International journal of advanced smart convergence

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

EEG Feature Engineering for Machine Learning-Based CPAP Titration Optimization in Obstructive Sleep Apnea

  • Juhyeong Kang (Department of Artificial Intelligence Convergence, Ewha Womans University) ;
  • Yeojin Kim (Department of Computer Science and Engineering, Ewha Womans University) ;
  • Jiseon Yang (Department of Mathematics, Ewha Womans University) ;
  • Seungwon Chung (Department of Neurology, Ewha Womans University Mokdong Hospital) ;
  • Sungeun Hwang (Department of Neurology, Ewha Womans University Mokdong Hospital) ;
  • Uran Oh (Department of Computer Science and Engineering, Ewha Womans University) ;
  • Hyang Woon Lee (Departments of Neurology and Medical Science, College of Medicine and Ewha Medical Research Institute, Graduate Programs of Artificial Intelligence Convergence and System Health Science & Engineering, Ewha Womans University)
  • Received : 2023.07.14
  • Accepted : 2023.07.23
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

Keywords

Acknowledgement

This work was supported by Institute of Information communications Technology Planning Evaluation (IITP) grant funded by the Korea government (MSIT) (No. RS-2022-00155966, Artificial Intelligence Convergence Innovation Human Resources Development (Ewha Womans University)) to JK, YK, JY, UO, HWL, and the Basic Research Lab Program through the National Research Foundation of Korea (NRF2021R1A4A1032582) to UO, and partly supported by grants from the Basic Science Research Program, Convergent Technology R&D Program for Human Augmentation, and BK21 Plus Program through the NRF funded by the Ministry of Science, Information and Communication Technologies/Ministry of Education & Future Planning (NRF-2019M3C1B8090803, 2020R1A2C2013216, and RS-2023-00265524) to HWL.

References

  1. K. A. Hutchinson, S. A. Karmali, J. Abi-Jaoude, T. Edwards, and C. Homsy, "Sleep quality among burn survivors and the importance of intervention: a systematic review and meta-analysis," Journal of Burn Care & Research, vol. 43, no. 6, pp. 1358-1379, 2022. DOI: https://doi.org/10.1093/jbcr/irac039
  2. R. Staats, I. Barros, D. Fernandes, D. Grencho, C. Reis, F. Matos, J. Valenc,a, J. Maroco, A. B. d. ˆAlmeida, and C. Barbara, "The importance of sleep fragmentation on the hemodynamic dipping in 'obstructive sleep apnea patients," Frontiers in Physiology, vol. 11, p. 104, 2020. DOI: https://doi.org/10.3389/fphys.2020.00104
  3. F. A. Grewe, M. Bradicich, T. Gaisl, M. Roeder, S. Thiel, N. A. Sievi, and M. Kohler, "Patterns of nightly cpap usage in osa patients with suboptimal treatment adherence," Sleep medicine, vol. 74, pp. 109-115, 2020. DOI: https://doi.org/10.1016/j.sleep.2020.05.042
  4. C. D. Turnbull, D. J. Bratton, S. E. Craig, M. Kohler, and J. R. Stradling, "In patients with minimally symptomatic osa can baseline characteristics and early patterns of cpap usage predict those who are likely to be longer-term users of cpap," Journal of thoracic disease, vol. 8, no. 2, p. 276, 2016. DOI: https://doi.org/10.3978/j.issn.2072-1439.2016.01.54
  5. P. Tovichien, A. Kulbun, and K. Udomittipong, "Comparing adherence of continuous and automatic positive airway pressure (cpap and apap) in obstructive sleep apnea (osa) children," Frontiers in Pediatrics, vol. 10, p. 841705, 2022. DOI: https://doi.org/10.3389/fped.2022.841705
  6. C. A. Kushida, A. Chediak, R. B. Berry, L. K. Brown, D. Gozal, C. Iber, S. Parthasarathy, S. F. Quan, J. A. Rowley, et al., "Clinical guidelines for the manual titration of positive airway pressure in patients with obstructive sleep apnea.," Journal of clinical sleep medicine: JCSM: official publication of the American Academy of Sleep Medicine, vol. 4, no. 2, pp. 157-171, 2008. DOI: https://doi.org/10.5664/jcsm.27133
  7. C. E. Sullivan, F. G. Issa, M. Berthon-Jones, and L. Eves, "Reversal of obstructive sleep apnoea by continuous positive airway pressure applied through the nares," Lancet, vol. 1, no. 8225, pp. 862-865, 1981. DOI: https://doi.org/10.1016/s0140-6736(81)92140-1
  8. L. J. Epstein, D. Kristo, P. J. Strollo Jr, N. Friedman, A. Malhotra, S. Patil, K. Ramar, R. Rogers, R. Schwab, E. Weaver, et al., "Adult obstructive sleep apnea task force of the american academy of sleep medicine. clinical guideline for the evaluation, management and long-term care of obstructive sleep apnea in adults," J Clin Sleep Med, vol. 5, no. 3, pp. 263-276, 2009. https://doi.org/10.5664/jcsm.27497
  9. V. Vimala, K. Ramar, and M. Ettappan, "An intelligent sleep apnea classification system based on eeg signals," Journal of medical systems, vol. 43, no. 2, p. 36, 2019. DOI: https://doi.org/10.1007/s10916-018-1146-8
  10. W. S. Almuhammadi, K. A. Aboalayon, and M. Faezipour, "Efficient obstructive sleep apnea classification based on eeg signals," in 2015 Long Island Systems, Applications and Technology, pp. 1-6, IEEE, 2015. DOI: https://doi.org/10.1109/LISAT.2015.7160186
  11. M. D. Khursheed, S. Parveen, and O. Farooq, "Machine learning based system for sleep apnea classification using eeg signal," in 2022 Second International Conference on Computer Science, Engineering and Applications (ICCSEA), pp. 1-5, IEEE, 2022. DOI: https://doi.org/10.1109/ICCSEA54677.2022.9936304
  12. X. Zhao, X. Wang, T. Yang, S. Ji, H. Wang, J. Wang, Y. Wang, and Q. Wu, "Classification of sleep apnea based on eeg sub-band signal characteristics," Scientific Reports, vol. 11, no. 1, p. 5824, 2021. DOI : https://doi.org/10.1038/s41598-021-85138-0
  13. C. Kang, S. An, H. J. Kim, M. Devi, A. Cho, S. Hwang, and H. W. Lee, "Age-integrated artificial intelligence framework for sleep stage classification and obstructive sleep apnea screening," Frontiers in Neuroscience, vol. 17, p. 1059186, 2023. DOI : https://doi.org/10.3389/fnins.2023.1059186
  14. M. E. S., B. K., D. H., K. Ludwig, K. N., H. T., G. H., and M. M., "A Novel Quantitative Arousal-Associated EEG-Metric to Predict Severity of Respiratory Distress in Obstructive Sleep Apnea Patients," Front. Physiol., vol. 13, p. 885270, 2022. DOI : DOI: https://doi.org/10.3389/fphys.2022.885270
  15. Y. J. Lee, J. W. Kim, Y.-J. G. Lee, and D.-U. Jeong, "Sleep eeg characteristics in young and elderly patients with obstructive sleep apnea syndrome," Psychiatry Investigation, vol. 13, no. 2, p. 217, 2016. DOI: https://doi.org/10.4306/pi.2016.13.2.217
  16. S. S. Kim and K. I. Yang, "Predictive model of optimal continuous positive airway pressure for obstructive sleep apnea patients with obesity by using machine learning," Journal of Sleep Medicine, vol. 15, no. 2, pp. 48-54, 2018. DOI: https://doi.org/10.13078/jsm.18012
  17. R. Adams, S. Appleton, A. Vakulin, A. D'Rozario, R. D. McEvoy, P. Catcheside, S. Martin, C. Lang, A. Vincent, and G. Wittert, "Effect of sleep apnea and insomnia on the association of depression with quantitative electroencephalogram measures (qeeg) in adult men during sleep-the mailes study," Sleep Medicine, vol. 40, no. Supplement 1, pp. e5-e6, 2017. DOI: https://doi.org/10.1016/j.sleep.2017.11.009
  18. R. Bellman, "Dynamic programming," Science, vol. 153, no. 3731, pp. 34-37, 1966. DOI : https://doi.org/10.1126/science.153.3731.34
  19. B. Hjorth, "Time domain descriptors and their relation to a particular model for generation of eeg activity," CEAN-Computerized EEG analysis, pp. 3-8, 1975.
  20. P. Memar and F. Faradji, "A Novel Multi-Class EEG-Based Sleep Stage Classification System," in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 1, pp. 84-95, Jan. 2018, DOI: 10.1109/TNSRE.2017.2776149.
  21. R. M. Mehmood, M. Bilal, S. Vimal, and S.-W. Lee, "Eeg-based affective state recognition from human brain signals by using hjorth-activity," Measurement, vol. 202, p. 111738, 2022. DOI : https://doi.org/10.1016/j.measurement.2022.111738
  22. A. B. Gardner, A. M. Krieger, G. Vachtsevanos, B. Litt, and L. P. Kaelbing, "One-class novelty detection for seizure analysis from intracranial eeg.," Journal of Machine Learning Research, vol. 7, no. 6, 2006.
  23. B. S,en, M. Peker, A. C, avus,oglu, and F. V. C, elebi, "A comparative study on classification of sleep stage based on eeg signals using feature selection and classification algorithms," Journal of medical systems, vol. 38, pp. 1-21, 2014. DOI : https://doi.org/10.1007/s10916-014-0018-0
  24. M. Albayrak, "The detection of an epileptiform activity on EEG signals by using data mining process," Technol. Appl. Sci., vol. 4, no. 1, pp. 1-12, 2009.
  25. S. Ozsen, "Classification of sleep stages using class-dependent sequential feature selection and artificial neural network," Neural Computing and Applications, vol. 23, pp. 1239-1250, 2013. DOI : https://doi.org/10.1007/s00521-012-1065-4
  26. L. Breiman, "Random forests," Machine learning, vol. 45, pp. 5-32, 2001. DOI : https://doi.org/10.1023/A:1010933404324
  27. C. Cortes and V. Vapnik, "Support-vector networks," Machine learning, vol. 20, pp. 273-297, 1995. DOI : https://doi.org/10.1007/BF00994018
  28. T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," in Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pp. 785-794, 2016. DOI : https://doi.org/10.1145/2939672.2939785
  29. S. M. Lundberg and S.-I. Lee, "A unified approach to interpreting model predictions," Advances in neural information processing systems, vol. 30, 2017.
  30. Y. Kim, J. Yang, D. Rim, and U. Oh, "Prediction of cognitive ability utilizing a machine learning approach based on digital therapeutics log data," The International Journal of Advanced Smart Convergence, vol. 12, no. 2, pp. 17-24, 2023. DOI: http://doi.org/10.7236/IJASC.2023.12.2.17
  31. JeeEun. Lee and Sun Kook Yoo, "Correlation Analysis of Electrocardiogram Signal according to Sleep Stage," Journal of Korea Multimedia Society, vol. 21, no. 12, pp. 1370-1378, 2018. DOI: http://dx.doi.org/10.9717/kmms.2018.21.12.1370