Snoring Sounds Classification of OSAHS Patients Based on Model Fusion

Downloads

Authors

  • Yexin LUO School of Physics and Optoelectronics, South China University of Technology, China
  • Jianxin PENG School of Physics and Optoelectronics, South China University of Technology, China
  • Li DING School of Advanced Manufacturing Engineering, Hefei University, China
  • Yikai ZHANG School of Physics and Optoelectronics, South China University of Technology, China
  • Lijuan SONG State Key Laboratory of Respiratory Disease, Department of Otolaryngology-Head and Neck Surgery, Laboratory of ENT-HNS Disease, First Affiliated Hospital, Guangzhou Medical University, China
  • Qianfan ZHANG School of Physics and Optoelectronics, South China University of Technology, China
  • Houpeng CHEN School of Physics and Optoelectronics, South China University of Technology, China

Abstract

Obstructive sleep apnea hypopnea syndrome (OSAHS) is a prevalent and detrimental chronic condition. The conventional diagnostic approach for OSAHS is intricate and costly. Snoring is one of the most typical and easily obtained symptom of OSAHS patients. In this study, a series of acoustic features are extracted from snoring sounds. A fused model that integrates a deep neural network, K-nearest neighbors (KNN), and a random under sampling boost algorithm is proposed to classify snoring sounds of simple snorers (SSSS), simple snoring sounds of OSAHS patients (SSSP), and apnea-hypopnea snoring sounds of OSAHS patients (APSP). The ReliefF algorithm is employed to select features with high relevance in each classification model. A hard voting strategy is implemented to obtain an optimal fused model. Results show that the proposed fused model achieves commendable performance with an accuracy rate of 85.76 %. It demonstrates the effectiveness and validity of assisting in diagnosing OSAHS patients based on the analysis of snoring sounds.

Keywords:

obstructive sleep apnea hypopnea syndrome, snoring sounds, deep neural network, model fusion

References

1. Alshaer H., Hummel R., Mendelson M., Marshal T., Bradley T.D. (2019), Objective relationship between sleep apnea and frequency of snoring assessed by machine learning, Journal of Clinical Sleep Medicine, 15(3): 463–470, https://doi.org/10.5664/jcsm.7676

2. Azarbarzin A., Moussavi Z. (2013), Snoring sounds variability as a signature of obstructive sleep apnea, Medical Engineering and Physics, 35(4): 479–485, https://doi.org/10.1016/j.medengphy.2012.06.013

3. Berry R.B. et al. (2012), Rules for scoring respiratory events in sleep: Update of the 2007 AASM manual for the scoring of sleep and associated events, Journal of Clinical Sleep Medicine, 8(5): 597–619, https://doi.org/10.5664/jcsm.2172

4. Caron C.J.J.M. et al. (2017), Obstructive sleep apnoea in craniofacial microsomia: Analysis of 755 patients, International Journal of Oral and Maxillofacial Surgery, 46(10): 1330–1337, https://doi.org/10.1016/j.ijom.2017.05.020

5. Castillo-Escario Y., Ferrer-Lluis I., Montserrat J.M., Jane R. (2019), Entropy analysis of acoustic signals recorded with a smartphone for detecting apneas and hypopneas: A comparison with a commercial system for home sleep apnea diagnosis, IEEE Access, 7: 128224–128241, https://doi.org/10.1109/ACCESS.2019.2939749

6. Cheng S. et al. (2022), Automated sleep apnea detection in snoring signal using long short-term memory neural networks, Biomedical Signal Processing and Control, 71(Part B): 103238, https://doi.org/10.1016/j.bspc.2021.103238

7. Ding L., Peng J., Song L., Zhang X. (2023), Automatically detecting apnea-hypopnea snoring signal based on VGG19 + LSTM, Biomedical Signal Processing and Control, 80(Part 2): 104351, https://doi.org/10.1016/j.bspc.2022.104351

8. Ding L., Peng J., Song L., Zhang X. (2024), Automatically detecting OSAHS patients based on transfer learning and model fusion, Physiological Measurement, 45(5): 055013, https://doi.org/10.1088/1361-6579/ad4953

9. Eckert D.J., Jordan A.S., Merchia P., Malhotra A. (2007), Central sleep apnea: Pathophysiology and treatment, Chest, 131(2): 595–607, https://doi.org/10.1378/chest.06.2287

10. Fiz J.A. et al. (1996), Acoustic analysis of snoring sound in patients with simple snoring and obstructive sleep apnoea, European Respiratory Journal, 9(11): 2365–2370, https://doi.org/10.1183/09031936.96.09112365

11. Friedman M., Ibrahim H., Joseph N.J. (2004), Staging of obstructive sleep apnea/hypopnea syndrome: A guide to appropriate treatment, Laryngoscope, 114(3): 454–459, https://doi.org/10.1097/00005537-200403000-00013

12. Ghosh P., Varma N.K.S., Ajith V.V., Suresh A. (2021), Upper airway and its association with neck circumference and hyoid position in OSA subjects – A cephalometric study, International Journal of Current Research and Review, 13(6): 167–171, https://doi.org/10.31782/IJCRR.2021.13610

13. Gislason T., Benediktsdottir B. (1995), Snoring, apneic episodes, and nocturnal hypoxemia among children 6 months to 6 years old: An epidemiologic study of lower limit of prevalence, Chest, 107(4): 963–966, https://doi.org/10.1378/chest.107.4.963

14. Gottlieb D.J., Punjabi N.M. (2020), Diagnosis and management of obstructive sleep apnea: A review, Journal of the American Medical Association, 323(14): 1389–1400, https://doi.org/10.1001/jama.2020.3514

15. Herzog M., Schmidt A., Bremert T., Herzog B., Hosemann W., Kaftan H. (2008), Analysed snoring sounds correlate to obstructive sleep disordered breathing, European Archives of Oto-Rhino-Laryngology, 265(1): 105–113, https://doi.org/10.1007/s00405-007-0408-8

16. Hou L., Zhang W., Shi D., Liu H. (2019), Estimation of apnea hypopnea index based on acoustic features of snoring, Journal of Shanghai University (Natural Science), 25(4): 435–444, https://doi.org/10.12066/j.issn.1007-2861.1942

17. Izci B., Douglas N.J. (2012), Obstructive sleep apnea-hypopnea syndrome, [in:] Obstructive Sleep Apnea: Causes, Treatment and Health Implications, Sacchetti L.M., Mangiardi P. [Eds.], pp. 129–182, Nova Science Publishers.

18. Janiesch C., Zschech P., Heinrich K. (2021), Machine learning and deep learning, Electronic Markets, 31(3): 685–695, https://doi.org/10.1007/s12525-021-00475-2

19. Karunajeewa A.S., Abeyratne U.R., Hukins C. (2011), Multi-feature snore sound analysis in obstructive sleep apnea–hypopnea syndrome, Physiological Measurement, 32(1): 83, https://doi.org/10.1088/0967-3334/32/1/006

20. Korompili G. et al. (2021), PSG-Audio, a scored polysomnography dataset with simultaneous audio recordings for sleep apnea studies, Scientific Data, 8(1): 197, https://doi.org/10.1038/s41597-021-00977-w

21. Kursa M.B., Rudnicki W.R. (2010), Feature selection with the Boruta package, Journal of Statistical Software, 36(11): 1–13, https://doi.org/10.18637/jss.v036.i11

22. Lee B.S., Ellis D.P.W. (2012), Noise robust pitch tracking by subband autocorrelation classification, [in:] 13th Annual Conference of the International Speech Communication Association 2012, https://doi.org/10.21437/interspeech.2012-221

23. Li J. et al. (2017), Feature selection: A data perspective, ACM Computing Surveys, 50(6): 94, https://doi.org/10.1145/3136625

24. Lugaresi E., Cirignotta F., Montagna P. (1988), Pathogenic aspects of snoring and obstructive apnea syndrome, Schweizerische Medizinische Wochenschrift, 118(38).

25. Markandeya M.N., Abeyratne U.R., Hukins C. (2018), Characterisation of upper airway obstructions using wide-band snoring sounds, Biomedical Signal Processing and Control, 46: 201–211, https://doi.org/10.1016/j.bspc.2018.07.013

26. Minaritzoglou A., Vagiakis E. (2008), Polysomnography: Recent data on procedure and analysis, Pneuomon, 21(4).

27. Osman A.M., Carter S.G., Carberry J.C., Eckert D.J. (2018), Obstructive sleep apnea: Current perspectives, Nature and Science of Sleep, 10: 21–34, https://doi.org/10.2147/NSS.S124657

28. Perez-Padilla J.R., Slawinski E., Difrancesco L.M., Feige R.R., Remmers J.E., Whitelaw W.A. (1993), Characteristics of the snoring noise in patients with and without occlusive sleep apnea, American Review of Respiratory Disease, 147(3), https://doi.org/10.1164/ajrccm/147.3.635

29. Pevernagie D., Aarts R.M., De Meyer M. (2010), The acoustics of snoring, Sleep Medicine Reviews, 14(2): 131–144, https://doi.org/10.1016/j.smrv.2009.06.002

30. Qian K. et al. (2021), Can machine learning assist locating the excitation of snore sound? A review, IEEE Journal of Biomedical and Health Informatics, 25(4): 1233–1246, https://doi.org/10.1109/JBHI.2020.3012666

31. Qian K., Janott C., Zhang Z., Heiser C., Schuller B. (2016), Wavelet features for classification of vote snore sounds, [in:] 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 221–225, https://doi.org/10.1109/ICASSP.2016.7471669

32. Redline S. et al. (2010), Obstructive sleep apnea–hypopnea and incident stroke, American Journal of Respiratory and Critical Care Medicine, 182(2), https://doi.org/10.1164/rccm.200911-1746oc

33. Seiffert C., Khoshgoftaar T.M., Van Hulse J., Napolitano A. (2010), RUSBoost: A hybrid approach to alleviating class imbalance, [in:] IEEE Transactions on Systems, Man, and Cybernetics Part A: Systems and Humans, 40(1): 185–197, https://doi.org/10.1109/TSMCA.2009.2029559

34. Shen F., Cheng S., Li Z., Yue K., Li W., Dai L. (2020), Detection of snore from OSAHS patients based on deep learning, Journal of Healthcare Engineering, https://doi.org/10.1155/2020/8864863

35. Sola-Soler J., Jane R., Fiz J.A., Morera J. (2007), Automatic classification of subjects with and without Sleep Apnea through snoring analysis, [in:] 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, https://doi.org/10.1109/IEMBS.2007.4353739

36. Song Y., Sun X., Ding L., Peng J., Song L., Zhang X. (2023), AHI estimation of OSAHS patients based on snoring classification and fusion model, American Journal of Otolaryngology, 44(5): 103964, https://doi.org/10.1016/j.amjoto.2023.103964

37. Sowho M., Sgambati F., Guzman M., Schneider H., Schwartz A. (2020), Snoring: A source of noise pollution and sleep apnea predictor, Sleep, 43(6), https://doi.org/10.1093/sleep/zsz305

38. Sun X., Ding L., Song Y., Peng J., Song L., Zhang X. (2023), Automatic identifying OSAHS patients and simple snorers based on Gaussian mixture models, Physiological Measurement, 44(4): 045003, https://doi.org/10.1088/1361-6579/accd43

39. Sun X., Peng J., Zhang X., Song L. (2022), Effective feature selection based on Fisher Ratio for snoring recognition using different validation methods, Applied Acoustics, 185: 108429, https://doi.org/10.1016/j.apacoust.2021.108429

40. Ulualp S.O. (2010), Snoring and obstructive sleep apnea, Medical Clinics of North America, 94(5): 1047–1055, https://doi.org/10.1016/j.mcna.2010.05.002

41. Wang C., Peng J., Song L., Zhang X. (2017), Automatic snoring sounds detection from sleep sounds via multi-features analysis, Australasian Physical and Engineering Sciences in Medicine, 40(1): 127–135, https://doi.org/10.1007/s13246-016-0507-1

42. White D.P. (2005), Pathogenesis of obstructive and central sleep apnea, American Journal of Respiratory and Critical Care Medicine, 172(11), https://doi.org/10.1164/rccm.200412-1631SO

43. Wu Z., Wang X., Jiang B. (2020), Fault diagnosis for wind turbines based on ReliefF and eXtreme gradient boosting, Applied Sciences, 10(9): 3258, https://doi.org/10.3390/app10093258

44. Zhang S., Li X., Zong M., Zhu X., Cheng D. (2017), Learning k for kNN Classification, ACM Transactions on Intelligent Systems and Technology, 8(3): 43, https://doi.org/10.1145/2990508

45. Zheng F., Zhang G., Song Z. (2001), Comparison of different implementations of MFCC, Journal of Computer Science and Technology, 16(6): 582–589, https://doi.org/10.1007/BF02943243

Other articles by the same author(s)