CP, et al. Technological distractions (part 2): a summary of approaches to manage clinical alarms with intent to reduce alarm fatigue. Crit Care Med. 2018;46(1):130–7.

    Article  PubMed  Google Scholar 

  3. Cvach M. Monitor alarm fatigue: an integrative review. Biomed Instrum Technol. 2012;46(4):268–77.

    Article  PubMed  Google Scholar 

  4. Wallis L. Alarm fatigue linked to patient’s death. AJN Am J Nurs. 2010;110(7):16.

    Article  PubMed  Google Scholar 

  5. Sun Z, Sessler DI, Dalton JE, et al. Postoperative hypoxemia is common and persistent: a prospective blinded observational study. Anesth Analg. 2015;121(3):709.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Overdyk F, Dahan A, Roozekrans M, der Schrier R, Aarts L, Niesters M. Opioid-induced respiratory depression in the acute care setting: a compendium of case reports. Pain Manag. 2014;4(4):317–25. https://doi.org/10.2217/pmt.14.19.

    Article  PubMed  Google Scholar 

  7. Khanna AK, Saager L, Bergese SD, et al. Opioid-induced respiratory depression increases hospital costs and length of stay in patients recovering on the general care floor. BMC Anesthesiol. 2021;21(1):1–12.

    Article  Google Scholar 

  8. Khanna AK, Bergese SD, Jungquist CR, et al. Prediction of opioid-induced respiratory depression on inpatient wards using continuous capnography and oximetry: an international prospective, observational trial. Anesth Analg. 2020;131(4):1012. https://doi.org/10.1213/ANE.0000000000004788.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  9. Pedregosa F, Michel V, Grisel O, et al. Scikit-learn: machine learning in python. J Mach Learn Res. 2011;12:2825–30.

    Google Scholar 

  10. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016;770–778.

  11. Smith LN. Cyclical learning rates for training neural networks. Proceedings – 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017. Published online May 11, 2017:464–472. https://doi.org/10.1109/WACV.2017.58.

  12. Abadi M, Barham P, Chen J et al. TensorFlow: a system for large-scale machine learning. In: 12th USENIX symposium on operating systems design and implementation (OSDI 16). USENIX Association; 2016:265–283. https://www.usenix.org/conference/osdi16/technical-sessions/presentation/abadi.

  13. Seabold S, Perktold J, Statsmodels. Econometric and statistical modeling with python. In: Proceedings of the 9th Python in Science Conference. 2010;57:10-25080.

  14. Steyerberg EW, Harrell FE Jr. Prediction models need appropriate internal, internal-external, and external validation. J Clin Epidemiol. 2016;69:245–7. https://doi.org/10.1016/j.jclinepi.2015.04.005.

    Article  PubMed  Google Scholar 

  15. Urman RD, Khanna AK, Bergese SD, et al. Postoperative opioid administration characteristics associated with opioid-induced respiratory depression: results from the PRODIGY trial. J Clin Anesth. 2021;70:110167.

    Article  CAS  PubMed  Google Scholar 

  16. Waljee JF, Zhong L, Hou H, Sears E, Brummet C, Chung KC. The utilization of opioid analgesics following common upper extremity surgical procedures: a national, population-based study. Plast Reconstr Surg. 2016;137(2):355e.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Bhagya D, Manikandan S. Speed of sound-based capnographic sensor with second-generation CNN for automated classification of cardiorespiratory abnormalities. IEEE Sens J. 2019;19(19):8887–94.

    Article  CAS  Google Scholar 

  18. Mieloszyk RJ, Verghese GC, Deitch K, et al. Automated quantitative analysis of capnogram shape for COPD–normal and COPD–CHF classification. IEEE Trans Biomed Eng. 2014;61(12):2882–90.

    Article  PubMed  Google Scholar 

  19. Bhagya D, Suchetha M. A 1-D deformable convolutional neural network for the quantitative analysis of capnographic sensor. IEEE Sens J. 2020;21(5):6672–8.

    Article  Google Scholar 

  20. Pertzov B, Ronen M, Rosengarten D, et al. Use of capnography for prediction of obstruction severity in non-intubated COPD and asthma patients. Respir Res. 2021;22(1):1–9.

    Article  Google Scholar 

  21. El-Badawy IM, Singh OP, Omar Z. Automatic classification of regular and irregular capnogram segments using time-and frequency-domain features: a machine learning-based approach. Technol Health Care. 2021;29(1):59–72.

    Article  PubMed  Google Scholar 

  22. El-Badawy IM, Omar Z, Singh OP. An effective machine learning approach for classifying artefact-free and distorted capnogram segments using simple time-domain features. IEEE Access. 2022;10:8767–78. https://doi.org/10.1109/ACCESS.2022.3143617.

    Article  Google Scholar 

  23. Jaffe MB. Using the features of the time and volumetric capnogram for classification and prediction. J Clin Monit Comput. 2017;31(1):19–41.

    Article  PubMed  Google Scholar 

  24. Herry CL, Townsend D, Green GC, Bravi A, Seely AJE. Segmentation and classification of capnograms: application in respiratory variability analysis. Physiol Meas. 2014;35(12):2343. https://doi.org/10.1088/0967-3334/35/12/2343.

    Article  CAS  PubMed  Google Scholar 

  25. Smith SW, Walsh B, Grauer K, et al. A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation. J Electrocardiol. 2019;52:88–95. https://doi.org/10.1016/J.JELECTROCARD.2018.11.013.

    Article  PubMed  Google Scholar 

  26. Maille B, Wilkin M, Million M, et al. Smartwatch electrocardiogram and artificial intelligence for assessing cardiac-rhythm safety of drug therapy in the COVID-19 pandemic. The QT-logs study. Int J Cardiol. 2021;331:333–9. https://doi.org/10.1016/J.IJCARD.2021.01.002.

    Article  PubMed  PubMed Central  Google Scholar 

  27. Fiorina L, Maupain C, Gardella C, et al. Evaluation of an ambulatory ECG analysis platform using deep neural networks in routine clinical practice. J Am Heart Assoc. 2022;11(18):26196. https://doi.org/10.1161/JAHA.122.026196.

    Article  Google Scholar 

  28. Brattain LJ, Pierce TT, Gjesteby LA, et al. AI-enabled, ultrasound-guided handheld robotic device for femoral vascular access. Biosens 2021. 2021;11(12):522. https://doi.org/10.3390/BIOS11120522.

    Article  Google Scholar 

  29. Mafeld S, Musing ELS, Conway A, Kennedy S, Oreopoulos G, Rajan D. Avoiding and managing error in interventional radiology practice: tips and tools. Can Assoc Radiol J. 2020;71(4):528–35. https://doi.org/10.1177/0846537119899215.

    Article  PubMed  Google Scholar 

  30. Conway A, Collins P, Chang K, et al. Pre-apneic capnography waveform abnormalities during procedural sedation and analgesia. J Clin Monit Comput. 2020;34(5):1061–8.

    Article  PubMed  Google Scholar 

  31. Conway A, Jungquist CR, Chang K, et al. Predicting prolonged apnea during nurse-administered procedural sedation: machine learning study. JMIR Perioper Med. 2021;4(2):e29200.

    Article  PubMed  PubMed Central  Google Scholar 

  32. Conway A, Rolley J, Page K, Fulbrook P. Issues and challenges associated with nurse-administered procedural sedation and analgesia in the cardiac catheterisation laboratory: a qualitative study. J Clin Nurs. 2014;23(3–4):374–84.

    Article  PubMed  Google Scholar 

  33. Conway A, Collins P, Chang K, et al. High flow nasal oxygen during procedural sedation for cardiac implantable electronic device procedures: a randomised controlled trial. Eur J Anaesthesiology. 2021;38(8):839–49.

    Article  Google Scholar 

  34. Howard JP, Cook CM, van de Hoef TP, et al. Artificial Intelligence for aortic pressure Waveform Analysis during Coronary Angiography: machine learning for Patient Safety. JACC Cardiovasc Interv. 2019;12(20):2093–101. https://doi.org/10.1016/J.JCIN.2019.06.036.

    Article  PubMed  Google Scholar 

  35. Arnold AD, Howard JP, Gopi A, et al. Discriminating electrocardiographic responses to his-bundle pacing using machine learning. Cardiovasc Digit Health J. 2020;1(1):11–20. https://doi.org/10.1016/J.CVDHJ.2020.07.001.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Funding

Data from this study were obtained from the PRODIGY trial, which was funded by Medtronic. The current study received no funding.

Author information

Authors and Affiliations

  1. Peter Munk Cardiac Centre, University Health Network, Toronto, Canada

    Aaron Conway

  2. Lawrence S. Bloomberg Faculty of Nursing, University of Toronto, Toronto, Canada

    Aaron Conway, Mohammad Goudarzi Rad & Wentao Zhou

  3. Department of Anesthesia and Pain Management, Toronto General Hospital, UHN, Toronto, Canada

    Matteo Parotto

  4. Department of Anesthesiology and Pain Medicine and Interdepartmental Division of Critical Care Medicine, University of Toronto, Toronto, Canada

    Matteo Parotto

  5. University at Buffalo, Buffalo, NY, USA

    Carla Jungquist

Authors
  1. Aaron Conway
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mohammad Goudarzi Rad
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Wentao Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Matteo Parotto
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Carla Jungquist
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Labelling of data was performed by AC and MG. Data analysis was performed by AC and WZ. The first draft of the manuscript was written by AC and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Aaron Conway.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher’s Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Conway, A., Goudarzi Rad, M., Zhou, W. et al. Deep learning classification of capnography waveforms: secondary analysis of the PRODIGY study. J Clin Monit Comput 37, 1327–1339 (2023). https://doi.org/10.1007/s10877-023-01028-y

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10877-023-01028-y

Keywords

Search

Navigation