Deep learning approaches for automated classification of neonatal lung ultrasound with assessment of human-to-AI interrater agreement.

Neonatal respiratory disorders pose significant challenges in clinical settings, often requiring rapid and accurate diagnostic solutions for effective management. Lung ultrasound (LUS) has emerged as a promising tool to evaluate respiratory conditions in neonates. This evaluation is mainly based on the interpretation of visual patterns (horizontal artifacts, vertical artifacts, and consolidations).

Lung function response to postnatal corticosteroids for the prevention and treatment of bronchopulmonary dysplasia.

Background: Steroid treatment is well-known for producing clinically significant improvements in respiratory support requirements. In this study, we utilized lung ultrasound and respiratory oscillometry to objectively assess this response and determine if the combination of these methods can serve as a valuable tool for comparing different treatment strategies.

Methods: We conducted a retrospective observational study including preterm infants with a gestational age below 32 weeks and/or a birth weight below 1500 g.

Early respiratory system reactance predicts respiratory outcomes in preterm infants: a retrospective, multicentre study.

Background: This multicentre, international, retrospective study aimed to investigate whether respiratory system reactance ( ) assessed by respiratory oscillometry on day 7 of life is associated with respiratory outcomes in preterm infants below 32 weeks gestational age (GA).

Methods: Sinusoidal pressure oscillations (2-5 cmHO peak-to-peak, 10 Hz) were superimposed on the positive end-expiratory pressure. We assessed the association of z-score with the duration of respiratory support using linear regression and with bronchopulmonary dysplasia (BPD) using logistic regression.

A Novel CPAP Device With an Integrated Oxygen Concentrator for Low Resource Countries: In Vitro Validation and Usability Test in Field.

To develop and validatea novel neonatal non-invasive respiratory support device prototype designed to operate in low-resource settings. The device integrates a blower-based ventilator and a portable oxygen concentrator. A novel control algorithm was designed to achieve the desired fraction of inspired oxygen (FiO) while minimizing power consumption.