Indications for Non-Invasive Ventilation in Respiratory Failure

Non-Invasive Ventilation Failure in Pediatric ICU: A Machine Learning Driven Prediction

Background/Objectives: Non-invasive ventilation (NIV) has emerged as a possible first-step treatment to avoid invasive intubation in pediatric intensive care units (PICUs) due to its advantages in reducing intubation-associated risks. However, the timely identification of NIV failure is crucial to prevent adverse outcomes. This study aims to identify predictors of first-attempt NIV failure in PICU patients by testing various machine learning techniques and comparing their predictive abilities. Methods: Data were sourced from the TIPNet registry, which comprised patients admitted to 23 Italian Paediatric Intensive Care Units (PICUs). We selected patients between January 2010 and January 2024 who received non-invasive ventilation (NIV) as their initial approach to respiratory support. The study aimed to develop a predictive model for NIV failure, selecting the best Machine Learning technique, including Generalized Linear Models, Random Forest, Extreme Gradient Boosting, and Neural Networks. Additionally, an ensemble approach was implemented. Model performances were measured using sensitivity, specificity, AUROC, and predictive values. Moreover, the model calibration was evaluated. Results: Out of 43,794 records, 1861 admissions met the inclusion criteria, with 678 complete cases and 97 NIV failures. The RF model demonstrated the highest AUROC and sensitivity equal to 0.83 (0.64, 0.94). Base excess, weight, age, systolic blood pressure, and fraction of inspired oxygen were identified as the most predictive features. A check for model calibration ensured the model's reliability in predicting NIV failure probabilities. Conclusions: This study identified highly sensitive models for predicting NIV failure in PICU patients, with RF as a robust option.

Comfort During Non-invasive Ventilation

Non-invasive ventilation (NIV) has been shown to be effective in avoiding intubation and improving survival in patients with acute hypoxemic respiratory failure (ARF) when compared to conventional oxygen therapy. However, NIV is associated with high failure rates due, in most cases, to patient discomfort. Therefore, increasing attention has been paid to all those interventions aimed at enhancing patient's tolerance to NIV. Several practical aspects have been considered to improve patient adaptation. In particular, the choice of the interface and the ventilatory setting adopted for NIV play a key role in the success of respiratory assistance. Among the different NIV interfaces, tolerance is poorest for the nasal and oronasal masks, while helmet appears to be better tolerated, resulting in longer use and lower NIV failure rates. The choice of fixing system also significantly affects patient comfort due to pain and possible pressure ulcers related to the device. The ventilatory setting adopted for NIV is associated with varying degrees of patient comfort: patients are more comfortable with pressure-support ventilation (PSV) than controlled ventilation. Furthermore, the use of electrical activity of the diaphragm (EADi)-driven ventilation has been demonstrated to improve patient comfort when compared to PSV, while reducing neural drive and effort. If non-pharmacological remedies fail, sedation can be employed to improve patient's tolerance to NIV. Sedation facilitates ventilation, reduces anxiety, promotes sleep, and modulates physiological responses to stress. Judicious use of sedation may be an option to increase the chances of success in some patients at risk for intubation because of NIV intolerance consequent to pain, discomfort, claustrophobia, or agitation. During the Coronavirus Disease-19 (COVID-19) pandemic, NIV has been extensively employed to face off the massive request for ventilatory assistance. Prone positioning in non-intubated awake COVID-19 patients may improve oxygenation, reduce work of breathing, and, possibly, prevent intubation. Despite these advantages, maintaining prone position can be particularly challenging because poor comfort has been described as the main cause of prone position discontinuation. In conclusion, comfort is one of the major determinants of NIV success. All the strategies aimed to increase comfort during NIV should be pursued.