ObjectiveTo assess changes in neonatal lung ultrasonography score (nLUS) after surfactant administration in preterm infants with respiratory distress syndrome (RDS).Working HypothesisThe reduction of nLUS score before (nLUSpre), 2 hours (nLUS2h), and 12 hours (nLUS12h) after surfactant administration to identify patients who will not need a second treatment.Study Design and SettingProspective observational study in the tertiary neonatal intensive care unit.Patients SelectionForty‐six preterm neonates with RDS of 32 weeks median gestational age (IQR 30‐33) and mean birth weight of 1650 ± 715 g.MethodologyLung ultrasonography was performed before, 2 hours, and 12 hours after surfactant administration in preterm infants with RDS needing surfactant treatment. Resulting nLUS was analyzed.ResultsThe Wilcoxon signed‐rank test demonstrated an nLUS lowering after 2 hours (P < .001) and 12 hours (P < .001) from surfactant administration. Sixteen newborns required surfactant retreatment with median gestational age of 32 weeks (IQR 29‐33) and mean birth weight of 1519 ± 506 g.The receiver operating characteristic analysis for the nLUS2h yielded an area under the curve of 0.80 (95% confidence interval, 0.76‐0.85; P < .001). A nLUS2h ≥7 showed a sensitivity of 94% and a specificity of 60% for needing a second treatment with surfactant.ConclusionsIn preterm infants with RDS requiring surfactant treatment, nLUS evaluated 2 hours after surfactant administration can be used to identify patients who will not need a second treatment.

BackgroundArtificial intelligence (AI) is a promising field in the neonatal field. We focused on lung ultrasound (LU), a useful tool for the neonatologist. Our aim was to train a neural network to create a model able to interpret LU.MethodsOur multicentric, prospective study included newborns with gestational age (GA) ≥ 33 + 0 weeks with early tachypnea/dyspnea/oxygen requirements. For each baby, three LU were performed: within 3 h of life (T0), at 4–6 h of life (T1), and in the absence of respiratory support (T2). Each scan was processed to extract the region of interest used to train a neural network to classify it according to the LU score (LUS). We assessed sensitivity, specificity, positive and negative predictive value of the AI model's scores in predicting the need for respiratory assistance with nasal continuous positive airway pressure and for surfactant, compared to an already studied and established LUS.ResultsWe enrolled 62 newborns (GA = 36 ± 2 weeks). In the prediction of the need for CPAP, we found a cutoff of 6 (at T0) and 5 (at T1) for both the neonatal lung ultrasound score (nLUS) and AI score (AUROC 0.88 for T0 AI model, 0.80 for T1 AI model). For the outcome “need for surfactant therapy”, results in terms of area under receiver operator characteristic (AUROC) are 0.84 for T0 AI model and 0.89 for T1 AI model. In the prediction of surfactant therapy, we found a cutoff of 9 for both scores at T0, at T1 the nLUS cutoff was 6, while the AI's one was 5. Classification accuracy was good both at the image and class levels.ConclusionsThis is, to our knowledge, the first attempt to use an AI model to interpret early neonatal LUS and can be extremely useful for neonatologists in the clinical setting.

Background Artificial intelligence (AI) is a promising field in the neonatal field.  We focused on lung ultrasound (LUS), a useful tool for the neonatologist. Our aim was to train a neural network to create a model able to interpret LUS. Methods Our multicentric, prospective study included newborns with gestational age (GA) ≥ 33+0 weeks with early tachypnea/dyspnea/oxygen requirements. For each baby, three LUS were performed: within 3 hours of life (T0), at 4–6 hours of life (T1) and in the absence of respiratory support (T2). Each scan was processed to extract ROI used to train a neural network to classify it according to the LUS score. We assessed sensitivity, specificity, positive and negative predictive value of the AI model’s scores in predicting the need for respiratory assistance with nasal Continuous Positive Airway Pressure (nCPAP) and for surfactant, compared to the “classical” scores. Results We enrolled 62 newborns (GA=36±2 weeks). In the prediction of the need for CPAP, we found a cut-off of 6 (at T0) and 5 (at T1) for both the classical nLUS and AI score. In the prediction of surfactant therapy we found a cut-off of 9 for both scores at T0, at T1 the nLUS cut-off was 6, while the AI’s one was 5. Classification accuracy was good both at the image and classes level. Conclusions This is, to our knowledge, the first attempt to use an AI model to interpret early neonatal LUS and can be extremely useful for neonatologist in the clinical setting.

Objective Recently, a novel approach to imaging Superior Vena Cava (SVC) flow has been presented, showing better repeatability and better agreement with MRI‐derived SVC flow measures. The objective was to establish normal values of SVC flow with the novel approach in the first 48 h of life. Study Design This was a prospective, observational study. All infants with gestational age (GA) less than 31 weeks were eligible. Echocardiographic evaluation was performed at 5, 12, 24, 48 h of postnatal life. A subgroup of uncomplicated infants was studied to define a normal range for SVC flow. Results Forty‐five infants were enrolled. We estimated normative values in a subgroup of 31 uncomplicated infants. The median SVC flow significantly increases from 83 ml/kg/min at 5 h of life to 153 ml/kg/min at 48 h (p < .001). Conclusion Using the novel approach we derived normal values of SVC flow in a cohort of uncomplicated preterm population at high risk for developing IVH.

No abstract