Search

Children born preterm (≤ 37 weeks) are at higher risk of developing cognitive problems and score lower on cognitive developmental assessments than full-term children. The objective of the paper is to analyse the impact of correction for prematurity on IQ scores amongst preterm born children at school age. A sample of 153 Spanish school-age children were assessed using the WISC-V (Full Scale IQ and all indexes). Assessments were re-scored based on corrected age. Pairwise t-tests were used to analyse the difference in mean IQ scores between corrected age and uncorrected (chronological) age. WISC-V IQ scores

Abstract Background Stability during early postnatal life in preterm infants is related to better outcomes. Although vital signs are monitored continuously in Neonatal Intensive Care Unites, this monitoring does not include all physiological parameters nor data such as movement patterns. Although there are scattered sources of data, there is no centralized data hub for neonates information. Results We have created the first neonate data hub for easy and interactive access to upload or download postural, physiological, and medical data of neonates: NeoVault. NeoVault is a platform that provides access to information through two interfaces: 1) via a Web interface (designed for medical personnel, data scientists, researchers); and 2) via a RESTful API (Application Programming Interfaces) -designed for developers-, aiming to integrate access to information into third-party applications. The web access allows searching and filtering according to specific parameters, visualization of data through graphs and images, and generation of datasets in CSV format. Access through the RESTful API is described in OpenAPI, enabling access to information from any device, facilitating it in an interoperable format. Currently, it contains nearly 800,000 postural records and 3.000 physiological data entries. The physiological and postural data stored for each neonate in NeoVault are collected through the NRP (Neonates Recording Platform) tool, which allows for the automatic and reliable collection of data. Conclusion NeoVault is an open platform for simple access to postural, physiological, and medical data of neonates that can be utilized by researchers, data scientists, medical personnel, and programmers. It enables integration into third-party applications and the generation of customized datasets.

Background and objectiveVery preterm infants are highly susceptible to Neurodevelopmental Impairments (NDIs), including cognitive, motor, and language deficits. This paper presents a systematic review of the application of Machine Learning (ML) techniques to predict NDIs in premature infants.MethodsThis review presents a comparative analysis of existing studies from January 2018 to December 2023, highlighting their strengths, limitations, and future research directions.ResultsWe identified 26 studies that fulfilled the inclusion criteria. In addition, we explore the potential of ML algorithms and discuss commonly used data sources, including clinical and neuroimaging data. Furthermore, the inclusion of omics data as a contemporary approach employed, in other diagnostic contexts is proposed.ConclusionsWe identified limitations and emphasized the significance of employing multimodal data models and explored various alternatives to address the limitations identified in the reviewed studies. The insights derived from this review guide researchers and clinicians toward improving early identification and intervention strategies for NDIs in this vulnerable population.

Preterm infants are prone to NeuroDevelopmental Impairment (NDI). Some previous works have identified clinical variables that can be potential predictors of NDI. However, machine learning (ML)-based models still present low predictive capabilities when addressing this problem. This work attempts to evaluate the application of ML techniques to predict NDI using clinical data from a cohort of very preterm infants recruited at birth and assessed at 2 years of age. Six different classification models were assessed, using all features, clinician-selected features, and mutual information feature selection. The best results were obtained by ML models trained using mutual information-selected features and employing oversampling, for cognitive and motor impairment prediction, while for language impairment prediction the best setting was clinician-selected features. Although the performance indicators in this local cohort are consistent with similar previous works and still rather poor. This is a clear indication that, in order to obtain better performance rates, further analysis and methods should be considered, and other types of data should be taken into account together with the clinical variables.

In this study, we introduce MGA-Net, a novel mask-guided attention neural network, which extends the U-net model for precision neonatal brain imaging. MGA-Net is designed to extract the brain from other structures and reconstruct high-quality brain images. The network employs a common encoder and two decoders: one for brain mask extraction and the other for brain region reconstruction. A key feature of MGA-Net is its high-level mask-guided attention module, which leverages features from the brain mask decoder to enhance image reconstruction. To enable the same encoder and decoder to process both MRI and ultrasound (US) images, MGA-Net integrates sinusoidal positional encoding. This encoding assigns distinct positional values to MRI and US images, allowing the model to effectively learn from both modalities. Consequently, features learned from a single modality can aid in learning a modality with less available data, such as US. We extensively validated the proposed MGA-Net on diverse and independent datasets from varied clinical settings and neonatal age groups. The metrics used for assessment included the DICE similarity coefficient, recall, and accuracy for image segmentation; structural similarity for image reconstruction; and root mean squared error for total brain volume estimation from 3D ultrasound images. Our results demonstrate that MGA-Net significantly outperforms traditional methods, offering superior performance in brain extraction and segmentation while achieving high precision in image reconstruction and volumetric analysis. Thus, MGA-Net represents a robust and effective preprocessing tool for MRI and 3D ultrasound images, marking a significant advance in neuroimaging that enhances both research and clinical diagnostics in the neonatal period and beyond.

IntroductionSeveral studies demonstrate the relationship between preterm birth and a reduced thalamus volume at term-equivalent age. In contrast, this study aims to investigate the link between the thalamic growth trajectory during the early postnatal period and neurodevelopment at two years of age.MethodsThalamic volume was extracted from 84 early MRI scans at postmenstrual age of 32.33 (± 2.63) weeks and 93 term-equivalent age MRI scans at postmenstrual age of 42.05 (± 3.33) weeks of 116 very preterm infants (56% male) with gestational age at birth of 29.32 (± 2.28) weeks and a birth weight of 1158.92 (± 348.59) grams. Cognitive, motor, and language outcomes at two years of age were assessed with Bayley Scales of Infant and Toddler Development Third Edition. Bivariate analysis was used to describe the clinical variables according to neurodevelopmental outcomes and multilevel linear regression models were used to examine the impact of these variables on thalamic volume and its relationship with neurodevelopmental outcomes.ResultsThe results suggest an association between severe brain injury and thalamic growth trajectory (β coef = −0.611; p < 0.001). Moreover, thalamic growth trajectory during early postnatal life was associated with the three subscale scores of the neurodevelopmental assessment (cognitive: β coef = 6.297; p = 0.004; motor: β coef = 7.283; p = 0.001; language: β coeficient = 9.053; p = 0.002).DiscussionThese findings highlight (i) the impact of severe brain injury on thalamic growth trajectory during early extrauterine life after preterm birth and (ii) the relationship of thalamic growth trajectory with cognitive, motor, and language outcomes.

Abstract To train, evaluate, and validate the application of a deep learning framework in three-dimensional ultrasound (3D US) for the automatic segmentation of ventricular volume in preterm infants with post haemorrhagic ventricular dilatation (PHVD). We trained a 2D convolutional neural network (CNN) for automatic segmentation ventricular volume from 3D US of preterm infants with PHVD. The method was validated with the Dice similarity coefficient (DSC) and the intra-class coefficient (ICC) compared to manual segmentation. The mean birth weight of the included patients was 1233.1 g (SD 309.4) and mean gestational age was 28.1 weeks (SD 1.6). A total of 152 serial 3D US from 10 preterm infants with PHVD were analysed. 230 ventricles were manually segmented. Of these, 108 were used for training a 2D CNN and 122 for validating the methodology for automatic segmentation. The global agreement for manual versus automated measures in the validation data (n = 122) was excellent with an ICC of 0.944 (0.874–0.971). The Dice similarity coefficient was 0.8 (± 0.01). 3D US based ventricular volume estimation through an automatic segmentation software developed through deep learning improves the accuracy and reduces the processing time needed for manual segmentation using VOCAL. 3D US should be considered a promising tool to help deepen our current understanding of the complex evolution of PHVD.

Objectives: The aim of this study is to explore if manually segmented total brain volume (TBV) from 3D ultrasonography (US) is comparable to TBV estimated by magnetic resonance imaging (MRI). We then wanted to test 2D based TBV estimation obtained through three linear axes which would enable monitoring brain growth in the preterm infant during admission.Methods: We included very low birth weight preterm infants admitted to our neonatal intensive care unit (NICU) with normal neuroimaging findings. We measured biparietal diameter, anteroposterior axis, vertical axis from US and MRI and TBV from both MRI and 3D US. We calculated intra- and interobserver agreement within and between techniques using the intraclass correlation coefficient and Bland-Altman methodology. We then developed a multilevel prediction model of TBV based on linear measurements from both US and MRI, compared them and explored how they changed with increasing age. The multilevel prediction model for TBV from linear measures was tested for internal and external validity and we developed a reference table for ease of prediction of TBV.Results: We used measurements obtained from 426 US and 93 MRI scans from 118 patients. We found good intra- and interobserver agreement for all the measurements. US measurements were reliable when compared to MRI, including TBV which achieved excellent agreement with that of MRI [ICC of 0.98 (95% CI 0.96–0.99)]. TBV estimated through 2D measurements of biparietal diameter, anteroposterior axis, and vertical axis was comparable among both techniques. We estimated the population 95% confidence interval for the mean values of biparietal diameter, anteroposterior axis, vertical axis, and total brain volume by post-menstrual age. A TBV prediction table based on the three axes is proposed to enable easy implementation of TBV estimation in routine 2D US during admission in the NICU.Conclusions: US measurements of biparietal diameter, vertical axis, and anteroposterior axis are reliable. TBV segmented through 3D US is comparable to MRI estimated TBV. 2D US accurate estimation of TBV is possible through biparietal diameter, vertical, and anteroposterior axes.

Introduction: Current guidelines in Spain recommend performing transthoracic echocardiography (TTE) in all children under 2 years of age with a heart murmur. In 2014, the American Paediatric Association published the first appropriate use criteria (AUC) for outpatient paediatric transthoracic echocardiography (TTE) to promote its cost-efficient use. The aim of this article is to analyse the AUC and other clinical factors as predictors of congenital heart disease (CHD) in children less than 2 years of age with a heart murmur, and to develop a safe and efficient referral strategy. Patients and method: Case–control study conducted with children less than 2 years of age, referred from Paediatric Primary Care to Paediatric Cardiology during a 4-year study. A predictive model for CHD was determined using multivariate analysis. Results: A total of 688 patients were included, with 129 (19%) cases of CHD. An age less than 3 months (adjusted odds ratio [ORa] 3.8 [1.5–8.4], p = 0.030) and fulfilling AUC (ORa 16.3 [9.4–28.3], p

Resumen: Introducción: La Sociedad Española de Cardiología Pediátrica y Cardiopatías Congénitas recomienda realizar ecocardiografía transtorácica (ETT) en todo menor de 2 años con soplo. En 2014 la Asociación Americana de Pediatría publicó los primeros criterios de uso apropiado de ETT pediátrica ambulatoria (CUA) como guía para promover un uso costo-eficiente de la misma. Nuestro objetivo fue analizar los CUA y otros factores clínicos como predictores de cardiopatía congénita (CC) en menores de 2 años con soplo para desarrollar una estrategia de derivación eficiente y segura. Pacientes y método: Estudio de casos y controles en menores de 2 años derivados por pediatría de atención primaria a cardiología pediátrica por soplo durante 4 años. Mediante análisis multivariante se determinó un modelo predictivo de CC. Resultados: Se incluyeron 688 pacientes con 129 casos (19%) de CC. La edad menor a 3 meses (odds ratio ajustada [ORa] 3,8[1,5-8,4]; p=0,030) y cumplimiento de CUA (ORa 16,3[9,4-28,3]; p

Resumen: Introducción: La incidencia de la encefalopatía hipóxico-isquémica perinatal (EHI) y la implementación de la hipotermia terapéutica (HT) es desconocida en España. Método: Estudio transversal nacional en recién nacidos vivos (RNV) ≥ 35 semanas de gestación mediante cuestionario on-line en las 90 unidades neonatales de nivel iii. Se solicitaron datos de los RNV con EHI moderada-grave en los años 2012 y 2013, y de la implementación de la HT en junio del 2015. Resultados: Se recibieron datos de los 90 hospitales. La incidencia de EHI moderada-grave fue 0,77/1.000 RNV (IC del 95%, 0,72; 0,83). El 86% de los RNV con EHI recibieron HT (activa o pasiva), aumentando los que recibieron HT activa del 78% en 2012 al 85% en 2013 (p = 0,01). El 14% no recibió HT principalmente por retraso en el diagnóstico o en el traslado, o por no indicarse el tratamiento. El 57% de los RN nació en hospitales sin HT, siendo el traslado en hipotermia pasiva; en el 39% por equipos sin formación adecuada. En junio del 2015, 57/90 centros realizaban HT: 54 HT corporal total activa (todos con dispositivos servocontrolados). Existió heterogeneidad en la distribución por comunidades autónomas (CC. AA.) de centros con HT activa y en el número de RN que recibieron HT. Conclusiones: La incidencia de EHI moderada-grave es homogénea entre CC. AA. Aunque se constata un importante progreso en la implementación de la HT, es preciso mejorar la disponibilidad de HT activa entre CC. AA., así como el diagnóstico precoz y el traslado con garantías desde los centros emisores. Abstract: Introduction: There are no data on the incidence of hypoxic-ischaemic encephalopathy (HIE) and the implementation of therapeutic hypothermia (TH) in Spain. Methods: This is a cross-sectional, national study, performed using an on-line questionnaire targeting level III neonatal care units in Spain. Participants were requested to provide data of all newborns ≥ 35 weeks of gestational age diagnosed with moderate-severe HIE over a two year-period (2012-2013), and of the implementation of TH up to June 2015. Results: All (90) contacted hospitals participated. HIE incidence rate was 0.77/1000 live newborns (95% CI 0.72 - 0.83). During 2012-2013, 86% of the newborns diagnosed with moderate-severe HIE received TH (active or passive). Active TH was increasingly used, from 78% in 2012 to 85% in 2013 (P=.01). Of the 14% that did not receive TH, it was mainly due to a delay in the diagnosis or inter-hospital transfer, and to the fact that the treatment was not offered. More than half (57%) were born in hospitals where TH was not provided, and passive hypothermia was used for inter-hospital patient transfer, and in 39% of the cases by inappropriately trained personnel. By June 2015, 57 out of 90 centres had implemented TH, of which 54 performed whole-body TH (using servo-controlled devices). The geographical distribution of centres with active TH, and the number of newborn that received TH, was heterogeneous. Conclusions: The incidence of moderate-severe HIE is homogeneous across Spanish territory. Significant progress is being made in the implementation of TH, however it is necessary to increase the availability of active TH between Autonomous Communities, to improve early diagnosis, and to guarantee high quality patient transfer to referral centres.

Introduction: There are no data on the incidence of hypoxic-ischaemic encephalopathy (HIE) and the implementation of therapeutic hypothermia (TH) in Spain. Methods: This is a cross-sectional, national study, performed using an on-line questionnaire targeting level III neonatal care units in Spain. Participants were requested to provide data of all newborns ≥ 35 weeks of gestational age diagnosed with moderate-severe HIE over a two year-period (2012–2013), and of the implementation of TH up to June 2015. Results: All (90) contacted hospitals participated. HIE incidence rate was 0.77/1000 live newborns (95% CI 0.72–0.83). During 2012–2013, 86% of the newborns diagnosed with moderate-severe HIE received TH (active or passive). Active TH was increasingly used, from 78% in 2012 to 85% in 2013 (P = .01). Of the 14% that did not receive TH, it was mainly due to a delay in the diagnosis or inter-hospital transfer, and to the fact that the treatment was not offered. More than half (57%) were born in hospitals where TH was not provided, and passive hypothermia was used for inter-hospital patient transfer, and in 39% of the cases by inappropriately trained personnel. By June 2015, 57 out of 90 centres had implemented TH, of which 54 performed whole-body TH (using servo-controlled devices). The geographical distribution of centres with active TH, and the number of newborn that received TH, was heterogeneous. Conclusions: The incidence of moderate-severe HIE is homogeneous across Spanish territory. Significant progress is being made in the implementation of TH, however it is necessary to increase the availability of active TH between Autonomous Communities, to improve early diagnosis, and to guarantee high quality patient transfer to referral centres. Resumen: Introducción: La incidencia de la encefalopatía hipóxico-isquémica perinatal (EHI) y la implementación de la hipotermia terapéutica (HT) es desconocida en España. Método: Estudio transversal nacional en recién nacidos vivos (RNV) ≥ 35 semanas de gestación mediante cuestionario on-line en las 90 unidades neonatales de nivel iii. Se solicitaron datos de los RNV con EHI moderada-grave en los años 2012 y 2013, y de la implementación de la HT en junio del 2015. Resultados: Se recibieron datos de los 90 hospitales. La incidencia de EHI moderada-grave fue 0.77/1.000 RNV (IC del 95%, 0.72; 0.83). El 86% de los RNV con EHI recibieron HT (activa o pasiva), aumentando los que recibieron HT activa del 78% en 2012 al 85% en 2013 (p = 0.01). El 14% no recibió HT principalmente por retraso en el diagnóstico o en el traslado, o por no indicarse el tratamiento. El 57% de los RN nació en hospitales sin HT, siendo el traslado en hipotermia pasiva; en el 39% por equipos sin formación adecuada. En junio del 2015, 57/90 centros realizaban HT: 54 HT corporal total activa (todos con dispositivos servocontrolados). Existió heterogeneidad en la distribución por comunidades autónomas (CC. AA.) de centros con HT activa y en el número de RN que recibieron HT. Conclusiones: La incidencia de EHI moderada-grave es homogénea entre CC. AA. Aunque se constata un importante progreso en la implementación de la HT, es preciso mejorar la disponibilidad de HT activa entre CC. AA., así como el diagnóstico precoz y el traslado con garantías desde los centros emisores.

Background: Myocardial function in very-low-birth-weight infants (VLBWIs) develops during early postnatal life, but different patterns of temporal evolution that might be related to the development of bronchopulmonary dysplasia (BPD) are not completely understood.Methods: A prospective cohort study including VLBWIs admitted to our NICU from January 2015 to 2017 was conducted. Plasma N-terminal pro B type natriuretic peptide (NTproBNP) levels were measured, and echocardiograms were performed at 24 and 72 h of life and weekly thereafter until 36 weeks of postmenstrual age (PMA). We measured the tricuspid annular plane systolic excursion (TAPSE) by M-mode; the lateral tricuspid E', A', and S' waves; and the myocardial performance index (MPI) by tissue doppler imaging (TDI). The subjects were divided into non-BPD and BPD groups.Results: We included 101 VLBWIs. The TAPSE and E', A', and S' waves increased while MPI-TDI decreased over time. Birth gestational age (GA) and postnatal PMA impacted these parameters, which evolved differently in those who developed BPD compared to those in the non-BPD group. The NTproBNP levels at 14 days of life and different echocardiographic parameters were associated with the development of BPD in different multivariate models.Conclusion: TAPSE and TDI values depend on GA and PMA and follow a different temporal evolution that is related to the later development of BPD. Combined biochemical and echocardiographic biomarkers can help identify which VLBWIs are at higher risk of developing BDP.

Introduction: One of the problems that the delivery of continuous positive airway pressure (CPAP) via a helmet poses is the generation of noise. The objective of our study was to assess the effect that the use of filter has on sound pressure levels generated by the delivery of positive airway pressure at different gas flow rates. Materials and Methods: Sound pressure levels generated by neonatal helmet CPAP delivery were measured at different gas flows (20, 30, and 40 l/min) with and without a breathing filter. Noise intensity was measured by installing microphones in the inner ear of dummy heads wearing helmets. Results: The sound pressure level increased by 38% at a gas flow of 40 l/min, as compared to a gas flow of 20 l/min {74 dBA [interquartile range (IQR) 2,2] vs 52 dBA (IQR 5,9), respectively}. Using the breathing filter as a diffuser has a variety of effects on sound pressure levels according to the gas flow rate. Conclusion: The intensity of the noise generated by helmet delivery of positive airway pressure depends on the type of helmet used, gas flow, and use or not of a diffuser filter. Breathing filters with gas flows over 30 l/min might not be recommended since they would not attenuate but will rather amplify sound pressure.

The role of rhinoviruses (RVs) in children with clinical syndromes not classically associated with RV infections is not well understood. We analyzed a cohort of children ≤21 years old who were PCR+ for RV at a large Pediatric Hospital from 2011 to 2013. Using univariate and multivariable logistic regression, we analyzed the associations between demographic, clinical characteristics, microbiology data, and clinical outcomes in children with compatible symptoms and incidental RV detection. Of the 2473 children (inpatients and outpatients) with an RV+ PCR, 2382 (96%) had compatible symptoms, and 91 (4%) did not. The overall median age was 14 months and 78% had underlying comorbidities. No differences in RV viral loads were found according to the presence of compatible symptoms, while in children with classic RV symptoms, RV viral loads were higher in single RV infections versus RV viral co-infections. Bacterial co-infections were more common in RV incidental detection (7.6%) than in children with compatible symptoms (1.9%, p < 0.001). The presence of compatible symptoms independently increased the odds ratio (OR, 95% CI) of hospitalization 4.8 (3.1–7.4), prolonged hospital stays 1.9 (1.1–3.1), need for oxygen 12 (5.8–25.0) and pediatric intensive care unit (PICU) admission 4.13 (2.0–8.2). Thus, despite comparable RV loads, disease severity was significantly worse in children with compatible symptoms.