IEMEK Journal of Embedded Systems and Applications (대한임베디드공학회논문지)

Institute of Embedded Engineering of Korea (대한임베디드공학회)
권호 표지
DOI QR코드

DOI QR Code

Severity Prediction of Sleep Respiratory Disease Based on Statistical Analysis Using Machine Learning

머신러닝을 활용한 통계 분석 기반의 수면 호흡 장애 중증도 예측

  • Received : 2023.01.31
  • Accepted : 2023.04.13
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Currently, polysomnography is essential to diagnose sleep-related breathing disorders. However, there are several disadvantages to polysomnography, such as the requirement for multiple sensors and a long reading time. In this paper, we propose a system for predicting the severity of sleep-related breathing disorders at home utilizing measurable elements in a wearable device. To predict severity, the variables were refined through a three-step variable selection process, and the refined variables were used as inputs into three machine-learning models. As a result of the study, random forest models showed excellent prediction performance throughout. The best performance of the model in terms of F1 scores for the three threshold criteria of 5, 15, and 30 classified as the AHI index was about 87.3%, 90.7%, and 90.8%, respectively, and the maximum performance of the model for the three threshold criteria classified as the RDI index was approx 79.8%, 90.2%, and 90.1%, respectively.

Keywords

Acknowledgement

이 논문은 2023년도 정부 (산업통상자원부)의 재원으로 한국산업기술진흥원의 지원을 받아 수행된 연구임 (P0012724, 2023년 산업전문인력역량강화사업).

References

  1. J. K. Kim, K. H. In, J. H. Kim, S. H You, K. H. Kang, J. J. Shim, S. Y. Lee, J. B. Lee, S. G. Lee, C. Park, C. Shin, "Prevalence of Sleep-disordered Breathing in Middle-aged Korean Men and Women," American Journal of Respiratory and Critical Care Medicine, Vol. 170, No. 10, pp. 1108-1113, 2004. https://doi.org/10.1164/rccm.200404-519OC
  2. M. Arzt, T. Young, L. Finn, J. B. Skatrud, T. D. Bradley, "Association of Sleep-disordered Breathing and the Occurrence of Stroke," American Journal of Respiratory and Critical Care Medicine, Vol. 172, No. 11, pp. 1447-1451, 2005. https://doi.org/10.1164/rccm.200505-702OC
  3. H. K. Yaggi, J. Concato, W. N. Kernan, J. H. Lichtman, L. M. Brass, V. Mohsenin, "Obstructive Sleep Apnea as a Risk Factor for Stroke and Death," New England Journal of Medicine, Vol. 353, No. 19, pp. 2034-2041, 2005. https://doi.org/10.1056/NEJMoa043104
  4. S. J. Choi, "Complications of Obstructive Sleep Apnea," The Korean Journal of Medicine, Vol. 89, No. 1, pp. 13-20, 2015 (in Korean).  https://doi.org/10.3904/kjm.2015.89.1.13
  5. J. Teran, A. Jimenez, J. Cordero, Cooperative Group Burgos-Santander, "The Association Between Sleep Apnea and the Risk of Traffic Accidents," New England Journal of Medicine, Vol. 340, No. 11, pp. 847-851, 1999. https://doi.org/10.1056/NEJM199903183401104
  6. P. S. Jeong, "Development of Non-contact Sleep-disordered Breathing Detection System using Air-Mattress," Master Degree, Yonsei University, 2016 (in Korean). 
  7. P. S. Jeong, "Development of Non-contact Sleep-disordered Breathing Detection System using Air-Mattress," Master Degree, Yonsei University, 2016 (in Korean). 
  8. S. F. Quan, J. C. Gillin, M. R. Littner, J. W. Shepard, "Sleep-related Breathing Disorders in Adults: Recommendations for Syndrome Definition and Measurement Techniques in Clinical Research," Editorials. Sleep (New York, NY), Vol. 22, No, 5, pp. 662-689, 1999. https://doi.org/10.1093/sleep/22.5.667
  9. R. M. Kim, K. M. Kim, J. H. Ahn, "Comparison Between Random Forest and Recurrent Neural Network for Photovoltaic Power Forecasting," Journal of Korean Society Of Environmental Engineers, Vol. 43, No. 5, pp. 347-355, 2021 (in Korean).  https://doi.org/10.4491/KSEE.2021.43.5.347
  10. K. H. Hong, "A Predictive Model for Suicidal Ideation of Adolescents Using Random Forests Machine Learning Algorithm," Korean Journal of Social Welfare. Vol. 72, No. 3, pp. 157-180, 2020. https://doi.org/10.20970/kasw.2020.72.3.007
  11. B. S. Seo, "A Study on the Prediction Model of the Elderly Depression Based on Random Forest," Master Degree, Dankook University. 2019 (in Korean). 
  12. B. S. Seo, "A Study on Prediction of Excessive Outpatient Care Users Using Random Forest and Artificial Neural Network," Master Degree, Namseoul University, 2019 (in Korean). 
  13. Y. J. Oh, H. C. Jung, "Development of Galaxy Image Classification Based on Hand-crafted Features and Machine Learning," IEMEK Journal of Embedded Systems and Applications, Vol. 16, No. 1, pp. 17-27, 2021 (in Korean). 
  14. J. H. Han, D. K. Ko, H. J. Choe, "Predicting and Analyzing Factors Affecting Financial Stress of Household using Machine Learning: Application of XGBoost," Korean Society of Consumer Studies, Vol. 30, No. 2, pp. 21-43, 2019 (in Korean).  https://doi.org/10.35736/JCS.30.2.2
  15. J. H. Kim, "Hybrid AdaBoost for Multiuser Priority Analysis," Master Degree, Chung-Ang University, 2016 (in Korean). 
  16. J. H. Kim, "A Comparative Analysis of Intelligent Classification Algorithms for Early Diabetes Prediction," Master Degree, Chonnam National University, 2021 (in Korean).
  17. J. H. Kim, "Comparative Analysis of Corporate Distress Predictive Models Using XGBoost," Master Degree, Dongguk University, 2019 (in Korean). 
  18. T. Chen, 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.
  19. J. H. Friedman, "Greedy Function Approximation: a Gradient Boosting Machine," Annals of Statistics. pp. 1189-1232, 2001.
  20. C. J. Kim, "Price Prediction on Building Prices with XGBoost Algorithm : Focusing on Eco-friendly Certification System," Master Degree, Sungkyunkwan University. 2022 (in Korean). 
  21. Degradation State Recognition of Piston Pump Based on ICEEMDAN and XGBoost - Scientific Figure on ResearchGate. Available from: https://www.researchgate.net/figure/Flow-chart-of-XGBoost_fig3_345327934 [accessed 24 Mar, 2023]
  22. D. G. Kim, Y. S. Park, L. J. Park, T. Y. Chung, "Developing of New a Tensorflow Tutorial Model on Machine Learning : Focusing on the Kaggle Titanic Dataset," IEMEK Journal of Embedded Systems and Applications, Vol. 14, No. 4 pp. 207-218, 2019 (in Korean).