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.

We read the letter to the editor “B-lines score: artifacts as a sign of neonatal specific disease?” by Quarato et al. and we are pleased by the interest aroused by our article “Neonatal lung ultrasonography score after surfactant in preterm infants: A prospective observational study” published on your journal. This study included preterm neonates with respiratory distress syndrome (RDS), requiring non-invasive ventilation and surfactant. The aim of our citated study was to asses changes of a validated neonatal lung ultrasonography score (nLUS) after surfactant treatment. Our data demonstrate a lowering of the nLUS 2h and 12h after surfactant treatment. In their letter to the editor Quarato et al. expressed criticism about the nLUS score validation and about the utility of the Lung Ultrasound (LUS) as a diagnostic tool. They conclude that “LUS can be used only for diagnosing minimal pleural effusion and, at least, as complementary imaging, in addiction to chest radiographs (CR), for monitoring the reduction of subpleural pneumonitic consolidations under therapy”. Our citated study hasn’t focused on validation of the nLUS score or on LUS as a diagnostic tool for neonatal RDS, so we don’t get how Quarato’s concerns can be addressed to our paper. Nevertheless, finding the debate about nLUS or LUS in the neonatal field an occasion to promote an improving in the care of the preterm babies, we will discuss objections raised in Quadrato’s work, point by point.