These results indicate that the use of only ECG sensors can achieve good accuracies in the detection of sleep apnea. Moreover, the contamination level of each ECG segment can be used to automatically detect artefacts, and to highlight segments that require further visual inspection.

ArticlesBackground: Currently, reliable reference values of regional cerebral oxygen saturation (rScO 2 ) for different gestational age (GA) groups are lacking, which hampers the implementation of near-infrared spectroscopy (NIRS) alongside monitoring arterial oxygen saturation (SaO 2 ) and blood pressure in neonatal intensive care. The aim of this study was to provide reference values for rScO 2 and cerebral fractional tissue oxygen extraction (cFTOE; (SaO 2 − rScO 2 )/SaO 2 ) for small adult and neonatal NIRS sensors. Methods: In this study, 999 infants born preterm (GA <32 wk) were monitored with NIRS during the first 72 h of life. Mixed modeling was used to generate reference curves grouped per 2 wk of GA. In addition, the influence of a hemodynamically significant patent ductus arteriosus, gender, and birth weight were explored. results: Average rScO 2 was ~65% at admission, increased with GA (1% per week) and followed a parabolic curve in relation to postnatal age with a peak at ~36 h. The cFTOE showed similar but inverse effects. On average, the neonatal sensor measured 10% higher than the adult sensor. conclusion: rScO 2 and cFTOE reference curves are provided for the first 72 h of life in preterm infants, which might support the broader implementation of NIRS in neonatal intensive care. d espite advances in neonatal intensive care that have led to a decline in morbidity, preterm birth is still associated with neurological sequelae (1). Brain injury in preterm infants is often caused by disturbances in cerebral blood flow (CBF) and oxygenation (2-4). Evidence is accumulating that monitoring blood pressure alone is not enough to ensure adequate (cerebral) perfusion and oxygenation (5,6).Near-infrared spectroscopy (NIRS) is a technique that can be used to monitor regional cerebral oxygen saturation (rScO 2 ), being both a measure of cerebral oxygenation as well as a surrogate of CBF. NIRS monitoring can be applied for prolonged periods of time, even in the most vulnerable infants (7). It uses multiple wavelengths of NIR light and relies on the distinct absorption spectra of oxygenated (O 2 Hb) and deoxygenated (HHb) hemoglobin to calculate relative concentrations of O 2 Hb and HHb, which are then used to calculate the rScO 2 (O 2 Hb/(O 2 Hb + HHb)). Where pulse-oximetry only measures the oxygen saturation in arterial blood (SaO 2 ), NIRS makes no distinction between different (cerebral) blood volume compartments; therefore, the rScO 2 represents the oxygen saturation in a mixed arterial-capillary-venous compartment in an approximate 20:5:75 distribution (8).NIRS is increasingly being used as a trend monitor of cerebral oxygen supply in neonates admitted to the neonatal intensive care unit (NICU). Readily interpretable reference values could provide another way of using NIRS in neonates by identifying neonates at risk. In other words, to identify neonates whose rScO 2 resides at the outskirts (high or low) of what is considered "normal. " Furthermore, reliable reference values could benefit NIRS research by...

No abstract

Identifying a core set of features is one of the most important steps in the development of an automated seizure detector. In most of the published studies describing features and seizure classifiers, the features were hand-engineered, which may not be optimal. The main goal of the present paper is using deep convolutional neural networks (CNNs) and random forest to automatically optimize feature selection and classification. The input of the proposed classifier is raw multi-channel EEG and the output is the class label: seizure/nonseizure. By training this network, the required features are optimized, while fitting a nonlinear classifier on the features. After training the network with EEG recordings of 26 neonates, five end layers performing the classification were replaced with a random forest classifier in order to improve the performance. This resulted in a false alarm rate of 0.9 per hour and seizure detection rate of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures. The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.