Background: Critically ill neonates are at greater risk for adverse drug reactions (ADRs). The differentiation of ADRs from reactions associated with organ dysfunction/immaturity or genetic variability is difficult. Methods: In this prospective cohort study, each ADR was assessed using newborn-specific severity and probability scales by the clinical pharmacist. Subsequently, a machine learning-based risk score was designed to predict ADR presence in neonates. Results: In 98/412 (23.8%) of (56.3%; male) neonates included, 187 ADRs (0.42 ADR/patient) were determined related to 49 different drugs (37.12%). Drugs identified as high risk were enoxaparin, dexmedetomidine, vinblastine, dornase alfa, etoposide/carboplatin and prednisolone. The independent variables included in the risk score to predict ADR presence, according to the random forest importance criterion, were: systemic hormones (2 points), cardiovascular drugs (3 points), diseases of the circulatory system (1 point), nervous system drugs (1 point), and parenteral nutrition treatment (1 point), (cut-off value: 3 points). This risk score correctly classified 91.1% of the observations in the test set (c-index: 0.914). Conclusions: Using the high-performing risk score specific to neonates, it is expected that high-risk neonatal ADRs can be determined and prevented before they occur. Moreover, the awareness of clinicians of these drugs can be improved with this web-tool, and mitigation strategies (change of drug, dose, treatment duration, etc.) can be considered, based on a benefit-harm relationship for suspected drugs with a newborn-centered approach.

Hospitalized newborns have an increased risk of malnutrition and, especially preterm infants, often experience malnutrition-related extrauterine growth restriction (EUGR). The aim of this study was to predict the discharge weight and the presence of weight gain at discharge with machine learning (ML) algorithms. The demographic and clinical parameters were used to develop the models using fivefold cross-validation in the software-R with a neonatal nutritional screening tool (NNST). A total of 512 NICU patients were prospectively included in the study. Length of hospital stay (LOS), parenteral nutrition treatment (PN), postnatal age (PNA), surgery, and sodium were the most important variables in predicting the presence of weight gain at discharge with a random forest classification (AUROC:0.847). The AUROC of NNST-Plus, which was improved by adding LOS, PN, PNA, surgery, and sodium to NNST, increased by 16.5%. In addition, weight at admission, LOS, gestation-adjusted age at admission (> 40 weeks), sex, gestational age, birth weight, PNA, SGA, complications of labor and delivery, multiple birth, serum creatinine, and PN treatment were the most important variables in predicting discharge weight with an elastic net regression (R² = 0.748). This is the first study on the early prediction of EUGR with promising clinical performance based on ML algorithms. It is estimated that the incidence of EUGR can be improved with the implementation of this ML-based web tool (http://www.softmed.hacettepe.edu.tr/NEO-DEER/) in clinical practice.

Background: Hypoxic ischemic encephalopathy (HIE) is a significant cause of mortality and short- and long-term morbidities. Therapeutic hypothermia (TH) has been shown to be the standard care for HIE of infants ≥36 weeks gestational age (GA), as it has been demonstrated to reduce the rates of mortality, and adverse neurodevelopmental outcomes. This study aims to determine the incidence of HIE in our country, to assess the TH management in infants with HIE, and present short-term outcomes of these infants. Methods: The Turkish Hypoxic Ischemic Encephalopathy Online Registry database was established for this multicenter, prospective, observational, nationally-based cohort study to evaluate the data of infants born at ≥34 weeks GA who displayed evidence of neonatal encephalopathy (NE) between March, 2020 and April 2022. Results: The incidence of HIE among infants born at ≥36 weeks GA (n = 965) was 2.13 per 1000 live births (517:242440), and accounting for 1.55% (965:62062) of all neonatal intensive care unit admissions. The rates of mild, moderate and severe HİE were 25.5% (n = 246), 58.9% (n = 568), and 15.6% (n = 151), respectively. Infants with severe HIE had higher rates of abnormal magnetic resonance imaging (MRI) findings, and mortality (p<0.001). No significant difference in mortality and abnormal MRI results was found according to the time of TH initiation (6 h) (p>0.05). TH was administered to 85 (34.5%) infants with mild HIE, and of those born of 34–35 weeks of GA, 67.4% (n = 31) received TH. A total of 58 (6%) deaths were reported with a higher mortality rate in infants born at 34–35 weeks of GA (OR 3.941, 95% Cl 1.446–10.7422, p = 0.007). Conclusion: The incidence of HIE remained similar over time with a reduction in mortality rate. The timing of TH initiation, whether <3 or 3–6 h, did not result in lower occurrences of brain lesions on MRI or mortality. An increasing number of infants with mild HIE and late preterm infants with HIE are receiving TH; however, the indications for TH require further clarification. Longer follow-up studies are necessary for this vulnerable population.

Background. The use of non-invasive ventilation methods in neonatal intensive care units has been increasing in recent years. Non-invasive ventilation techniques are lung preserving methods and they reduce the risk of volutrauma, barotrauma, and atelectotrauma. Methods. The effect of heated humidified high-flow nasal cannula (HHHFNC), continuous positive airway pressure (CPAP), nasal intermittent positive-pressure ventilation (NIPPV), and nasal high-frequency oscillation ventilation (NHFOV) were compared in preterm infants with respiratory distress. Results. Between December 2015 and February 2017, a total of 76 preterm infants (gestational age < 32 weeks) with respiratory distress were enrolled in this study. Of the patients, 20 received HHHFNC, while 20 received nasal CPAP (NCPAP), 19 received NIPPV, and 17 received NHFOV for respiratory support. The primary outcome was intubation requirement during non-invasive respiratory support. The secondary outcome included duration of non-invasive ventilation, air leak syndrome, abdominal distension, intraventricular hemorrhage, necrotizing enterocolitis (NEC), nasal injury, increased secretions, agitation, and mortality rate. The intubation ratio was higher in the NCPAP (40%) and NHFOV (29.4%) groups when compared with the NIPPV (10.5%) and HHHFNC (11.8%) groups. More nasal injury had developed in the NIPPV (78.9%) and NHFOV (82.4%) groups when compared with the NCPAP (40%) and HHHFNC (35%) groups. Moreover, the viscous secretion that blocked the cannulas was higher in NIPPV (78.9%) and NHFOV (76.5%) groups than NCPAP (25%) and HHHFNC (40%) groups. There were no significant differences in the duration of non-invasive ventilation methods, abdominal distension, NEC, air leak syndrome or mortality in the 4 groups. Conclusions. The NIPPV and HHHFNC methods can be useful as a primary mode of respiratory support for respiratory distress. However, doctors need to be careful with regard to the complications that may develop.

Aims: Evidence for drug–drug interactions (DDIs) that may cause age-dependent differences in the incidence and severity of adverse drug reactions (ADRs) in newborns is sparse. We aimed to develop machine learning (ML) algorithms that predict DDI presence by integrating each DDI, which is objectively evaluated with the scales in a risk matrix (probability + severity). Methods: This double-center, prospective randomized cohort study included neonates admitted to the neonatal intensive care unit in a tertiary referral hospital during the 17-month study period. Drugs were classified by the Anatomical Therapeutic Chemical (ATC) classification and assessed for potential and clinically relevant DDIs to risk analyses with the Drug Interaction Probability Scale (DIPS, causal probability) and the Lexicomp^® DDI (severity) database. Results: A total of 412 neonates (median (interquartile range) gestational age of 37 (4) weeks) were included with 32,925 patient days, 131 different medications, and 11,908 medication orders. Overall, at least one potential DDI was observed in 125 (30.4%) of the patients (2.6 potential DDI/patient). A total of 38 of these 125 patients had clinically relevant DDIs causing adverse drug reactions (2.0 clinical DDI/patient). The vast majority of these DDIs (90.66%) were assessed to be at moderate risk. The performance of the ML algorithms that predicts of the presence of relevant DDI was as follows: accuracy 0.944 (95% CI 0.888–0.972), sensitivity 0.892 (95% CI 0.769–0.962), F1 score 0.904, and AUC 0.929 (95% CI 0.874–0.983). Conclusions: In clinical practice, it is expected that optimization in treatment can be achieved with the implementation of this high-performance web tool, created to predict DDIs before they occur with a newborn-centered approach.