Interoperable Models for Identifying Critically Ill Children at Risk of Neurologic Morbidity.

Area of Science:

• Pediatric Critical Care Medicine
• Neuroscience
• Artificial Intelligence in Healthcare

Background:

• Decreased pediatric critical care mortality shifts focus to neurodevelopmental outcomes.
• Early identification of neurologic morbidity is crucial for timely interventions.
• Developing predictive models can enhance surveillance for at-risk children.

Purpose of the Study:

• To develop machine-learning models to identify acquired neurologic morbidity in critically ill children.
• To assess the correlation between these models and serum-based brain injury biomarkers.
• To improve neurodevelopmental potential preservation in pediatric intensive care.

Main Methods:

• A prognostic study utilizing data from two quaternary pediatric intensive care units (development and external validation).
• Machine learning models (extreme gradient boosted) were developed and validated.
• Neurologic morbidity was the primary outcome, defined by composite criteria or neurocritical care consultation.
• Correlation with serum biomarkers (glial fibrillary acidic protein) was assessed.

Main Results:

• A generalizable model achieved an F1 score of 0.37 and AUC of 0.81 at the validation site.
• The number needed to alert was 4, with a Brier score of 0.04 after recalibration.
• Serum glial fibrillary acidic protein levels showed significant correlation with model predictions (rs=0.34, P=.007).

Conclusions:

• The study demonstrates a well-performing machine learning model for predicting neurologic morbidity in critically ill children.
• Biomolecular corroboration supports the model's clinical relevance.
• Further prospective validation and refinement of these biomarker-coupled risk models are warranted.