DOI QR코드

DOI QR Code

Predictive Model of Optimal Continuous Positive Airway Pressure for Obstructive Sleep Apnea Patients with Obesity by Using Machine Learning

비만 폐쇄수면무호흡 환자에서 기계학습을 통한 적정양압 예측모형

  • Kim, Seung Soo (Sleep Disorders Center, Soonchunhyang University Cheonan Hospital, Soonchunhyang University College of Medicine) ;
  • Yang, Kwang Ik (Sleep Disorders Center, Soonchunhyang University Cheonan Hospital, Soonchunhyang University College of Medicine)
  • 김승수 (순천향대학교 의과대학 천안병원 수면장애센터) ;
  • 양광익 (순천향대학교 의과대학 천안병원 수면장애센터)
  • Received : 2018.11.06
  • Accepted : 2018.11.29
  • Published : 2018.12.31

Abstract

Objectives: The aim of this study was to develop a predicting model for the optimal continuous positive airway pressure (CPAP) for obstructive sleep apnea (OSA) patient with obesity by using a machine learning. Methods: We retrospectively investigated the medical records of 162 OSA patients who had obesity [body mass index (BMI) ≥ 25] and undertaken successful CPAP titration study. We divided the data to a training set (90%) and a test set (10%), randomly. We made a random forest model and a least absolute shrinkage and selection operator (lasso) regression model to predict the optimal pressure by using the training set, and then applied our models and previous reported equations to the test set. To compare the fitness of each models, we used a correlation coefficient (CC) and a mean absolute error (MAE). Results: The random forest model showed the best performance {CC 0.78 [95% confidence interval (CI) 0.43-0.93], MAE 1.20}. The lasso regression model also showed the improved result [CC 0.78 (95% CI 0.42-0.93), MAE 1.26] compared to the Hoffstein equation [CC 0.68 (95% CI 0.23-0.89), MAE 1.34] and the Choi's equation [CC 0.72 (95% CI 0.30-0.90), MAE 1.40]. Conclusions: Our random forest model and lasso model ($26.213+0.084{\times}BMI+0.004{\times}$apnea-hypopnea index+$0.004{\times}oxygen$ desaturation index-$0.215{\times}mean$ oxygen saturation) showed the improved performance compared to the previous reported equations. The further study for other subgroup or phenotype of OSA is required.

Keywords

References

  1. Sullivan CE, Issa FG, Berthon-Jones M, Eves L. Reversal of obstructive sleep apnoea by continuous positive airway pressure applied through the nares. Lancet 1981;1:862-865.
  2. Camacho M, Riaz M, Tahoori A, Certal V, Kushida CA. Mathematical equations to predict positive airway pressures for obstructive sleep apnea: a systematic review. Sleep Disord 2015;2015:293868.
  3. Sunwoo JS, Yang KI. Overview of treatment for obstructive sleep apnea in adults. J Sleep Med 2017;14:1-9. https://doi.org/10.13078/jsm.17001
  4. Kushida CA, Chediak A, Berry RB, et al.; American Academy of Sleep Medicine. Clinical guidelines for the manual titration of positive airway pressure in patients with obstructive sleep apnea. J Clin Sleep Med 2008;4:157-171.
  5. Morgenthaler TI, Aurora RN, Brown T, et al.; Standards of Practice Committee of the AASM; American Academy of Sleep Medicine. Practice parameters for the use of autotitrating continuous positive airway pressure devices for titrating pressures and treating adult patients with obstructive sleep apnea syndrome: an update for 2007. An American Academy of Sleep Medicine report. Sleep 2008;31:141-147. https://doi.org/10.1093/sleep/31.1.141
  6. Rosen CL, Auckley D, Benca R, et al. A multisite randomized trial of portable sleep studies and positive airway pressure autotitration versus laboratory-based polysomnography for the diagnosis and treatment of obstructive sleep apnea: the HomePAP study. Sleep 2012;35:757-767. https://doi.org/10.5665/sleep.1870
  7. Ayas NT, Patel SR, Malhotra A, et al. Auto-titrating versus standard continuous positive airway pressure for the treatment of obstructive sleep apnea: results of a meta-analysis. Sleep 2004;27:249-253. https://doi.org/10.1093/sleep/27.2.249
  8. Ip S, D'Ambrosio C, Patel K, et al. Auto-titrating versus fixed continuous positive airway pressure for the treatment of obstructive sleep apnea: a systematic review with meta-analyses. Syst Rev 2012;1:20. https://doi.org/10.1186/2046-4053-1-20
  9. Marrone O, Cibella F, Pepin JL, et al.; ESADA Network. Fixed but not autoadjusting positive airway pressure attenuates the time-dependent decline in glomerular filtration rate in patients with OSA. Chest 2018;154:326-334. https://doi.org/10.1016/j.chest.2018.04.020
  10. Patruno V, Aiolfi S, Costantino G, et al. Fixed and autoadjusting continuous positive airway pressure treatments are not similar in reducing cardiovascular risk factors in patients with obstructive sleep apnea. Chest 2007;131:1393-1399. https://doi.org/10.1378/chest.06-2192
  11. Pepin JL, Tamisier R, Baguet JP, et al. Fixed-pressure CPAP versus autoadjusting CPAP: comparison of efficacy on blood pressure in obstructive sleep apnoea, a randomised clinical trial. Thorax 2016;71:726-733. https://doi.org/10.1136/thoraxjnl-2015-207700
  12. Miljeteig H, Hoffstein V. Determinants of continuous positive airway pressure level for treatment of obstructive sleep apnea. Am Rev Respir Dis 1993;147(6 Pt 1):1526-1530. https://doi.org/10.1164/ajrccm/147.6_Pt_1.1526
  13. Rowley JA, Tarbichi AG, Badr MS. The use of a predicted CPAP equation improves CPAP titration success. Sleep Breath 2005;9:26-32. https://doi.org/10.1007/s11325-005-0004-3
  14. El Solh AA, Aldik Z, Alnabhan M, Grant B. Predicting effective continuous positive airway pressure in sleep apnea using an artificial neural network. Sleep Med 2007;8:471-477. https://doi.org/10.1016/j.sleep.2006.09.005
  15. Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw 2010;33:1-22.
  16. Breiman L. Random forests. Machine Learning 2001;45:5-32. https://doi.org/10.1023/A:1010933404324
  17. Ferreira-Santos D, Pereira Rodrigues P. Phenotyping obstructive sleep apnea patients: a first approach to cluster visualization. Stud Health Technol Inform 2018;255:75-79.
  18. Johns MW. A new method for measuring daytime sleepiness: the Epworth sleepiness scale. Sleep 1991;14:540-545. https://doi.org/10.1093/sleep/14.6.540
  19. Berry RB, Brooks R, Gamaldo CE, et al. The AASM manual for the scoring of sleep and associated events: rules, terminology and technical specifications, Version 2.0. Darien: American Academy of Sleep Medicine, 2012.
  20. Lee GH, Kim MJ, Lee EM, Kim CS, Lee SA. Prediction of optimal CPAP pressure and validation of an equation for Asian patients with obstructive sleep apnea. Respir Care 2013;58:810-815.
  21. Choi JH, Kim EJ, Kim KW, et al. Optimal continuous positive airway pressure level in korean patients with obstructive sleep apnea syndrome. Clin Exp Otorhinolaryngol 2010;3:207-211. https://doi.org/10.3342/ceo.2010.3.4.207
  22. Lantz B(Trans. Yun SJ). Machine learning with R: expert techniques for predictive modeling to solve all your data analysis problems. 2nd ed. Seoul: Acorn publishing Co., 2014.
  23. Huh MH. Data science: introduction and topics. Paju: Freedom Academy INC, 2018:123-34.
  24. de Vlaming R, Groenen PJ. The current and future use of ridge regression for prediction in quantitative genetics. Biomed Res Int 2015;2015:143712.
  25. Hsieh CH, Lu RH, Lee NH, Chiu WT, Hsu MH, Li YC. Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks. Surgery 2011;149:87-93. https://doi.org/10.1016/j.surg.2010.03.023
  26. Diaz-Uriarte R, Alvarez de Andres S. Gene selection and classification of microarray data using random forest. BMC Bioinformatics 2006;7:3. https://doi.org/10.1186/1471-2105-7-3