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

• Published in: Diagnostics (Basel) 2024-12, Vol.14 (24), p.2857
• Main Authors: Chiaruttini, Maria Vittoria, Lorenzoni, Giulia, Daverio, Marco, Marchetto, Luca, Izzo, Francesca, Chidini, Giovanna, Picconi, Enzo, Nettuno, Claudio, Zanonato, Elisa, Sagredini, Raffaella, Rossetti, Emanuele, Mondardini, Maria Cristina, Cecchetti, Corrado, Vitale, Pasquale, Alaimo, Nicola, Colosimo, Denise, Sacco, Francesco, Genoni, Giulia, Perrotta, Daniela, Micalizzi, Camilla, Moggia, Silvia, Chisari, Giosuè, Rulli, Immacolata, Wolfler, Andrea, Amigoni, Angela, Gregori, Dario
• Format: Article
• Language: English
• Subjects: Algorithms; Chronic illnesses; Failure; Generalized linear models; Hypoxia; Intensive care; Machine learning; Medical research; Medicine, Experimental; Missing data; Mortality; Neural networks; NIV; NIV failure; non-invasive ventilation; Ostomy; Pediatric intensive care; Pediatrics; PICU; Regression analysis; Respiratory failure; TIPNet; Ventilators
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics14242857

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.