Accurate neonatal heart rate monitoring using a new wireless, cap mounted device.

AIM: A device for newborn heart rate (HR) monitoring at birth that is compatible with delayed cord clamping and minimises hypothermia risk could have advantages over current approaches. We evaluated a wireless, cap mounted device (fhPPG) for monitoring neonatal HR. METHODS: A total of 52 infants on the neonatal intensive care unit (NICU) and immediately following birth by elective caesarean section (ECS) were recruited. HR was monitored by electrocardiogram (ECG), pulse oximetry (PO) and the fhPPG device. Success rate, accuracy and time to output HR were compared with ECG as the gold standard. Standardised simulated data assessed the fhPPG algorithm accuracy. RESULTS: Compared to ECG HR, the median bias (and 95% limits of agreement) for the NICU was fhPPG -0.6 (-5.6, 4.9) vs PO -0.3 (-6.3, 6.2) bpm, and ECS phase fhPPG -0.5 (-8.7, 7.7) vs PO -0.1 (-7.6, 7.1) bpm. In both settings, fhPPG and PO correlated with paired ECG HRs (both R2  = 0.89). The fhPPG HR algorithm during simulations demonstrated a near-linear correlation (n = 1266, R2  = 0.99). CONCLUSION: Monitoring infants in the NICU and following ECS using a wireless, cap mounted device provides accurate HR measurements. This alternative approach could confer advantages compared with current methods of HR assessment and warrants further evaluation at birth.

Postnatal gestational age estimation of newborns using Small Sample Deep Learning.

A baby's gestational age determines whether or not they are premature, which helps clinicians decide on suitable post-natal treatment. The most accurate dating methods use Ultrasound Scan (USS) machines, but these are expensive, require trained personnel and cannot always be deployed to remote areas. In the absence of USS, the Ballard Score, a postnatal clinical examination, can be used. However, this method is highly subjective and results vary widely depending on the experience of the examiner. Our main contribution is a novel system for automatic postnatal gestational age estimation using small sets of images of a newborn's face, foot and ear. Our two-stage architecture makes the most out of Convolutional Neural Networks trained on small sets of images to predict broad classes of gestational age, and then fuses the outputs of these discrete classes with a baby's weight to make fine-grained predictions of gestational age using Support Vector Regression. On a purpose-collected dataset of 130 babies, experiments show that our approach surpasses current automatic state-of-the-art postnatal methods and attains an expected error of 6 days. It is three times more accurate than the Ballard method. Making use of images improves predictions by 33% compared to using weight only. This indicates that even with a very small set of data, our method is a viable candidate for postnatal gestational age estimation in areas were USS is not available.

Marked variation in newborn resuscitation practice: a national survey in the UK.

BACKGROUND: Although international newborn resuscitation guidance has been in force for some time, there are no UK data on current newborn resuscitation practices. OBJECTIVE: Establish delivery room (DR) resuscitation practices in the UK, and identify any differences between neonatal intensive care units (NICU), and other local neonatal services. METHODS: We conducted a structured two-stage survey of DR management, among UK neonatal units during 2009-2010 (n=192). Differences between NICU services (tertiary level) and other local neonatal services (non-tertiary) were analysed using Fisher's exact and Student's t-tests. RESULTS: There was an 89% response rate (n=171). More tertiary NICUs institute DR CPAP than non-tertiary units (43% vs. 16%, P=0.0001) though there was no significant difference in frequency of elective intubation and surfactant administration for preterm babies. More tertiary units commence DR resuscitation in air (62% vs. 29%, P<0.0001) and fewer in 100% oxygen (11% vs. 41%, P<0.0001). Resuscitation of preterm babies in particular, commences with air in 56% of tertiary units. Significantly more tertiary units use DR pulse oximeters (58% vs. 29%, P<0.01) and titrate oxygen based on saturations. Almost all services use occlusive wrapping to maintain temperature for preterm infants. CONCLUSIONS: In the UK, there are many areas of good evidence based DR practice. However, there is marked variation in management, including between units of different designation, suggesting a need to review practice to fulfil new resuscitation guidance, which will have training and resource implications.