D. Álvarez

Utility of Approximate Entropy From Overnight Pulse Oximetry Data in the Diagnosis of the Obstructive Sleep Apnea Syndrome

Approximate entropy (ApEn) is a family of statistics introduced as a quantification of regularity in time series without any a priori knowledge about the system generating them. The aim of this preliminary study was to assess whether a time series analysis of arterial oxygen saturation (SaO2) signals from overnight pulse oximetry by means of ApEn could yield essential information on the diagnosis of obstructive sleep apnea (OSA) syndrome. We analyzed SaO2 signals from 187 subjects: 111 with a positive diagnosis of OSA and 76 with a negative diagnosis of OSA. We divided our data in a training set (44 patients with OSA Positive and 30 patients with OSA Negative) and a test set (67 patients with OSA Positive and 46 patients with OSA Negative). The training set was used for algorithm development and optimum threshold selection. Results showed that recurrence of apnea events in patients with OSA determined a significant increase in ApEn values. This method was assessed prospectively using the test dataset, where we obtained 82.09% sensitivity and 86.96% specificity. We conclude that ApEn analysis of SaO2 from pulse oximetric recording could be useful in the study of OSA

Approximate Entropy from Overnight Pulse Oximetry for the Obstructive Sleep Apnea Syndrome

The aim of this preliminary study was to asses whether a time series analysis from overnight pulse oximetry by means of approximate entropy (ApEn) could yield essential information on the diagnosis of obstructive sleep apnea (OSA) syndrome. We analyzed the oxygen saturation (SaO2) signals of 74 patients (44 with a positive diagnosis of OSA and 30 with a negative diagnosis of OSA) by means of ApEn, which quantified the regularity (or complexity) of time series. Results showed that recurrence of apnea events in patients with OSA determined a significant increase in ApEn values with a mean plusmnstandard deviation (SD) of 1.07 plusmn 0.30. A mean plusmn SD ApEn value of 0.47 plusmn 0.25 was estimated in patients without OSA. We obtained an area under the ROC curve of 0.94. The optimum threshold was selected at 0.81, where we achieved a 79.5% sensitivity and 90% specificity. Further analyses are necessary with new and larger data set to test the potential value of our methodology prospectively

Cross Approximate Entropy Analysis of Nocturnal Oximetry Signals in the Diagnosis of the Obstructive Sleep Apnea Syndrome

This study is focused on the analysis of blood oxygen saturation (SaO2) and heart rate (HR) from nocturnal oximetry using cross approximate entropy (Cross-ApEn). We assessed its usefulness in screening obstructive sleep apnea (OSA) syndrome. We applied Cross-ApEn(m,r,N) to quantify the asynchrony between paired SaO2 and HR records of 74 patients (44 with a positive OSA diagnosis and 30 with a negative OSA diagnosis). Cross-ApEn values were significantly lower in the OSA positive group compared with those obtained in the OSA negative group. A receiver operating characteristic (ROC) analysis showed that the best results, in terms of diagnostic accuracy, were achieved with m=2 and r=0.6. With these input parameters, the optimum decision threshold was found at 1.7, where we achieved 95.5% sensitivity, 73.3% specificity and 86.5% accuracy. Further analyses should be carried out with new and larger data sets to test the usefulness of our methodology prospectively

Automated analysis of unattended portable oximetry by means of Bayesian neural networks to assist in the diagnosis of sleep apnea

Sleep apnea-hypopnea syndrome (SAHS) is a chronic sleep-related breathing disorder, which is currently considered a major health problem. In-lab nocturnal polysomnography (NPSG) is the gold standard diagnostic technique though it is complex and relatively unavailable. On the other hand, the analysis of blood oxygen saturation (SpO2) from nocturnal pulse oximetry (NPO) is a simple, noninvasive, highly available and effective alternative. This study focused on the design and assessment of a neural network (NN) aimed at detecting SAHS using information from at-home unsupervised portable SpO2 recordings. A Bayesian multilayer perceptron NN (MLP-NN) was proposed, fed with complementary oximetric features properly selected. A dataset composed of 320 unattended SpO2 recordings was analyzed (60% for training and 40% for validation). The proposed Bayesian MLP-NN achieved 94.2% sensitivity, 69.6% specificity, and 89.8% accuracy in the test set. Our results suggest that automated analysis of at-home portable NPO recordings by means of Bayesian MLP-NN could be an effective and highly available technique in the context of SAHS diagnosis.

Exploring the spectral information of airflow recordings to help in pediatric Obstructive Sleep Apnea-Hypopnea Syndrome diagnosis.

This work aims at studying the usefulness of the spectral information contained in airflow (AF) recordings in the context of Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) in children. To achieve this goal, we defined two spectral bands of interest related to the occurrence of apneas and hypopneas. We characterized these bands by extracting six common spectral features from each one. Two out of the 12 features reached higher diagnostic ability than the 3% oxygen desaturation index (ODI3), a clinical parameter commonly used as screener for OSAHS. Additionally, the stepwise logistic regression (SLR) feature-selection algorithm showed that the information contained in the two bands was complementary, both between them and with ODI3. Finally, the logistic regression method involving spectral features from the two bands, as well as ODI3, achieved high diagnostic performance after a bootstrap validation procedure (84.6±9.6 sensitivity, 87.2±9.1 specificity, 85.8±5.2 accuracy, and 0.969±0.03 area under ROC curve). These results suggest that the spectral information from AF is helpful to detect OSAHS in children.