다양한 머신 러닝 알고리즘을 이용한 폐쇄수면무호흡 진단의 정확도
Diagnostic Accuracy of Different Machine Learning Algorithms for Obstructive Sleep Apnea
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Objectives: The objective of this study was to develop models for predicting obstructive sleep apnea (OSA) based on easily obtainable clinical information of patients using various machine learning techniques. Methods: We used a data set that included the records of 1,368 patients, in which 1,074 patients were male (78.5 %), and 294 patients were female (21.5 %). We randomly divided the data into a training set (1,000) and test set (368). Five machine learning methods, i.e., support vector machine model, lasso logit model, naïve bayes, discriminant analysis, and K-nearest neighbor (KNN), with a 10-cross fold technique were used with the proposed model to predict OSA. We evaluated the accuracy, sensitivity, specificity, and precision of each model for three thresholds [Apnea-Hypopnea Index (AHI)≥5, AHI≥15, and AHI≥30]. Results: Among the machine learning techniques, KNN showed the best results compared to the other techniques. The accuracy, sensitivity, specificity, and precision of OSA prediction were 87.0%, 91.0%, 74.4%, and 91.9%, respectively, based on AHI≥5. When the threshold of OSA was AHI≥15 or AHI≥30, KNN provided lower accuracy (79.6% each) and precision (79.0% and 68.7%), which were still higher than those of the other techniques. Conclusions: The model derived from the KNN technique exhibited the best performance based on its highest level of accuracy. We demonstrate that this model is a useful tool for predicting OSA.
Abstract
Objectives: The objective of this study was to develop models for predicting obstructive sleep apnea (OSA) based on easily obtainable clinical information of patients using various machine learning techniques. Methods: We used a data set that included the records of 1,368 patients, in which 1,074 patients were male (78.5 %), and 294 patients were female (21.5 %). We randomly divided the data into a training set (1,000) and test set (368). Five machine learning methods, i.e., support vector machine model, lasso logit model, naïve bayes, discriminant analysis, and K-nearest neighbor (KNN), with a 10-cross fold technique were used with the proposed model to predict OSA. We evaluated the accuracy, sensitivity, specificity, and precision of each model for three thresholds [Apnea-Hypopnea Index (AHI)≥5, AHI≥15, and AHI≥30]. Results: Among the machine learning techniques, KNN showed the best results compared to the other techniques. The accuracy, sensitivity, specificity, and precision of OSA prediction were 87.0%, 91.0%, 74.4%, and 91.9%, respectively, based on AHI≥5. When the threshold of OSA was AHI≥15 or AHI≥30, KNN provided lower accuracy (79.6% each) and precision (79.0% and 68.7%), which were still higher than those of the other techniques. Conclusions: The model derived from the KNN technique exhibited the best performance based on its highest level of accuracy. We demonstrate that this model is a useful tool for predicting OSA.
참고문헌 (44)
- Peppard PE, "Increased prevalence of sleep-disordered breathing in adults", Am J Epi-demiol, 177, pp.1006~1014 (2013)[DOI]
- Young T, "Burden of sleep apnea: rationale, design, and major findings of the Wisconsin Sleep Cohort study", WMJ, 108, pp.246~249 (2009)
- Malhotra A, "Obstructive sleep apnoea", Lancet, 360, pp.237~245 (2002)[DOI]
- Sunwoo JS, "Prevalence, sleep characteristics, and comorbidities in a population at high risk for obstructive sleep apnea : a nationwide questionnaire study in South Korea", PLoS One, 13, pp.e0193549~ (2018)[DOI]
- Nieto FJ, "Association of sleep-disordered breathing, sleep apnea, and hypertension in a large community-based study", JAMA, 283, pp.1829~1836 (2000)[DOI]
- Shahar E, "Sleep-disordered breathing and cardiovascular disease: cross-sectional results of the Sleep Heart Health Study", Am J Respir Crit Care Med, 163, pp.19~25 (2001)[DOI]
- Engleman HM, "Sleep · 4 : sleepiness, cognitive function, and quality of life in obstructive sleep apnoea", hypopnoea syndrome, 2004, pp.59, 618~622
- Costa LE, "Potential underdiagnosis of obstructive sleep apnoea in the cardiology outpatient setting", Heart, 101, pp.1288~1292 (2015)[DOI]
- Kapur V, "Underdiagnosis of sleep apnea syndrome in U.S. communities", Sleep Breath, 6, pp.49~54 (2002)[DOI]
- Mirrakhimov AE, "Prevalence of obstructive sleep apnea in Asian adults : a systematic review of the literature", BMC Pulm Med, 13, pp.10~ (2013)[DOI]
- Li KK, "Obstructive sleep apnea syndrome: a comparison between Far-East Asian and white men", Laryngoscope, 110(10 Pt 1), pp.1689~1693 (2000)[DOI]
- Hastie T, "The elements of statistical learning:data mining, inference, and prediction" (2009), Springer
- Rajkomar A, "Machine learning in medicine", N Engl J Med, 380, pp.1347~1358 (2019)[DOI]
- Samant P, "Machine learning techniques for medical diagnosis of diabetes using iris images", Comput Methods Programs Biomed, 157, pp.121~128 (2018)[DOI]
- Gunčar G, "An application of machine learning to haematological diagnosis", Sci Rep, 8, pp.411~ (2018)[DOI]
- 양요찬, "서울지역 대학생들의 요천추 만곡과 목-허리둘레의 관계에 대한 연구", 한방재활의학과학회지, 23(4), pp.169~176 (2013), 한방재활의학과학회
- Cameron N, "Human growth: its assessment, evaluation and variation", pp.2018
- Sateia MJ, "International classification of sleep disorders-third edition", Chest, 146, pp.1387~1394 (2014)[DOI]
- American Academy of Sleep Medicine Task Force, "Sleep-related breathing disorders in adults: recommendations for syndrome definition and measurement techniques in clinical research. The Report of an American Academy of Sleep Medicine Task Force", Sleep, 22, pp.667~689 (1999)[DOI]
- James G, "An introduction to statistical learning with applications in R" (2013), Springer
- Kapur V, "The medical cost of undiagnosed sleep apnea", Sleep, 22, pp.749~755 (1999)[DOI]
- Farney RJ, "The STOPBang equivalent model and prediction of severity of obstructive sleep apnea : relation to polysomnographic measurements of the apnea", hypopnea index, 2011, pp.7, 459~465
- Rowley JA, "The use of clinical prediction formulas in the evaluation of obstructive sleep apnea", Sleep, 23, pp.929~938 (2000)[DOI]
- Waxman JA, "Automated prediction of apnea and hypopnea, using a LAMSTAR artificial neural network", Am J Respir Crit Care Med, 181, pp.727~733 (2010)[DOI]
- Deflandre E, "Development and validation of a morphologic obstructive sleep apnea prediction score : the DES-OSA score", Anesth Analg, 122, pp.363~372 (2016)[DOI]
- Aaronson JA, "Can a prediction model combining self-reported symptoms, sociodemographic and clinical features serve as a reliable first screening method for sleep apnea syndrome in patients with stroke?", Arch Phys Med Rehabil, 95, pp.747~752 (2014)[DOI]
- Khandoker AH, "Support vector machines for automated recognition of obstructive sleep apnea syndrome from ECG recordings", IEEE Trans Inf Technol Biomed, 13, pp.37~48 (2009)[DOI]
- Uçar MK, "Automatic sleep staging in obstructive sleep apnea patients using photoplethysmography, heart rate variability signal and machine learning techniques", Neural Comput & Applic, 29, pp.1~16 (2018)[DOI]
- Islam SMS, "Deep learning of facial depth maps for obstructive sleep apnea prediction", International Conference on Machine Learning and Data Engineering (iCMLDE), pp.154~157 (2018), IEEE
- Mencar C, "Application of machine learning to predict obstructive sleep apnea syndrome severity", Health Informatics J, 26, pp.298~317 (2020)[DOI]
- Pépin JL, "Assessment of mandibular movement monitoring with machine learning analysis for the diagnosis of obstructive sleep apnea", JAMA Netw Open, 3, pp.e1919657~ (2020)[DOI]
- Chekroud AM, "Cross-trial prediction of treatment outcome in depression : a machine learning approach", Lancet Psychiatry, 3, pp.243~250 (2016)[DOI]
- Oğretmenoğlu O, "Body fat composition : a predictive factor for obstructive sleep apnea", Laryngoscope, 115, pp.1493~1498 (2005)[DOI]
- Wysocki J, "Anthropometric and physiologic assessment in sleep apnoea patients regarding body fat distribution", Folia Morphol, 75, pp.393~399 (2016)[DOI]
- Katz SL, "Does neck-to-waist ratio predict obstructive sleep apnea in children", J Clin Sleep Med, 10, pp.1303~1308 (2014)[DOI]
- Yang KI, "Sleep disorders: case-based learning", pp.154~156 (2020), PanMun Education
- Liu WT, "Prediction of the severity of obstructive sleep apnea by anthropometric features via support vector machine", PLoS One, 12, pp.e0176991~ (2017)[DOI]
- Wu MF, "A new method for self-estimation of the severity of obstructive sleep apnea using easily available measurements and neural fuzzy evaluation system", IEEE J Biomed Health Inform, 21, pp.1524~1532 (2017)[DOI]
- Keshavarz Z, "Obstructive sleep apnea : a prediction model using supervised machine learning method", Stud Health Technol Inform, 272, pp.387~390 (2020)[DOI]
- 양현주, "폐쇄성수면무호흡 진단을 위한 Berlin, STOP, STOP-Bang 설문의 유용성에 관한 고찰", Journal of sleep medicine, 16(1), pp.11~20 (2019), 대한수면연구학회[DOI]
- Nuckton TJ, "Physical examination : Mallampati score as an independent predictor of obstructive sleep apnea", Sleep, 29, pp.903~908 (2006)[DOI]
- Friedman M, "Updated Friedman Staging System for obstructive sleep apnea", Adv Otorhinolaryngol, 80, pp.41~48 (2017)[DOI]
- Friedman M, "Diagnostic value of the Friedman tongue position and Mallampati classification for obstructive sleep apnea : a meta-analysis", Otolaryngol Head Neck Surg, 148, pp.540~547 (2013)[DOI]
- Yu JL, "Utility of the modified Mallampati grade and Friedman tongue position in the assessment of obstructive sleep apnea", J Clin Sleep Med, 16, pp.303~308 (2020)[DOI]