Enhancing daily life for children with cognitive developmental delay through insights into brain development.

Cognitive developmental delay, including severe intellectual disability (IQ below 70) and borderline intellectual functioning (IQ 70-85), poses significant challenges, including high costs and emotional burden. Early diagnosis and interventions might improve adaptive behavior and daily life functioning. High-risk groups include children with neonatal complications, congenital anomalies, genetic disorders, or metabolic errors, yet over 50% of cases have unknown causes. To provide timely diagnosis and intervention for children with cognitive developmental delay, it is important to increase our understanding and ability to prognosticate their level of functioning. The pivotal role of brain development in the first few years of life presents a window of opportunity for these goals. By detailed investigation of common patterns in structural brain development and connectivity by MRI in relation to cognitive and executive functioning, this review aims to identify potential factors that might improve understanding and prognostication of children with cognitive developmental delay. Exploring similarities among diverse patient groups with childhood cognitive developmental delay, this review intends to provide a nuanced perspective. IMPACT: This review identified several MRI brain developmental markers, especially in the white matter, that might hold potential to be a prognostic marker for intellectual and executive functioning in children with cognitive developmental delay. Bringing together information on aberrant brain developmental trajectories and connectivity across different patient childhood populations with cognitive developmental delay might improve our understanding and prognostication.

Impact of daily music on comfort scores in preterm infants: a randomized controlled trial.

BACKGROUND: Premature birth heightens neurodevelopmental risks, theorized to partly stem from altered sensory inputs and disrupted sleep patterns. Modifying the acoustic milieu through music intervention (MI) offers promise to improve neonatal comfort, reduce sleep disturbances, and stabilize physiological parameters. This study explores the impact of non-pharmacological MI on these health indicators within the Neonatal Intensive Care Unit (NICU). METHODS: A single-blinded RCT was conducted. Premature infants (34 > GA > 29 wks) were randomly assigned to either receive 8 min of daily MI or placebo for up to 15 days. Validated behavioral comfort scores were visually obtained by a blinded observer before and after intervention. Additionally, physiological signs (HR, RR, SatO2) were recorded. Differences between the groups were analyzed using χ² tests and t-tests. RESULTS: In total 56 preterm infants were included. After intervention, comfort levels increased significantly in the MI compared to placebo group (p = 0.000). Neonates receiving MI transitioned from wakefulness to a state of sleep significantly more compared to placebo (p = 0.002). Physiological parameters remained stable. CONCLUSIONS: This study adds to existing literature demonstrating that a music intervention in a NICU setting can enhance comfort and sleep of premature infants without adversely affecting physiological parameters. IMPACT: The study demonstrates that music interventions (MI) in a Neonatal Intensive Care Unit (NICU) setting can significantly increase comfort levels and positively impact the sleep of premature infants without negatively impacting their physiological parameters. This research increases evidence for non-pharmacological interventions, specifically music, as beneficial for the well-being of premature infants in NICU settings. It replicates and expands upon previous methodological designs, providing more robust evidence of MI's positive effects on this vulnerable population. The positive outcomes of music intervention could influence hospital policies by integrating non-pharmacological practices into standard neonatal care protocols to enhance developmental support for premature infants.

Population Pharmacokinetics and Target Attainment of Allopurinol and Oxypurinol Before, During, and After Cardiac Surgery with Cardiopulmonary Bypass in Neonates with Critical Congenital Heart Disease.

BACKGROUND: The CRUCIAL trial (NCT04217421) is investigating the effect of postnatal and perioperative administration of allopurinol on postoperative brain injury in neonates with critical congenital heart disease (CCHD) undergoing cardiac surgery with cardiopulmonary bypass (CPB) shortly after birth. OBJECTIVE: This study aimed to characterize the pharmacokinetics (PK) of allopurinol and oxypurinol during the preoperative, intraoperative, and postoperative phases in this population, and to evaluate target attainment of the current dosing strategy. METHODS: Nonlinear mixed-effects modeling was used to develop population PK models in 14 neonates from the CRUCIAL trial who received up to five intravenous allopurinol administrations throughout the postnatal and perioperative periods. Target attainment was defined as achieving an allopurinol concentration >2 mg/L in at least two-thirds of the patients during the first 24 h after birth and between the start and 36 h after cardiac surgery with CPB. RESULTS: A two-compartment model for allopurinol was connected to a one-compartment model for oxypurinol with an auto-inhibition effect on the conversion, which best described the PK. In a typical neonate weighing 3.5 kg who underwent cardiac surgery at a postnatal age (PNA) of 5.6 days, the clearance (CL) of allopurinol and oxypurinol at birth was 0.95 L/h (95% confidence interval 0.75-1.2) and 0.21 L/h (0.17-0.27), respectively, which subsequently increased with PNA to 2.97 L/h and 0.41 L/h, respectively, before CPB. During CPB, allopurinol and oxypurinol CL decreased to 1.38 L/h (0.9-1.87) and 0.12 L/h (0.05-0.22), respectively. Post-CPB, allopurinol CL increased to 2.21 L/h (1.74-2.83), while oxypurinol CL dropped to 0.05 L/h (0.01-0.1). Target attainment was 100%, 53.8%, and 100% at 24 h postnatally, 24 h after the start of CPB, and 36 h after the end of cardiac surgery, respectively. The combined concentrations of allopurinol and oxypurinol maintained ≥ 90% inhibition of xanthine oxidase (IC90XO) throughout the postnatal and perioperative period. CONCLUSIONS: The minimal target concentration of allopurinol was not achieved at every predefined time interval in the CRUCIAL trial; however, the dosing strategy used was deemed adequate, since it yielded concentrations well exceeding the IC90XO. The decreased CL of both compounds during CPB suggests influence of the hypothermia, hemofiltration, and the potential sequestration of allopurinol in the circuit. The reduced CL of oxypurinol after CPB is likely attributable to impaired kidney function.

Placenta histology related to flow and oxygenation in fetal congenital heart disease.

BACKGROUND: Fetuses with congenital heart defects (CHD) show delayed neurodevelopment, fetal growth restriction (FGR) and placenta related complications. The neurodevelopmental delay may be, partly, attributed to placental factors. AIM: As both placental development and fetal aortic flow/oxygenation influence neurodevelopment, placentas were compared within fetal CHD groups based on aortic oxygenation and flow, aiming to unravel the true effects in the developmental processes. STUDY DESIGN: Placental tissues of pregnancies with fetal CHD and healthy controls were selected from biobanks of two Dutch academic hospitals (LUMC, UMCU). Additionally, biometry and Dopplers were assessed. SUBJECTS: CHD cases with reduced oxygenation (RO) towards the fetal brain were compared to cases with reduced flow (RF) in the aortic arch and healthy controls. Genetic abnormalities, termination of pregnancy, fetal demise and/or multiple pregnancies were excluded. OUTCOME MEASURES: Histological outcomes were related to fetal Dopplers and biometry. A placenta severity score was used to assess the severity of placental abnormalities per case. RESULTS: In CHD, significantly more delayed maturation, maternal vascular malperfusion, fetal hypoxia and higher placenta severity scores (median 14 in RO, 14 in RF, 5 in controls, p < 0.001) were observed. Doppler abnormalities (PI UA > p90, PI MCA < p10, CPR < p10) and FGR were more often found in CHD. There were no differences in placental abnormalities, fetal growth and fetal Dopplers between cases with RO and RF. CONCLUSION: Fetal hemodynamics in the ascending aorta could not be related to placenta characteristics. We hypothesize that placental development influences neurodevelopment in excess of hemodynamics in CHD cases.

Association between sleep stages and brain microstructure in preterm infants: Insights from DTI analysis.

STUDY OBJECTIVES: The aim of this study was to investigate the relationship between sleep stages and neural microstructure - measured using diffusion tensor imaging - of the posterior limb of the internal capsule and corticospinal tract in preterm infants. METHODS: A retrospective cohort of 50 preterm infants born between 24 + 4 and 29 + 3 weeks gestational age was included in the study. Sleep stages were continuously measured for 5-7 consecutive days between 29 + 0 and 31 + 6 weeks postmenstrual age using an in-house-developed, and recently published, automated sleep staging algorithm based on routinely measured heart rate and respiratory rate. Additionally, a diffusion tensor imaging scan was conducted at term equivalent age as part of standard care. Region of interest analysis of the posterior limb of the internal capsule was performed, and tractography was used to analyze the corticospinal tract. The association between sleep and white matter microstructure of the posterior limb of the internal capsule and corticospinal tract was examined using a multiple linear regression model, adjusted for potential confounders. RESULTS: The results of the analyses revealed an interaction effect between sleep stage and days of invasive ventilation on the fractional anisotropy of the left and right posterior limb of the internal capsule (ß = 0.04, FDR-adjusted p = 0.001 and ß = 0.04, FDR-adjusted p = 0.02, respectively). Furthermore, an interaction effect between sleep stage and days of invasive ventilation was observed for the radial diffusivity of the mean of the left and right PLIC (ß = -4.1e-05, FDR-adjusted p = 0.04). CONCLUSIONS: Previous research has shown that, in very preterm infants, invasive ventilation has a negative effect on white matter tract maturation throughout the brain. A positive association between active sleep and white matter microstructure of the posterior limb of the internal capsule, may indicate a protective role of sleep in this vulnerable population.

Brain MRI Injury Patterns across Gestational Age among Preterm Infants with Perinatal Asphyxia.

INTRODUCTION: Brain injury patterns of preterm infants with perinatal asphyxia (PA) are underreported. We aimed to explore brain magnetic resonance imaging (MRI) findings and associated neurodevelopmental outcomes in these newborns. METHODS: Retrospective multicenter study included infants with gestational age (GA) 24.0-36.0 weeks and PA, defined as ≥2 of the following: (1) umbilical cord pH ≤7.0, (2) 5-min Apgar score ≤5, and (3) fetal distress or systemic effects of PA. Findings were compared between GA <28.0 (group 1), 28.0-31.9 (group 2), and 32.0-36.0 weeks (group 3). Early MRI (<36 weeks postmenstrual age or <10 postnatal days) was categorized according to predominant injury pattern, and MRI around term-equivalent age (TEA, 36.0-44.0 weeks and ≥10 postnatal days) using the Kidokoro score. Adverse outcomes included death, cerebral palsy, epilepsy, severe hearing/visual impairment, or neurodevelopment <-1 SD at 18-24 months corrected age. RESULTS: One hundred nineteen infants with early MRI (n = 94) and/or MRI around TEA (n = 66) were included. Early MRI showed predominantly hemorrhagic injury in groups 1 (56%) and 2 (45%), and white matter (WM)/watershed injury in group 3 (43%). Around TEA, WM scores were highest in groups 2 and 3. Deep gray matter (DGM) (aOR 15.0, 95% CI: 3.8-58.9) and hemorrhagic injury on early MRI (aOR 2.5, 95% CI: 1.3-4.6) and Kidokoro WM (aOR 1.3, 95% CI: 1.0-1.6) and DGM sub-scores (aOR 4.8, 95% CI: 1.1-21.7) around TEA were associated with adverse neurodevelopmental outcomes. CONCLUSION: The brain injury patterns following PA in preterm infants differ across GA. Particularly DGM abnormalities are associated with adverse neurodevelopmental outcomes.

Morbidity and trends in length of hospitalisation of very and extremely preterm infants born between 2008 and 2021 in the Netherlands: a cohort study.

OBJECTIVES: This study investigated changes in the length of stay (LoS) at a level III/IV neonatal intensive care unit (NICU) and level II neonatology departments until discharge home for very preterm infants and identified factors influencing these trends. DESIGN: Retrospective cohort study based on data recorded in the Netherlands Perinatal Registry between 2008 and 2021. SETTING: A single level III/IV NICU and multiple level II neonatology departments in the Netherlands. PARTICIPANTS: NICU-admitted infants (n=2646) with a gestational age (GA) <32 weeks. MAIN OUTCOME MEASURES: LoS at the NICU and overall LoS until discharge home. RESULTS: The results showed an increase of 5.1 days (95% CI 2.2 to 8, p<0.001) in overall LoS in period 3 after accounting for confounding variables. This increase was primarily driven by extended LoS at level II hospitals, while LoS at the NICU remained stable. The study also indicated a strong association between severe complications of preterm birth and LoS. Treatment of infants with a lower GA and more (severe) complications (such as severe retinopathy of prematurity) during the more recent periods may have increased LoS. CONCLUSION: The findings of this study highlight the increasing overall LoS for very preterm infants. LoS of very preterm infants is presumably influenced by the occurrence of complications of preterm birth, which are more frequent in infants at a lower gestational age.

Placental Pathology Contributes to Impaired Volumetric Brain Development in Neonates With Congenital Heart Disease.

BACKGROUND: Neonates with congenital heart disease are at risk for impaired brain development in utero, predisposing children to postnatal brain injury and adverse long-term neurodevelopmental outcomes. Given the vital role of the placenta in fetal growth, we assessed the incidence of placental pathology in fetal congenital heart disease and explored its association with total and regional brain volumes, gyrification, and brain injury after birth. METHODS AND RESULTS: Placentas from 96 term singleton pregnancies with severe fetal congenital heart disease were prospectively analyzed for macroscopic and microscopic pathology. We applied a placental pathology severity score to relate placental abnormalities to neurological outcome. Postnatal, presurgical magnetic resonance imaging was used to analyze brain volumes, gyrification, and brain injuries. Placental analyses revealed the following abnormalities: maternal vascular malperfusion lesions in 46%, nucleated red blood cells in 37%, chronic inflammatory lesions in 35%, delayed maturation in 30%, and placental weight below the 10th percentile in 28%. Severity of placental pathology was negatively correlated with cortical gray matter, deep gray matter, brainstem, cerebellar, and total brain volumes (r=-0.25 to -0.31, all P<0.05). When correcting for postmenstrual age at magnetic resonance imaging in linear regression, this association remained significant for cortical gray matter, cerebellar, and total brain volume (adjusted R2=0.25-0.47, all P<0.05). CONCLUSIONS: Placental pathology occurs frequently in neonates with severe congenital heart disease and may contribute to impaired brain development, indicated by the association between placental pathology severity and reductions in postnatal cortical, cerebellar, and total brain volumes.

Detailed statistical analysis plan for ALBINO: effect of Allopurinol in addition to hypothermia for hypoxic-ischemic Brain Injury on Neurocognitive Outcome - a blinded randomized placebo-controlled parallel group multicenter trial for superiority (phase III).

BACKGROUND: Despite therapeutic hypothermia (TH) and neonatal intensive care, 45-50% of children affected by moderate-to-severe neonatal hypoxic-ischemic encephalopathy (HIE) die or suffer from long-term neurodevelopmental impairment. Additional neuroprotective therapies are sought, besides TH, to further improve the outcome of affected infants. Allopurinol - a xanthine oxidase inhibitor - reduced the production of oxygen radicals and subsequent brain damage in pre-clinical and preliminary human studies of cerebral ischemia and reperfusion, if administered before or early after the insult. This ALBINO trial aims to evaluate the efficacy and safety of allopurinol administered immediately after birth to (near-)term infants with early signs of HIE. METHODS/DESIGN: The ALBINO trial is an investigator-initiated, randomized, placebo-controlled, double-blinded, multi-national parallel group comparison for superiority investigating the effect of allopurinol in (near-)term infants with neonatal HIE. Primary endpoint is long-term outcome determined as survival with neurodevelopmental impairment versus death versus non-impaired survival at 2 years. RESULTS: The primary analysis with three mutually exclusive responses (healthy, death, composite outcome for impairment) will be on the intention-to-treat (ITT) population by a generalized logits model according to Bishop, Fienberg, Holland (Bishop YF, Discrete Multivariate Analysis: Therory and Practice, 1975) and ."will be stratified for the two treatment groups. DISCUSSION: The statistical analysis for the ALBINO study was defined in detail in the study protocol and implemented in this statistical analysis plan published prior to any data analysis. This is in accordance with the Declaration of Helsinki and the International Conference on Harmonization Good Clinical Practice guidelines. TRIAL REGISTRATION: ClinicalTrials.gov NCT03162653. Registered on 22 May 2017.

Effect of Systemic Hydrocortisone on Brain Abnormalities and Regional Brain Volumes in Ventilator-dependent Infants Born Preterm: Substudy of the SToP-BPD Study.

OBJECTIVE: To evaluate whether a high cumulative dose of systemic hydrocortisone affects brain development compared with placebo when initiated between 7 and 14 days after birth in ventilated infants born preterm. STUDY DESIGN: A double-blind, placebo-controlled, randomized trial was conducted in 16 neonatal intensive care units among infants born at <30 weeks of gestation or with a birth weight of <1250 g who were ventilator-dependent in the second week after birth. Three centers performed MRI at term-equivalent age. Brain injury was assessed on MRI using the Kidokoro scoring system and compared between the 2 treatment groups. Both total and regional brain volumes were calculated using an automatic segmentation method and compared using multivariable regression analysis adjusted for baseline variables. RESULTS: From the 3 centers, 78 infants participated in the study and 59 had acceptable MRI scans (hydrocortisone group, n = 31; placebo group, n = 28). Analyses of the median global brain abnormality score of the Kidokoro score showed no difference between the hydrocortisone and placebo groups (median, 7; IQR, 5-9 vs median, 8, IQR, 4-10, respectively; P = .92). In 39 infants, brain tissue volumes were measured, showing no differences in the adjusted mean total brain tissue volumes, at 352 ± 32 mL in the hydrocortisone group and 364 ± 51 mL in the placebo group (P = .80). CONCLUSIONS: Systemic hydrocortisone started in the second week after birth in ventilator-dependent infants born very preterm was not found to be associated with significant differences in brain development compared with placebo treatment. TRIAL REGISTRATION: The SToP-BPD study was registered with the Netherlands Trial Register (NTR2768; registered on 17 February 2011; https://www.trialregister.nl/trial/2640) and the European Union Clinical Trials Register (EudraCT, 2010-023777-19; registered on 2 November 2010; https://www.clinicaltrialsregister.eu/ctr-search/trial/2010-023777-19/NL).

Perioperative Brain Injury in Relation to Early Neurodevelopment Among Children with Severe Congenital Heart Disease: Results from a European Collaboration.

OBJECTIVE: To examine the relationship between perioperative brain injury and neurodevelopment during early childhood in patients with severe congenital heart disease (CHD). STUDY DESIGN: One hundred and seventy children with CHD and born at term who required cardiopulmonary bypass surgery in the first 6 weeks after birth were recruited from 3 European centers and underwent preoperative and postoperative brain MRIs. Uniform description of imaging findings was performed and an overall brain injury score was created, based on the sum of the worst preoperative or postoperative brain injury subscores. Motor and cognitive outcomes were assessed with the Bayley Scales of Infant and Toddler Development Third Edition at 12 to 30 months of age. The relationship between brain injury score and clinical outcome was assessed using multiple linear regression analysis, adjusting for CHD severity, length of hospital stay (LOS), socioeconomic status (SES), and age at follow-up. RESULTS: Neither the overall brain injury score nor any of the brain injury subscores correlated with motor or cognitive outcome. The number of preoperative white matter lesions was significantly associated with gross motor outcome after correction for multiple testing (P = .013, ß = -0.50). SES was independently associated with cognitive outcome (P < .001, ß = 0.26), and LOS with motor outcome (P < .001, ß = -0.35). CONCLUSION: Preoperative white matter lesions appear to be the most predictive MRI marker for adverse early childhood gross motor outcome in this large European cohort of infants with severe CHD. LOS as a marker of disease severity, and SES influence outcome and future intervention trials need to address these risk factors.

Detecting Asymmetry of Upper Limb Activity with Accelerometry in Infants at Risk for Unilateral Spastic Cerebral Palsy.

AIMS: To examine whether accelerometry can quantitate asymmetry of upper limb activity in infants aged 3-12 months at risk for developing unilateral spastic cerebral palsy (USCP). METHOD: A prospective study was performed in 50 infants with unilateral perinatal brain injury at high risk of developing USCP. Triaxial accelerometers were worn on the ipsilateral and contralesional upper limb during the Hand Assessment for Infants (HAI). Infants were grouped in three age intervals (3-5 months, 5-7.5 months and 7.5 until 12 months). Each age interval group was divided in a group with and without asymmetrical hand function based on HAI cutoff values suggestive of USCP. RESULTS: In a total of 82 assessments, the asymmetry index for mean upper limb activity was higher in infants with asymmetrical hand function compared to infants with symmetrical hand function in all three age groups (ranging from 41 to 51% versus - 2-6%, p < 0.01), while the total activity of both upper limbs did not differ. CONCLUSIONS: Upper limb accelerometry can identify asymmetrical hand function in the upper limbs in infants with unilateral perinatal brain injury from 3 months onwards and is complementary to the Hand Assessment for Infants.

Machine Learning-Derived Active Sleep as an Early Predictor of White Matter Development in Preterm Infants.

White matter dysmaturation is commonly seen in preterm infants admitted to the neonatal intensive care unit (NICU). Animal research has shown that active sleep is essential for early brain plasticity. This study aimed to determine the potential of active sleep as an early predictor for subsequent white matter development in preterm infants. Using heart and respiratory rates routinely monitored in the NICU, we developed a machine learning-based automated sleep stage classifier in a cohort of 25 preterm infants (12 females). The automated classifier was subsequently applied to a study cohort of 58 preterm infants (31 females) to extract active sleep percentage over 5-7 consecutive days during 29-32 weeks of postmenstrual age. Each of the 58 infants underwent high-quality T2-weighted magnetic resonance brain imaging at term-equivalent age, which was used to measure the total white matter volume. The association between active sleep percentage and white matter volume was examined using a multiple linear regression model adjusted for potential confounders. Using the automated classifier with a superior sleep classification performance [mean area under the receiver operating characteristic curve (AUROC) = 0.87, 95% CI 0.83-0.92], we found that a higher active sleep percentage during the preterm period was significantly associated with an increased white matter volume at term-equivalent age [ß = 0.31, 95% CI 0.09-0.53, false discovery rate (FDR)-adjusted p-value = 0.021]. Our results extend the positive association between active sleep and early brain development found in animal research to human preterm infants and emphasize the potential benefit of sleep preservation in the NICU setting.

Cranial MRI beyond the Neonatal Period and Neurodevelopmental Outcomes in Neonatal Encephalopathy Due to Perinatal Asphyxia: A Systematic Review.

BACKGROUND: Magnetic resonance imaging (MRI) including diffusion-weighted imaging within seven days after birth is widely used to obtain prognostic information in neonatal encephalopathy (NE) following perinatal asphyxia. Later MRI could be useful for infants without a neonatal MRI or in the case of clinical concerns during follow-up. Therefore, this review evaluates the association between cranial MRI beyond the neonatal period and neurodevelopmental outcomes following NE. METHODS: A systematic literature search was performed using PubMed and Embase on cranial MRI between 2 and 24 months after birth and neurodevelopmental outcomes following NE due to perinatal asphyxia. Two independent researchers performed the study selection and risk of bias analysis. Results were separately described for MRI before and after 18 months. RESULTS: Twelve studies were included (high-quality n = 2, moderate-quality n = 6, low-quality n = 4). All reported on MRI at 2-18 months: seven studies demonstrated a significant association between the pattern and/or severity of injury and overall neurodevelopmental outcomes and three showed a significant association with motor outcome. There were insufficient data on non-motor outcomes and the association between MRI at 18-24 months and neurodevelopmental outcomes. CONCLUSIONS: Cranial MRI performed between 2 and 18 months after birth is associated with neurodevelopmental outcomes in NE following perinatal asphyxia. However, more data on the association with non-motor outcomes are needed.

Early qualitative and quantitative amplitude-integrated electroencephalogram and raw electroencephalogram for predicting long-term neurodevelopmental outcomes in extremely preterm infants in the Netherlands: a 10-year cohort study.

BACKGROUND: Extremely preterm infants (<28 weeks of gestation) are at great risk of long-term neurodevelopmental impairments. Early amplitude-integrated electroencephalogram (aEEG) accompanied by raw EEG traces (aEEG-EEG) has potential for predicting subsequent outcomes in preterm infants. We aimed to determine whether and which qualitative and quantitative aEEG-EEG features obtained within the first postnatal days predict neurodevelopmental outcomes in extremely preterm infants. METHODS: This study retrospectively analysed a cohort of extremely preterm infants (born before 28 weeks and 0 days of gestation) who underwent continuous two-channel aEEG-EEG monitoring during their first 3 postnatal days at Wilhelmina Children's Hospital, Utrecht, the Netherlands, between June 1, 2008, and Sept 30, 2018. Only infants who did not have genetic or metabolic diseases or major congenital malformations were eligible for inclusion. Features were extracted from preprocessed aEEG-EEG signals, comprising qualitative parameters grouped in three types (background pattern, sleep-wake cycling, and seizure activity) and quantitative metrics grouped in four categories (spectral content, amplitude, connectivity, and discontinuity). Machine learning-based regression and classification models were used to evaluate the predictive value of the extracted aEEG-EEG features for 13 outcomes, including cognitive, motor, and behavioural problem outcomes, at 2-3 years and 5-7 years. Potential confounders (gestational age at birth, maternal education, illness severity, morphine cumulative dose, the presence of severe brain injury, and the administration of antiseizure, sedative, or anaesthetic medications) were controlled for in all prediction analyses. FINDINGS: 369 infants were included and an extensive set of 339 aEEG-EEG features was extracted, comprising nine qualitative parameters and 330 quantitative metrics. The machine learning-based regression models showed significant but relatively weak predictive performance (ranging from r=0·13 to r=0·23) for nine of 13 outcomes. However, the machine learning-based classifiers exhibited acceptable performance in identifying infants with intellectual impairments from those with optimal outcomes at age 5-7 years, achieving balanced accuracies of 0·77 (95% CI 0·62-0·90; p=0·0020) for full-scale intelligence quotient score and 0·81 (0·65-0·96; p=0·0010) for verbal intelligence quotient score. Both classifiers maintained identical performance when solely using quantitative features, achieving balanced accuracies of 0·77 (95% CI 0·63-0·91; p=0·0030) for full-scale intelligence quotient score and 0·81 (0·65-0·96; p=0·0010) for verbal intelligence quotient score. INTERPRETATION: These findings highlight the potential benefits of using early postnatal aEEG-EEG features to automatically recognise extremely preterm infants with poor outcomes, facilitating the development of an interpretable prognostic tool that aids in decision making and therapy planning. FUNDING: European Commission Horizon 2020.

Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis.

BACKGROUND AND AIM: Preterm infants are prone to neonatal infections such as late-onset sepsis (LOS). The consequences of LOS can be severe and potentially life-threatening. Unfortunately, LOS often presents with unspecific symptoms, and early screening laboratory tests have limited diagnostic value and are often late. This study aimed to build a predictive algorithm to aid doctors in the early detection of LOS in very preterm infants. METHODS: In a retrospective cohort study, all consecutively admitted preterm infants (GA ≤ 32 weeks) from 2008 until 2019 were included. They were classified as LOS or control according to blood culture results, currently the gold standard. To generate features, routine and continuously measured oxygen saturation and heart rate data with a minute-by-minute sampling rate were extracted from electronic medical records. Care was taken not to include variables indicative of existing LOS suspicion. The timing of a positive blood culture served as a proxy for LOS-onset. An equivalent timestamp was generated in gestational-age-matched control patients without a positive blood culture. Three machine learning (ML) techniques (generalized additive models, logistic regression, and XGBoost) were used to build a classification algorithm. To simulate the performance of the algorithm in clinical practice, a simulation using multiple alarm thresholds was performed on hourly predictions for the total hospitalization period. RESULTS: 292 infants with LOS were matched to 1497 controls. The median gestational age before matching was 28.1 and 30.3 weeks, respectively. Evaluation of the overall discriminative power of the LR algorithm yielded an AUC of 0.73 (p < 0.05) at the moment of clinical suspicion (t = 0). In the longitudinal simulation, our algorithm detects LOS in at least 47% of the patients before clinical suspicion without exceeding the alarm fatigue threshold of 3 alarms per day. Furthermore, medical experts evaluated the algorithm as clinically relevant regarding the feature contributions in the model explanations. CONCLUSIONS: An ML algorithm was trained for the early detection of LOS. Performance was evaluated on both prediction horizons and in a clinical impact simulation. To the best of our knowledge, our assessment of clinical impact with a retrospective simulation on longitudinal data is the most extensive in the literature on LOS prediction to date. The clinically relevant algorithm, based on routinely collected data, can potentially accelerate clinical decisions in the early detection of LOS, even with limited inputs.

Brain injury and long-term outcome after neonatal surgery for non-cardiac congenital anomalies.

BACKGROUND: There is growing evidence that neonatal surgery for non-cardiac congenital anomalies (NCCAs) in the neonatal period adversely affects long-term neurodevelopmental outcome. However, less is known about acquired brain injury after surgery for NCCA and abnormal brain maturation leading to these impairments. METHODS: A systematic search was performed in PubMed, Embase, and The Cochrane Library on May 6, 2022 on brain injury and maturation abnormalities seen on magnetic resonance imaging (MRI) and its associations with neurodevelopment in neonates undergoing NCCA surgery the first month postpartum. Rayyan was used for article screening and ROBINS-I for risk of bias assessment. Data on the studies, infants, surgery, MRI, and outcome were extracted. RESULTS: Three eligible studies were included, reporting 197 infants. Brain injury was found in n = 120 (50%) patients after NCCA surgery. Sixty (30%) were diagnosed with white matter injury. Cortical folding was delayed in the majority of cases. Brain injury and delayed brain maturation was associated with a decrease in neurodevelopmental outcome at 2 years of age. CONCLUSIONS: Surgery for NCCA was associated with high risk of brain injury and delay in maturation leading to delay in neurocognitive and motor development. However, more research is recommended for strong conclusions in this group of patients. IMPACT: Brain injury was found in 50% of neonates who underwent NCCA surgery. NCCA surgery is associated with a delay in cortical folding. There is an important research gap regarding perioperative brain injury and NCCA surgery.