Background: We propose a modified lung ultrasound (LUS) score in neonates with respiratory distress syndrome (RDS), which includes posterior instead of lateral lung fields, and a 5-grade rating scale instead of a 4-grade rating scale. The purpose of this study was to evaluate the reproducibility of the rating scale and its correlation with blood oxygenation and to assess the ability of early post-birth scans to predict the mode of respiratory support on day of life 3 (DOL 3). As a secondary objective, the weight of posterior scans in the overall LUS score was assessed. Methods: We analyzed 619 serial lung scans performed in 70 preterm infants < 32 weeks gestation and birth weight < 1500 g. Assessments were performed within 24 h of birth (LUS₀) and on days 2, 3, 5, 7, 10, 14, 21 and 28. LUS scores were correlated with oxygen saturation over fraction of inspired oxygen (S/F) and mode of respiratory support. Interrater agreement was determined with the intraclass correlation coefficient (ICC) and Cronbach’s alpha. Probabilities of the need for various respiratory support modes on DOL 3 were assessed with ordinal logistic regression. Least square (ls) means of the posterior and anterior pulmonary field scores were compared. Results: The LUS score correlated significantly with S/F (Spearman rho = −0.635; p < 0.0001) and had excellent interrater agreement (ICC = 0.94, 95% CI 0.93–0.95; Cronbach’s alpha = 0.99). Significant predictors of ventilation requirements on DOL 3 were LUS₀ (p < 0.016) and birth weight (BW) (p < 0.001). In the ROC analysis, LUS₀ had high reliability in prognosing invasive ventilation on DOL 3 (AUC = 0.845 (95% DeLong CI: 0.738–0.951; p < 0.001)). Invasive ventilation was the most likely mode of respiratory support for LUS₀ scores: ≥7 (in infants with BW 900 g), ≥ 10 (in infants with BW 1050 g) and ≥ 15 (in infants with BW 1280 g). Posterior fields exhibited significantly higher average scores than anterior fields. Respective ls means (confidence levels) were 4.0 (3.8–4.1) vs. 2.2 (2.0–2.4); p < 0.001. Conclusions: Post-birth LUS predicts ventilation requirements on DOL 3. Scores of posterior pulmonary fields have a predominant weight in the overall LUS score.

Objective There is growing evidence for the usefulness of the lung ultrasound score (LUS) in neonatal intensive care. We evaluated whether the LUS is predictive of outcomes in infants with respiratory distress syndrome (RDS). Study Design Neonates less than 34 weeks of gestational age were eligible for this prospective, multicenter cohort study. The outcomes of interest were the need for mechanical ventilation (MV) at <72 hours of life, the need for surfactant (SF), successful weaning from continuous positive airway pressure (CPAP), extubation readiness, and bronchopulmonary dysplasia. Lung scans were taken at 0 to 6 hours of life (Day 1), on Days 2, 3, and 7, and before CPAP withdrawal or extubation. Sonograms were scored (range 0–16) by a blinded expert sonographer. The area under the receiver operating characteristic curve (AUC) was used to estimate the prediction accuracy of the LUS. Results A total of 647 scans were obtained from 155 newborns with a median gestational age of 32 weeks. On Day 1, a cutoff LUS of 6 had a sensitivity (Se) of 88% and a specificity (Sp) of 79% to predict the need for SF (AUC = 0.86), while a cutoff LUS of 7 predicted the need for MV at <72 hours of life (Se = 89%, Sp = 65%, AUC = 0.80). LUS acquired prior to weaning off CPAP was an excellent predictor of successful CPAP withdrawal, with a cutoff level of 1 (Se = 67%, Sp = 100%, AUC = 0.86). Conclusion The LUS has significant predictive ability for important outcomes in neonatal RDS. Key Points

This study aimed to assess interrater agreement in lung ultrasound scores (LUS) among neonatologists with varying experience levels and an expert sonographer. A post hoc analysis was conducted on data from a prospective multicenter study involving 155 infants born <34 weeks’ gestation, all with respiratory distress syndrome. A total of 629 lung scans were performed and video-recorded by 21 point-of-care sonographers, including both experienced (n = 7) and inexperienced (n = 14) evaluators. Subsequently, a blinded expert sonographer re-evaluated the assigned LUS values. The Cohen’s kappa statistic for individual pulmonary field assessments ranged from 0.89 to 0.93, indicating nearly perfect agreement. The interclass correlation coefficient (ICC) confirmed excellent reliability on total LUS values, demonstrating similar performance of experienced (ICC = 0.92, 95% CI 0.90–0.94) and inexperienced sonographers (ICC = 0.93, 95% CI 0.92–0.94). This study underscores that lung ultrasound is easily learned, and LUS exhibits outstanding reproducibility, irrespective of the sonographer’s level of experience.

Objective: Thrombosis is a common complication of umbilical artery catheterization. The purpose of this study was to compare the novel ultralow umbilical artery catheter position (catheter tip at the junction of the umbilical and internal iliac arteries) versus the conventional high umbilical artery catheter position (tip in the aorta, above the diaphragm) for the incidence of thrombosis. Study design: This study was conduct- ed in a nonacademic, tertiary-referral neonatal center. The insertion and placement of the umbilical artery catheter was performed under continuous ultrasound guidance. Serial ultrasound examinations were per- formed to identify thrombosis in 38 consecutive newborns with an umbilical artery catheter placed in the novel ultralow position. The control group consisted of 50 infants with an umbilical artery catheter placed in the standard position. Results: The incidence of thrombosis requiring anticoagulant treatment was 22% in neonates with an umbilical artery catheter in the standard position. No thrombosis was detected in those with an umbilical artery catheter placed in the ultralow position. The study and control groups had similar catheter indwelling times (mean, 8.2 ± 4.1 vs. 8.5 ± 4.0 days, p = 0.687). Conclusions: This is the first report to present a novel position for the placement of umbilical artery catheters. The preliminary findings for the novel ultralow umbilical artery catheter position indicate that it may provide a safety benefit over the conventional umbilical artery catheter position.

In this paper, we present the findings of a study focused on discovering process models and tracking their evolution over time. The research specifically targets a distinct category of these models known as behavioral patterns. Consequently, the challenges and techniques addressed here involve temporal data. To demonstrate the issues and methodologies associated with identifying process patterns and their changes, we use illustrative data from the treatment of respiratory failure in premature infants. The main achievement of the paper is to successfully model behavioral patterns using machine learning models and predict changes in a neonate’s state. That was justified by comparing the classifier’s sensitivity for cases of deterioration, improvement, and stability. Classification quality is best when the pattern remains constant. However, in the proposed model, when the pattern deteriorates, the classification quality decreases only slightly.

Severe pulmonary diseases, including atelectasis, pneumonia, and meconium aspiration syndrome, are major causes of neonatal respiratory distress, weaning difficulties, ventilator or oxygen dependence, prolonged oxygen requirements, extended hospitalization, and poor prognosis. The lack of simple and effective treatment strategies seriously endangers the survival and health of newborns, particularly premature infants. Recent advances in lung ultrasound (LUS) technology have made LUS-guided non-fiberobronchoscopic bronchoalveolar lavage (NFB-BAL) a promising solution. This approach addresses the limitations of conventional BAL in neonates by enabling accurate diagnosis, precise lesion localization, and dynamic procedural monitoring, hence reducing complications. Based on international expert consensus, these guidelines were developed to improve knowledge and promote the application of this technology and enhance operational standardization to ensure its effectiveness and safety. These guidelines contain 17 recommendations on 13 key clinical issues for reference and implementation in clinical practice. The wide application of these guidelines is expected to help significantly improve the prognosis of critically ill newborns with atelectatic pulmonary diseases.