비만 폐쇄수면무호흡 환자에서 기계학습을 통한 적정양압 예측모형
Predictive Model of Optimal Continuous Positive Airway Pressure for Obstructive Sleep Apnea Patients with Obesity by Using Machine Learning
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
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×BMI+0.004×apnea-hypopnea index+0.004×oxygen desaturation index–0.215×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.
Abstract
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×BMI+0.004×apnea-hypopnea index+0.004×oxygen desaturation index–0.215×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.
참고문헌 (26)
- Sullivan CE, "Reversal of obstructive sleep apnoea by continuous positive airway pressure applied through the nares", Lancet, 1, pp.862~865 (1981)
- Camacho M, "Mathematical equations to predict positive airway pressures for obstructive sleep apnea: a systematic review", Sleep Disord, 2015, pp.293868~ (2015)
- 선우준상, "성인 폐쇄수면무호흡의 치료 개괄", Journal of sleep medicine, 14(1), pp.1~9 (2017), 대한수면연구학회[DOI]
- Kushida CA, "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, 4, pp.157~171 (2008)
- Morgenthaler TI, "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, 31, pp.141~147 (2008)
- Rosen CL, "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, 35, pp.757~767 (2012)
- Ayas NT, "Auto-titrating versus standard continuous positive airway pressure for the treatment of obstructive sleep apnea: results of a meta-analysis", Sleep, 27, pp.249~253 (2004)
- Ip S, "Auto-titrating versus fixed continuous positive airway pressure for the treatment of obstructive sleep apnea: a systematic review with meta-analyses", Syst Rev, 1, pp.20~ (2012)
- Marrone O, "Fixed but not autoadjusting positive airway pressure attenuates the time-dependent decline in glomerular filtration rate in patients with OSA", Chest, 154, pp.326~334 (2018)
- Patruno V, "Fixed and autoadjusting continuous positive airway pressure treatments are not similar in reducing cardiovascular risk factors in patients with obstructive sleep apnea", Chest, 131, pp.1393~1399 (2007)
- Pépin JL, "Fixed-pressure CPAP versus autoadjusting CPAP: comparison of efficacy on blood pressure in obstructive sleep apnoea, a randomised clinical trial", Thorax, 71, pp.726~733 (2016)
- Miljeteig H, "Determinants of continuous positive airway pressure level for treatment of obstructive sleep apnea", Am Rev Respir Dis, 147(6 Pt 1), pp.1526~1530 (1993)
- Rowley JA, "The use of a predicted CPAP equation improves CPAP titration success", Sleep Breath, 9, pp.26~32 (2005)
- El Solh AA, "Predicting effective continuous positive airway pressure in sleep apnea using an artificial neural network", Sleep Med, 8, pp.471~477 (2007)
- Friedman J, "Regularization paths for generalized linear models via coordinate descent", J Stat Softw, 33, pp.1~22 (2010)
- Breiman L, "Random forests", Machine Learning, 45, pp.5~32 (2001)
- Ferreira-Santos D, "Phenotyping obstructive sleep apnea patients: a first approach to cluster visualization", Stud Health Technol Inform, 255, pp.75~79 (2018)
- Johns MW, "A new method for measuring daytime sleepiness: the Epworth sleepiness scale", Sleep, 14, pp.540~545 (1991)
- Berry RB, "The AASM manual for the scoring of sleep and associated events: rules, terminology and technical specifications, Version 2.0" (2012), American Academy of Sleep Medicine
- Lee GH, "Prediction of optimal CPAP pressure and validation of an equation for Asian patients with obstructive sleep apnea", Respir Care, 58, pp.810~815 (2013)
- 최지호, "Optimal Continuous Positive Airway Pressure Level in Korean Patients with Obstructive Sleep Apnea Syndrome", Clinical and Experimental Otorhinolaryngology, 3(4), pp.207~211 (2010), 대한이비인후과학회
- Lantz B, "Machine learning with R: expert techniques for predictive modeling to solve all your data analysis problems" (2014), Acorn publishing Co.
- Huh MH, "Data science: introduction and topics", pp.123~134 (2018), Freedom Academy INC
- de Vlaming R, "The current and future use of ridge regression for prediction in quantitative genetics", Biomed Res Int, 2015, pp.143712~ (2015)
- Hsieh CH, "Novel solutions for an old disease: diagnosis of acute appendicitis with random forest, support vector machines, and artificial neural networks", Surgery, 149, pp.87~93 (2011)
- Díaz-Uriarte R, "Gene selection and classification of microarray data using random forest", BMC Bioinformatics, 7, pp.3~ (2006)