scholarly journals Obstructive sleep apnea syndrome detection based on ballistocardiogram via machine learning approach

2019 ◽  
Vol 16 (5) ◽  
pp. 5672-5686
Author(s):  
Weidong Gao ◽  
◽  
Yibin Xu ◽  
Shengshu Li ◽  
Yujun Fu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Obstructive Sleep Apnea Syndrome ◽  
Sleep Apnea Syndrome ◽  
Learning Approach ◽  
Obstructive Sleep ◽  
Machine Learning Approach ◽  
Apnea Syndrome

scholarly journals Application of machine learning to predict obstructive sleep apnea syndrome severity

2019 ◽  
Vol 26 (1) ◽  
pp. 298-317 ◽  
Author(s):  
Corrado Mencar ◽  
Crescenzio Gallo ◽  
Marco Mantero ◽  
Paolo Tarsia ◽  
Giovanna E Carpagnano ◽  
...  
Keyword(s):  
Machine Learning ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Obstructive Sleep Apnea Syndrome ◽  
Sleep Apnea Syndrome ◽  
Support Vector ◽  
Apnea Hypopnea Index ◽  
Machine Learning Methods ◽  
Obstructive Sleep ◽  
Apnea Syndrome

Introduction: Obstructive sleep apnea syndrome has become an important public health concern. Polysomnography is traditionally considered an established and effective diagnostic tool providing information on the severity of obstructive sleep apnea syndrome and the degree of sleep fragmentation. However, the numerous steps in the polysomnography test to diagnose obstructive sleep apnea syndrome are costly and time consuming. This study aimed to test the efficacy and clinical applicability of different machine learning methods based on demographic information and questionnaire data to predict obstructive sleep apnea syndrome severity. Materials and methods: We collected data about demographic characteristics, spirometry values, gas exchange (PaO2, PaCO2) and symptoms (Epworth Sleepiness Scale, snoring, etc.) of 313 patients with previous diagnosis of obstructive sleep apnea syndrome. After principal component analysis, we selected 19 variables which were used for further preprocessing and to eventually train seven types of classification models and five types of regression models to evaluate the prediction ability of obstructive sleep apnea syndrome severity, represented either by class or by apnea–hypopnea index. All models are trained with an increasing number of features and the results are validated through stratified 10-fold cross validation. Results: Comparative results show the superiority of support vector machine and random forest models for classification, while support vector machine and linear regression are better suited to predict apnea–hypopnea index. Also, a limited number of features are enough to achieve the maximum predictive accuracy. The best average classification accuracy on test sets is 44.7 percent, with the same average sensitivity (recall). In only 5.7 percent of cases, a severe obstructive sleep apnea syndrome (class 4) is misclassified as mild (class 2). Regression results show a minimum achieved root mean squared error of 22.17. Conclusion: The problem of predicting apnea–hypopnea index or severity classes for obstructive sleep apnea syndrome is very difficult when using only data collected prior to polysomnography test. The results achieved with the available data suggest the use of machine learning methods as tools for providing patients with a priority level for polysomnography test, but they still cannot be used for automated diagnosis.

Postoperative monitoring of children with obstructive sleep apnea syndrome

2014 ◽  
Vol 155 (18) ◽  
pp. 703-707 ◽  
Author(s):  
Pálma Benedek ◽  
Gabriella Kiss ◽  
Eszter Csábi ◽  
Gábor Katona
Keyword(s):  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Obstructive Sleep Apnea Syndrome ◽  
Preoperative Evaluation ◽  
Sleep Apnea Syndrome ◽  
Study Patient ◽  
Severe Obstructive Sleep Apnea ◽  
Obstructive Sleep ◽  
Significant Difference ◽  
Apnea Syndrome

Introduction: Treatment of pediatric obstructive sleep apnea syndrome is surgical. The incidence of postoperative respiratory complications in this population is 5–25%. Aim: The aim of the authors was to present the preoperative evaluation and monitoring procedure elaborated in Heim Pál Children Hospital, Budapest. Method: 142 patients were involved in the study. Patient history was obtained and physical examination was performed in all cases. Thereafter, polysomnography was carried out, the severity of the obstructive sleep apnea syndrome was determined, and the patients underwent tonsilloadenotomy. Results: 45 patients with mild, 50 patients with moderate and 47 patients with severe obstructive sleep apnea syndrome were diagnosed. There was no complication in patients with mild disease, while complications were observed in 6 patients in the moderate group and 24 patients in the severe group (desaturation, apnea, stridor, stop breathing) (p<0.000). In patients with severe obstructive sleep apnea syndrome, no significant difference was noted in preoperative apnoea-hypapnea index (p = 0.23) and in nadir oxygen saturation values (p = 0.73) between patients with and without complication. Conclusions: Patients with severe obstructive sleep apnea syndrome should be treated in hospital where pediatric intensive care unit is available. Orv. Hetil., 2014, 155(18), 703–707.

Sign in / Sign up

Export Citation Format

Share Document