Skip to main content

Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model


Apnea-bradycardia (AB) is a common complication in prematurely born infants, which is associated with reduced survival and neurodevelopmental outcomes. Thus, early detection or predication of AB episodes is critical for initiating preventive interventions. To develop automatic real-time operating systems for early detection of AB, recent advances in signal processing can be employed. Hidden Markov Models (HMM) are probabilistic models with the ability of learning different dynamics of the real time-series such as clinical recordings. In this study, a hierarchy of HMMs named as layered HMM was presented to detect AB episodes from pre-processed single-channel Electrocardiography (ECG). For training the hierarchical structure, RR interval, and width of QRS complex were extracted from ECG as observations. The recordings of 32 premature infants with median 31.2 (29.7, 31.9) weeks of gestation were used for this study. The performance of the proposed layered HMM was evaluated in detecting AB. The best average accuracy of 97.14 ± 0.31% with detection delay of − 5.05 ± 0.41 s was achieved. The results show that layered structure can improve the performance of the detection system in early detecting of AB episodes. Such system can be incorporated for more robust long-term monitoring of preterm infants.

This is a preview of subscription content, access via your institution.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6







Neonatal intensive care unit




Hidden Markov Model


Layered Hidden Markov Model


Coupled Hidden Markov Model


Hidden semi-Markov Model


Coupled Hidden semi-Markov Model








Receiver operating characteristic


Area under the ROC curve


Perfect detection


Distance to PD


  1. Aarno, D., and D. Kragic. Evaluation of layered HMM for motion intention recognition. In: IEEE International Conference on Advanced Robotics, 2007.

  2. Aarno, D., and D. Kragic. Layered HMM for motion intention recognition. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, 2006.

  3. Aguirre, L. A., V. C. C. Barros, and Á. V. Souza. Nonlinear multivariable modeling and analysis of sleep apnea time series. Comput. Biol. Med. 29(3):207–228, 1999.

    Article  CAS  Google Scholar 

  4. Altuve, M., et al. Comparing hidden Markov model and hidden semi-Markov model based detectors of apnea-bradycardia episodes in preterm infants. In: Computing in Cardiology, 2012.

  5. Altuve, M., et al. On-line apnea-bradycardia detection using hidden semi-Markov models. In Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011.

  6. Altuve, M., et al. Multivariate ECG analysis for apnoea–bradycardia detection and characterisation in preterm infants. Int. J. Biomed. Eng. Technol. 5(2–3):247–265, 2011.

    Article  Google Scholar 

  7. Altuve, M., et al. Online apnea–bradycardia detection based on hidden semi-markov models. Medical & Biological Engineering & Computing 53(1):1–13, 2015.

    Article  Google Scholar 

  8. Cruz, J., et al. Algorithm fusion for the early detection of apnea-bradycardia in preterm infants. In: Computers in Cardiology, 2006.

  9. Gee, A. H., et al. Predicting Bradycardia in preterm infants using point process analysis of heart rate. IEEE Trans. Biomed. Eng. 64(9):2300–2308, 2017.

    Article  Google Scholar 

  10. Ghahjaverestan, N. M., et al. Coupled Hidden Markov model-based method for apnea bradycardia detection. IEEE J. Biomed. Health Inf. 20(2):527–538, 2016.

    Article  Google Scholar 

  11. Glodek, M., et al. Recognizing human activities using a layered Markov architecture. In: International Conference on Artificial Neural Networks, 2012. Berlin: Springer.

  12. He, L., C.-F. Zong, and C. Wang. Driving intention recognition and behaviour prediction based on a double-layer hidden Markov model. J. Zhejiang Univ. Sci. C 13(3):208–217, 2012.

    Article  Google Scholar 

  13. Hornero, R., et al. Utility of approximate entropy from overnight pulse oximetry data in the diagnosis of the obstructive sleep apnea syndrome. IEEE Trans. Biomed. Eng. 54(1):107–113, 2006.

    Article  Google Scholar 

  14. Kabir, M. H., et al. Two-layer hidden Markov model for human activity recognition in home environments. Int. J. Distrib. Sensor Netw. 2016:1–12, 2016.

    Google Scholar 

  15. Masoudi, S., et al. Early detection of apnea-bradycardia episodes in preterm infants based on coupled hidden Markov model. In: IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2013.

  16. McNames, J. and A. Fraser. Obstructive sleep apnea classification based on spectrogram patterns in the electrocardiogram. In: Computers in Cardiology 2000, Vol. 27 (Cat. 00CH37163), 2000, IEEE.

  17. Montazeri Ghahjaverestan, N., et al. Apnea bradycardia detection based on new coupled hidden semi Markov model. Med. Biol. Eng. Comput. 59:1–11, 2020.

    Article  Google Scholar 

  18. Oliver, N., A. Garg, and E. Horvitz. Layered representations for learning and inferring office activity from multiple sensory channels. Comput. Vis. Image Understand. 96(2):163–180, 2004.

    Article  Google Scholar 

  19. Pan, J., and W. J. Tompkins. A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. 3:230–236, 1985.

    Article  Google Scholar 

  20. Perdikis, S., T. Dimitrios, and M.G. Strintzis. Recognition of humans activities using layered hidden Markov models. In: Cognitive Information Processing Workshop, 2008.

  21. Poets, C. F., et al. The relationship between bradycardia, apnea, and hypoxemia in preterm infants. Pediatr. Res 34(2):144–147, 1993.

    Article  CAS  Google Scholar 

  22. Portet, F., et al. Evaluation of on-line bradycardia boundary detectors from neonatal clinical data. In: 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2007. IEEE.

  23. Rabiner, L. R. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77(2):257–286, 1989.

    Article  Google Scholar 

  24. Razin, Y. S., et al. Predicting task intent from surface electromyography using layered hidden Markov models. IEEE Robot. Autom. Lett. 2(2):1180–1185, 2017.

    Article  Google Scholar 

  25. Richard J. Martin, C.G.W., Apnea of Prematurity, in Comprehensive Physiology 2012. pp. 2923–2931.

  26. Shirwaikar, R.D., et al. Machine learning techniques for neonatal apnea prediction. J. Artific. Intell. 9(1–3), 2016.

  27. Solaimanpour, S., and P. Doshi. A layered HMM for predicting motion of a leader in multi-robot settings. In: IEEE International Conference on Robotics and Automation (ICRA), 2017.

  28. Thome, N., S. Miguet, and S. Ambellouis. A real-time, multiview fall detection system: a LHMM-based approach. IEEE Trans. Circ. Syst. Video Technol. 18(11):1522–1532, 2008.

    Article  Google Scholar 

  29. Williamson, J.R., et al. Individualized apnea prediction in preterm infants using cardio-respiratory and movement signals. In: IEEE International Conference on Body Sensor Networks, 2013.

Download references

Conflict of interest

The authors have no conflict of interest to declare.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Mohammad Bagher Shamsollahi.

Additional information

Associate Editor Ka-Wai Kwok oversaw the review of this article.

Publisher's Note

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

Rights and permissions

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sadoughi, A., Shamsollahi, M.B., Fatemizadeh, E. et al. Detection of Apnea Bradycardia from ECG Signals of Preterm Infants Using Layered Hidden Markov Model. Ann Biomed Eng 49, 2159–2169 (2021).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: