RT info:eu-repo/semantics/article T1 Statistical and Nonlinear Analysis of Oximetry from Respiratory Polygraphy to Assist in the Diagnosis of Sleep Apnea in Children A1 Álvarez González, Daniel A1 Gutiérrez Tobal, Gonzalo César A1 Alonso Álvarez, María Luz A1 Terán Santos, Joaquín A1 Campo Matias, Félix del A1 Hornero Sánchez, Roberto K1 Sleep Apnea in Children AB Obstructive Sleep Apnea-Hypopnea Syndrome(OSAHS) is a sleep related breathing disorder that hasimportant consequences in the health and development ofinfants and young children. To enhance the early detection ofOSAHS, we propose a methodology based on automatedanalysis of nocturnal blood oxygen saturation (SpO2) fromrespiratory polygraphy (RP) at home. A database composed of50 SpO2 recordings was analyzed. Three signal processingstages were carried out: (i) feature extraction, where statisticalfeatures and nonlinear measures were computed and combinedwith conventional oximetric indexes, (ii) feature selection usinggenetic algorithms (GAs), and (iii) feature classification throughlogistic regression (LR). Leave-one-out cross-validation (loo-cv)was applied to assess diagnostic performance. The proposedmethod reached 80.8% sensitivity, 79.2% specificity, 80.0%accuracy and 0.93 area under the ROC curve (AROC), whichimproved the performance of single conventional indexes. Ourresults suggest that automated analysis of SpO2 recordings fromat-home RP provides essential and complementary informationto assist in OSAHS diagnosis in children. PB IEEE Conference Publications SN 1557-170X YR 2014 FD 2014 LK http://uvadoc.uva.es/handle/10324/21714 UL http://uvadoc.uva.es/handle/10324/21714 LA eng NO Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2014, v. 2014, p. 1860-3 NO Producción Científica DS UVaDOC RD 29-mar-2024