Oxygen saturation regularity analysis in the diagnosis of obstructive sleep apnea

Campo, Félix del; Hornero, Roberto; Zamarrón, Carlos; Abásolo, Daniel; Álvarez, Daniel

doi:10.1016/j.artmed.2005.10.005

Cited by 50 publications

(39 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In contrast, oximetry recordings corresponding to control subjects tend to have a near-constant value of saturation around 97% [26]. According to our previous research, nonlinear analysis of oximetry data can capture these differences, representing a useful means to quantitatively distinguish OSAS patients from control subjects [1, 7,16]. The proposed OSAS detection algorithm calculates the following nonlinear methods from the SaO 2 recordings during the feature extraction stage:…”

Section: Step 1 Feature Extractionmentioning

confidence: 93%

“…The extracted features measure relevant properties of oximetry data in order to discriminate signals from OSAS positive subjects. Previously, it was shown that spectral and nonlinear analyses of SaO 2 signals provide valuable information to detect OSAS [1, 7,16,39]. Statistically significant differences were found between OSAS positive and negative subjects by evaluating different spectral [39] and nonlinear features [1, 7,16].…”

Section: Step 1 Feature Extractionmentioning

confidence: 98%

“…Conventional oximetry indices such as the oxygen desaturation index over 2% (ODI2), 3% (ODI3), and 4% (ODI4), and the cumulative time spent below 90% of saturation (CT90) represent a first approach for automated analysis of SaO 2 signals [14,22,26,34]. A more advanced interpretation of oximetry data can be obtained by using signal processing techniques [1,7,16,39]. According to this approach, several diagnostic algorithms have been developed by using pattern classification methods [23][24][25].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automated detection of obstructive sleep apnoea syndrome from oxygen saturation recordings using linear discriminant analysis

Marcos

Hornero

Álvarez

et al. 2010

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

Nocturnal polysomnography (PSG) is the gold-standard to diagnose obstructive sleep apnoea syndrome (OSAS). However, it is complex, expensive, and time-consuming. We present an automatic OSAS detection algorithm based on classification of nocturnal oxygen saturation (SaO(2)) recordings. The algorithm makes use of spectral and nonlinear analysis for feature extraction, principal component analysis (PCA) for preprocessing and linear discriminant analysis (LDA) for classification. We conducted a study to characterize and prospectively validate our OSAS detection algorithm. The population under study was composed of subjects suspected of suffering from OSAS. A total of 214 SaO(2) signals were available. These signals were randomly divided into a training set (85 signals) and a test set (129 signals) to prospectively validate the proposed method. The OSAS detection algorithm achieved a diagnostic accuracy of 93.02% (97.00% sensitivity and 79.31% specificity) on the test set. It outperformed other alternative implementations that either use spectral and nonlinear features separately or are based on logistic regression (LR). The proposed method could be a useful tool to assist in early OSAS diagnosis, contributing to overcome the difficulties of conventional PSG.

show abstract

Section: Step 1 Feature Extractionmentioning

confidence: 93%

Section: Step 1 Feature Extractionmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automated detection of obstructive sleep apnoea syndrome from oxygen saturation recordings using linear discriminant analysis

Marcos

Hornero

Álvarez

et al. 2010

Med Biol Eng Comput

Self Cite

View full text Add to dashboard Cite

show abstract

“…The trademarks of pulse oximeters that were compared with PSG for the diagnosis of SAHS were mainly Ohmeda [8][9][10][11][12][13][14][15][16][17][18][19], Pulsox [17,[20][21][22][23][24], Nellcor [11,12,25,26], and Criticare [27][28][29][30]. Most of them are sparsely portables to be used at home.…”

Section: Introductionmentioning

confidence: 99%

Validation of the WristOx 3100™ oximeter for the diagnosis of sleep apnea/hypopnea syndrome

et al. 2008

View full text Add to dashboard Cite

show abstract

“…Among these complementary approaches, nonlinear methods have been marginally explored. Approximate entropy (ApEn) [22], sample entropy (SampEn) [23], central tendency measure [24], and Lempel-Ziv complexity [25] have demonstrated their usefulness to characterise desaturations linked to apnoeic events both in adults [26][27][28][29][30][31][32] and children [16,19]. Nevertheless, we hypothesise that different nonlinear metrics could gain insight into the dynamics of oximetry leading to additional and essential information.…”

Section: Introductionmentioning

confidence: 99%

Multiscale Entropy Analysis of Unattended Oximetric Recordings to Assist in the Screening of Paediatric Sleep Apnoea at Home

Crespo

Álvarez

Gutiérrez‐Tobal

et al. 2017

Entropy

Self Cite

View full text Add to dashboard Cite

Untreated paediatric obstructive sleep apnoea syndrome (OSAS) can severely affect the development and quality of life of children. In-hospital polysomnography (PSG) is the gold standard for a definitive diagnosis though it is relatively unavailable and particularly intrusive. Nocturnal portable oximetry has emerged as a reliable technique for OSAS screening. Nevertheless, additional evidences are demanded. Our study is aimed at assessing the usefulness of multiscale entropy (MSE) to characterise oximetric recordings. We hypothesise that MSE could provide relevant information of blood oxygen saturation (SpO 2 ) dynamics in the detection of childhood OSAS. In order to achieve this goal, a dataset composed of unattended SpO 2 recordings from 50 children showing clinical suspicion of OSAS was analysed. SpO 2 was parameterised by means of MSE and conventional oximetric indices. An optimum feature subset composed of five MSE-derived features and four conventional clinical indices were obtained using automated bidirectional stepwise feature selection. Logistic regression (LR) was used for classification. Our optimum LR model reached 83.5% accuracy (84.5% sensitivity and 83.0% specificity). Our results suggest that MSE provides relevant information from oximetry that is complementary to conventional approaches. Therefore, MSE may be useful to improve the diagnostic ability of unattended oximetry as a simplified screening test for childhood OSAS.

show abstract

Oxygen saturation regularity analysis in the diagnosis of obstructive sleep apnea

Cited by 50 publications

References 33 publications

Automated detection of obstructive sleep apnoea syndrome from oxygen saturation recordings using linear discriminant analysis

Automated detection of obstructive sleep apnoea syndrome from oxygen saturation recordings using linear discriminant analysis

Validation of the WristOx 3100™ oximeter for the diagnosis of sleep apnea/hypopnea syndrome

Multiscale Entropy Analysis of Unattended Oximetric Recordings to Assist in the Screening of Paediatric Sleep Apnoea at Home

Contact Info

Product

Resources

About