RT info:eu-repo/semantics/article
T1 Analysis and Classification of Oximetry Recordings to Predict Obstructive Sleep Apnea Severity in Children
A1 Gutiérrez Tobal, Gonzalo César
A1 Kheirandish Gozal, Leila
A1 Álvarez González, Daniel
A1 Crespo Senado, Andrea
A1 Philby, Mona F.
A1 Meelad, Mohammadi
A1 Campo Matias, Félix del
A1 Gozal, David
A1 Hornero Sánchez, Roberto
K1 Sleep Apnea  severity in Children
AB Current study is focused around the potential useof oximetry to determine the obstructive sleep apnea-hypopneasyndrome (OSAHS) severity in children. Single-channel SpO2recordings from 176 children were divided into three severitygroups according to the apnea-hypopnea index (AHI): AHI<1events per hour (e/h), 1≤AHI<5 e/h, and AHI ≥5 e/h. Spectralanalysis was conducted to define and characterize a frequencyband of interest in SpO2. Then we combined the spectral datawith the 3% oxygen desaturation index (ODI3) by means of amulti-layer perceptron (MLP) neural network, in order toclassify children into one of the three OSAHS severity groups.Following our MLP multiclass approach, a diagnostic protocolwith capability to reduce the need of polysomnography tests by46% could be derived. Moreover, our proposal can be alsoevaluated, in a binary classification task for two common AHIdiagnostic cutoffs (AHI = 1 e/h and AHI= 5 e/h). Highdiagnostic ability was reached in both cases (84.7% and 85.8%accuracy, respectively) outperforming the clinical variableODI3 as well as other measures reported in recent studies.These results suggest that the information contained in SpO2could be helpful in pediatric OSAHS severity detection.
PB IEEE Conference Publications
SN 1557-170X
YR 2015
FD 2015
LK http://uvadoc.uva.es/handle/10324/21719
UL http://uvadoc.uva.es/handle/10324/21719
LA eng
NO Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2015, p. 4540-3
NO Producción Científica
DS UVaDOC
RD 25-nov-2024