Machine Learning-Based Prediction of 48-Hour Extubation Success in Mechanically Ventilated Children: A Single-Center Retrospective Cohort Study

Abstract

Highlights What are the main findings? In this retrospective cohort of 341 mechanically ventilated children, 298 (87.4%) achieved 48 h extubation success, while 43 (12.6%) experienced extubation failure. Random Forest showed the numerically highest internally cross-validated discrimination, with an AUC of 0.983 (95% CI, 0.971–0.993), while model-based analyses highlighted respiratory, metabolic, inflammatory, and neurological variables associated with extubation outcome. What are the implications of the main findings? Integrating routinely available multidimensional pre-extubation data may improve risk stratification beyond reliance on any single conventional weaning parameter. These findings should currently be regarded as internal proof-of-concept evidence and require prospective multicenter external validation before routine clinical implementation. Abstract Background: Accurate assessment of extubation readiness in mechanically ventilated children remains difficult because successful sustained breathing depends on the interaction of respiratory, metabolic, inflammatory, neurological, and cardiovascular factors. This study developed and internally validated machine-learning models for predicting 48 h extubation success using routinely available pre-extubation data. Methods: Of 1097 total PICU admissions, 341 mechanically ventilated children treated between 2021 and 2026 constituted the final analytic cohort. The primary outcome was survival without reintubation during the first 48 h after planned extubation. Demographic, clinical, laboratory, blood gas, illness severity, and ventilator variables were evaluated. Logistic Regression, Random Forest, Gradient Boosting, and Support Vector Machine models were assessed using stratified 5-fold cross-validation. Unsupervised k-means clustering was performed to identify physiological phenotypes. Results: Extubation was successful in 298 children (87.4%) and failed in 43 (12.6%). Failure was associated with higher oxygenation index, lactate, procalcitonin, C-reactive protein, PaCO2, pSOFA, PEEP, and rapid shallow breathing index, together with lower arterial pH, bicarbonate, ionized calcium, hemoglobin, albumin, sodium, and Glasgow Coma Scale scores. Random Forest yielded the numerically highest discrimination, with an AUC of 0.983 (95% CI, 0.971–0.993), a sensitivity of 0.980, a specificity of 0.814, an accuracy of 0.959, and a Brier score of 0.032. Arterial pH, the oxygenation index, bicarbonate, ionized calcium, procalcitonin, lactate, and PaCO2 showed the highest Random Forest Gini importance scores. Clustering identified a low-severity phenotype (n = 302; 97% success; 0% mortality) and a high-severity phenotype (n = 39; 10% success; 100% mortality). Conclusions: Multidimensional machine-learning models predicted 48 h pediatric extubation success with strong internal discrimination. Prospective multicenter external validation is required before clinical implementation.