Prevalence, management, health-care burden, and 90-day outcomes of prolonged mechanical ventilation in the paediatric intensive care unit (LongVentKids): an international, prospective, cross-sectional cohort study.

Background: The number of children requiring prolonged mechanical ventilation (PMV) has increased with the advancement of medical care. We aimed to estimate the prevalence of PMV worldwide, document demographic and clinical characteristics of children requiring PMV in paediatric intensive care units (PICUs), and to understand variation in clinical practice and health-care burden.

Methods: This international, multicentre, cross-sectional cohort study screened participating PICUs in 28 countries for children aged >37 postgestational weeks to 17 years who had been receiving mechanical ventilation (MV; invasive or non-invasive) for at least 14 consecutive days.

Hybrid Deep Learning-Based Enhanced Occlusion Segmentation in PICU Patient Monitoring.

Remote patient monitoring has emerged as a prominent non-invasive method, using digital technologies and computer vision (CV) to replace traditional invasive monitoring. While neonatal and pediatric departments embrace this approach, Pediatric Intensive Care Units (PICUs) face the challenge of occlusions hindering accurate image analysis and interpretation. In this study, we propose a hybrid approach to effectively segment common occlusions encountered in remote monitoring applications within PICUs.

Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies.

Background/objectives: This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors.

Methods: Tree-based models (TBMs) such as XGBoost, LightGBM, CatBoost, Random Forests (RFs), Voting Classifier ensembles, and sequential models (LSTM, GRU) were trained on the MIMIC-III and IV datasets. A preprocessing pipeline addressed missing data, class imbalances, and synthetic data flagged with masks.

Peak inspiratory pressure lacks accuracy to estimate plateau pressure in infants with severe obstructive lower airway disease.

Purpose: In children with acute respiratory distress syndrome receiving mechanical ventilation, the peak inspiratory pressure (PIP) is close to plateau pressure (P) when inspiratory flow approaches zero. We aimed to evaluate the reliability of PIP to estimate P in infants with severe respiratory viral infection (SRVI), characterized by increased airway resistance, and the accuracy of an equational model to estimates P (eP) based on PIP.

Methods: This was a retrospective observational study including mechanically ventilated children (1 to 24 month old) with SRVI, whose respiratory mechanics measurements were performed to evaluate PIP and P The measured P was compared with the result of the equation: eP = PIP - [5.