Application of a combined predictive model based on lung ultrasound score trajectory changes in deciding mechanical ventilator weaning for neonatal respiratory distress syndrome: a retrospective study

Back to news list

Source: Frontiers Medicine

Original: https://www.frontiersin.org/articles/10.3389/fmed.2026.1764757...

Published: 2026-03-11T00:00:00Z

A retrospective study included neonates with neonatal respiratory distress syndrome (NRDS) who were on mechanical ventilation from January 2020 to December 2024. Patients were divided into groups according to the success of extubation, where failure meant reintubation within 48 hours. The predictive model combined trajectory changes in lung ultrasound score (LUS), gestational age (GA), partial pressure of oxygen (PaO2) and oxygenation index (OI). Significant predictors were LUS-high (OR=24.099), LUS-medium (OR=6.675), PaO2 (OR=0.964) and OI (OR=1.409). The nomogram with these factors achieved an area under the curve (AUC) of 0.914, a good fit (Hosmer-Lemeshow p=0.624) and an excellent net benefit according to the decision curve. An internal validation cohort confirmed the reliability of the model. The model helps predict extubation outcomes, but requires external validation before clinical use.