Lung ultrasound (LU) and clinical parameters evaluated during the first postnatal hour potentially predict the length of CPAP therapy in newborns with respiratory distress. In a single-centre, prospective observational pilot study, 130 newborns ≥36 weeks gestational age were assessed using standardised LU at 30 and 60 min postnatally. Various clinical parameters were evaluated influencing CPAP duration (<1 vs. ≥1 h) using univariate and multivariate analyses. Lung ultrasound score >5, FiO2 > 0.21 and respiratory acidosis 30 min postnatally were associated with CPAP ≥1 h. Our model showed good diagnostic quality (ROC AUC = 0.87) and was confirmed by classification and regression tree (CART) analysis. Additional LU findings like double lung point and pleural line abnormalities were frequently observed, with good interrater reliability for LU interpretation (ICC = 0.76-0.77). Newborns with postnatal respiratory distress at risk for prolonged CPAP therapy can be identified based on specific LU and clinical parameters assessed 30 min postnatally. Despite the need for validation in an independent sample, these findings may lay the groundwork for a prediction tool. LU proved feasible and reliable for assessing respiratory status in this population, highlighting potential utility in clinical practice.