OSA-weigher: an automated computational framework for identifying obstructive sleep apnea based on event phase segmentation

  • Fan Liu
  • Xingshe Zhou
  • Zhu Wang
  • Hongbo Ni
  • Tianben Wang
Original Research
  • 36 Downloads

Abstract

Obstructive sleep apnea (OSA) is one of the most common sleep-related breathing disorders, which causes various diseases and reduces life quality severely. In this paper, we propose OSA-Weigher, an automated computational framework that can improve the performance of identifying OSA events. Particularly, the key idea of OSA-Weigher is to subdivide each potential event segment (PES, i.e., a data segment that may or may not contain an OSA event) and to explore more information of respiratory pattern, so as to improve OSA events identification performance. Concretely, we utilize a micro-movement sensitive mattress (MSM) to get ballistocardiography (BCG) signal during sleep, and locate PESs by identifying the occurrence of arousals (i.e., a mechanism that makes patients recover from being apneic). Afterwards, we divide each PES into three phases (i.e., Apnea Phase, Respiratory Effort Phase and Arousal Phase) using a sliding window-based adaptive method. Based on these phases, we further extract and select efficient fine-grained features to characterize respiratory pattern from multiple aspects. Finally, these PESs are classified into OSA events or non-OSA events by employing an optimized ensemble classifier. Experimental results based on a real BCG dataset of 116 subjects show that OSA-Weigher outperforms the baseline method by 12.7% in terms of Precision, 14.8% in terms of Recall and 0.152 in terms of AUC (area under ROC curve).

Keywords

Obstructive sleep apnea OSA Apnea Respiratory effort Arousal Event structure 

Notes

Acknowledgements

This work was partially supported by the National Natural Science Foundation of China (No. 61332013), the National Key Research and Development Program of China (No. 2016YFB1001400), and the China Scholarship Council (No. 201706290110).

References

  1. Al-Angari HM, Sahakian AV (2007) Use of sample entropy approach to study heart rate variability in obstructive sleep apnea syndrome. IEEE Trans Biomed Eng 54(10):1900–1904.  https://doi.org/10.1109/tbme.2006.889772 CrossRefGoogle Scholar
  2. Al-Angari HM, Sahakian AV (2012) Automated recognition of obstructive sleep apnea syndrome using support vector machine classifier. IEEE Trans Inf Technol Biomed 16(3):463–468.  https://doi.org/10.1109/titb.2012.2185809 CrossRefGoogle Scholar
  3. Behar J, Roebuck A, Shahid M et al (2015) Sleepap: an automated obstructive sleep apnoea screening application for smartphones. IEEE J Biomed Health Inf 19(1):325–331.  https://doi.org/10.1109/jbhi.2014.2307913 CrossRefGoogle Scholar
  4. Berry RB, Gleeson K (1997) Respiratory arousal from sleep: mechanisms and significance. Sleep 20(8):654–675.  https://doi.org/10.1093/sleep/20.8.654 CrossRefGoogle Scholar
  5. Bsoul M, Minn H, Tamil L (2011) Apnea MedAssist: real-time sleep apnea monitor using single-lead ECG. IEEE Trans Inf Technol Biomed 15(3):416–427.  https://doi.org/10.1109/titb.2010.2087386 CrossRefGoogle Scholar
  6. Chen L, Zhang X, Song C (2015) An automatic screening approach for obstructive sleep apnea diagnosis based on single-lead electrocardiogram. IEEE Trans Autom Sci Eng 12(1):106–115.  https://doi.org/10.1109/tase.2014.2345667 CrossRefGoogle Scholar
  7. Cheung K, Ishman SL, Benke JR et al (2016) Prediction of obstructive sleep apnea using visual photographic analysis. J Clin Anesth 32:40–46.  https://doi.org/10.5665/sleep/32.1.46 CrossRefGoogle Scholar
  8. Corbishley P, Rodríguez-Villegas E (2008) Breathing detection: towards a miniaturized, wearable, battery-operated monitoring system. IEEE Trans Biomed Eng 55(1):196–204.  https://doi.org/10.1109/tbme.2007.910679 CrossRefGoogle Scholar
  9. Daulatzai MAKA., Khandoker AH, Karmakar CK et al (2009) Characterization of chimeric surface submentalis EMG activity during hypopneas in obstructive sleep apnea patients. In: Science and Technology for Humanity (TIC-STH), Toronto International Conference, IEEE, pp 782–788.  https://doi.org/10.1109/tic-sth.2009.5444394
  10. De Chazal P, Heneghan C, Sheridan E et al (2003) Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea. IEEE Trans Biomed Eng 50(6):686–696.  https://doi.org/10.1109/tbme.2003.812203 CrossRefGoogle Scholar
  11. Dingli K, Fietze I, Assimakopoulos T et al (2002) Arousability in sleep apnoea/hypopnoea syndrome patients. Eur Respir J 20(3):733–740.  https://doi.org/10.1183/09031936.02.00262002 CrossRefGoogle Scholar
  12. Fujiwara K, Miyajima M, Yamakawa T et al (2016) Epileptic seizure prediction based on multivariate statistical process control of heart rate variability features. IEEE Trans Biomed Eng 63(6):1321–1332.  https://doi.org/10.1109/tbme.2015.2512276 CrossRefGoogle Scholar
  13. Hassan AR (2016) Computer-aided obstructive sleep apnea detection using normal inverse Gaussian parameters and adaptive boosting. Biomed Signal Process Control 29:22–30.  https://doi.org/10.1016/j.bspc.2016.05.009 CrossRefGoogle Scholar
  14. Isa SM, Fanany MI, Jatmiko W et al (2011) Sleep Apnea Detection from ECG signal: analysis on optimal features, principal components, and nonlinearity. In: Bioinformatics and Biomedical Engineering (iCBBE), IEEE 5th International Conference on, pp 1–4.  https://doi.org/10.1109/icbbe.2011.5780285
  15. Jin J, Sánchez-Sinencio E (2015) A home sleep apnea screening device with time-domain signal processing and autonomous scoring capability. IEEE Trans Biomed Circuits Syst 9(1):96–104.  https://doi.org/10.1109/tbcas.2014.2314301 CrossRefGoogle Scholar
  16. Jones SG, Riedner BA, Smith RF et al (2014) Regional reductions in sleep electroencephalography power in obstructive sleep apnea: a high-density EEG study. Sleep 37(2):399–407.  https://doi.org/10.5665/sleep.3424 Google Scholar
  17. Kim KK, Kim JS, Lim YG et al (2009) The effect of missing RR-interval data on heart rate variability analysis in the frequency domain. Physiol Meas 30(10):1039.  https://doi.org/10.1088/0967-3334/30/10/005 CrossRefGoogle Scholar
  18. Koley BL, Dey D (2012a) Selection of features for detection of obstructive sleep apnea events. In: Annual IEEE India Conference (INDICON), IEEE, pp 991–996.  https://doi.org/10.1109/indcon.2012.6420761
  19. Koley B, Dey D (2012b) Automated detection of apnea and hypopnea events. In: Emerging Applications of Information Technology (EAIT), IEEE 3rd International Conference on, pp 85–88.  https://doi.org/10.1109/eait.2012.6407868
  20. Lázaro J, Gil E, Vergara JM et al (2014) Pulse rate variability analysis for discrimination of sleep-apnea-related decreases in the amplitude fluctuations of pulse photoplethysmographic signal in children. IEEE J Biomed Health Inf 18(1):240–246.  https://doi.org/10.1109/jbhi.2013.2267096 CrossRefGoogle Scholar
  21. Lévy P, Kohler M, McNicholas WT et al (2015) Obstructive sleep apnoea syndrome. Nat Rev Dis Primers 1:15015.  https://doi.org/10.1038/nrdp.2015.15 CrossRefGoogle Scholar
  22. Liu F, Zhou X, Wang Z et al (2016a) A light-weight data preprocessing and integrative scheduling framework for health monitoring. In: Biomedical and Health Informatics (BHI), IEEE-EMBS International Conference on, pp 192–195.  https://doi.org/10.1109/bhi.2016.7455867
  23. Liu F, Zhou X, Wang Z et al (2016b) Identifying obstructive sleep apnea by exploiting fine-grained BCG features Based on Event Phase Segmentation. In: Bioinformatics and bioengineering (BIBE), IEEE 16th International Conference on, pp 293–300.  https://doi.org/10.1109/bibe.2016.45
  24. Malhotra A, White DP (2002) Obstructive sleep apnoea. The lancet 360(9328):237–245.  https://doi.org/10.1016/s0140-6736(02)09464-3 CrossRefGoogle Scholar
  25. Nandakumar R, Gollakota S, Watson N (2015) Contactless sleep apnea detection on smartphones. In: Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services. ACM, pp 45–57.  https://doi.org/10.1145/2742647.2742674
  26. Ohisa N, Ogawa H, Murayama N et al (2011) A novel EEG index for evaluating the sleep quality in patients with obstructive sleep apnea-hypopnea syndrome. Tohoku J Exp Med 223(4):285–289.  https://doi.org/10.1620/tjem.223.285 CrossRefGoogle Scholar
  27. Penzel T, Kantelhardt JW, Grote L et al (2003) Comparison of detrended fluctuation analysis and spectral analysis for heart rate variability in sleep and sleep apnea. IEEE Trans Biomed Eng 50(10):1143–1151.  https://doi.org/10.1109/tbme.2003.817636 CrossRefGoogle Scholar
  28. Peppard PE, Young T, Barnet JH et al (2013) Increased prevalence of sleep-disordered breathing in adults. Am J Epidemiol 177(9):1006–1014.  https://doi.org/10.1093/aje/kws342 CrossRefGoogle Scholar
  29. Pitson D, Stradling J (1998) Autonomic markers of arousal during sleep in patients undergoing investigation for obstructive sleep apnoea, their relationship to EEG arousals, respiratory events and subjective sleepiness. J Sleep Res 7(1):53–59.  https://doi.org/10.1046/j.1365-2869.1998.00092.x CrossRefGoogle Scholar
  30. Quan SF, Gillin JC, Littner MR et al (1999) Sleep-related breathing disorders in adults: Recommendations for syndrome definition and measurement techniques in clinical research. Sleep 22(5):667–689.  https://doi.org/10.1093/sleep/22.5.667 CrossRefGoogle Scholar
  31. RS-611 (2018). The sleep monitoring system. Beijing RisingSun Science-Tech Co., Ltd. http://www.risingsuntec.cn/04-product/product.htm. Accessed 1 Jan 2018
  32. Samy L, Macey PM, Alshurafa N et al (2015) An automated framework for predicting obstructive sleep apnea using a brief, daytime, non-intrusive test procedure. In: Proceedings of the 8th ACM International Conference on Pervasive Technologies Related to Assistive Environments, pp 70.  https://doi.org/10.1145/2769493.2769541
  33. SOMNOscreenTM plus (2018). The Portable PSG. SOMNOmedics Germany, http://somnomedics.eu/products/polysomnography-somnoscreentm-plus/. Accessed 9 Jan 2018
  34. Varon C, Caicedo A, Testelmans D et al (2015) A novel algorithm for the automatic detection of sleep apnea from single-lead ECG. IEEE Trans Biomed Eng 62(9):2269–2278.  https://doi.org/10.1109/tbme.2015.2422378 CrossRefGoogle Scholar
  35. Wang Z, Zhou X, Zhao W et al (2017) Assessing the severity of sleep apnea syndrome based on ballistocardiogram. PloS One 12(4):e0175351.  https://doi.org/10.1371/journal.pone.0175351 CrossRefGoogle Scholar
  36. Wang Z, Guo B, Yu Z et al (2018) Wi-Fi CSI based behavior recognition: from signals, actions to activities. IEEE Commun Mag. arXiv:1712.00146Google Scholar
  37. Wu Y, Krishnan S (2010) Statistical analysis of gait rhythm in patients with Parkinson’s disease. IEEE Trans Neural Syst Rehabil Eng 18(2):150–158.  https://doi.org/10.1109/tnsre.2009.2033062 CrossRefGoogle Scholar
  38. Xie B, Minn H (2012) Real-time sleep apnea detection by classifier combination. IEEE Trans Inf Technol Biomed 16(3):469–477.  https://doi.org/10.1109/titb.2012.2188299 CrossRefGoogle Scholar
  39. Younes M (2004) Role of arousals in the pathogenesis of obstructive sleep apnea. Am J Respir Crit Care Med 169(5):623–633.  https://doi.org/10.1164/rccm.200307-1023oc CrossRefGoogle Scholar
  40. Zhang J, Zhang Q, Wang Y et al (2013) A real-time auto-adjustable smart pillow system for sleep apnea detection and treatment. In: Proceedings of the 12th International Conference on Information Processing in Sensor Networks (IPSN), ACM, pp 179–190.  https://doi.org/10.1145/2461381.2461405
  41. Zhao W, Ni H, Zhou X et al (2015) Identifying sleep apnea syndrome using heart rate and breathing effort variation analysis based on ballistocardiography. In: Engineering in Medicine and Biology Society (EMBC), 37th Annual International Conference of the IEEE, IEEE, pp 4536–4539.  https://doi.org/10.1109/embc.2015.7319403

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of Computer ScienceNorthwestern Polytechnical UniversityXi’anChina

Personalised recommendations