To develop and validate an early risk prediction model for short-term major adverse events (MAE) in pediatric intensive care unit (PICU) admissions with infection, emphasizing the clinical significance of MAE using admission (M0) and early reassessment (M1) features.
Key Findings:
Random forest (RF) model showed the most favorable performance with an AUC of 0.724 and PR-AUC of 0.741 in the internal test set, indicating its potential for clinical application.
Interpretation:
A parallel M0 + M1 framework demonstrated moderate discrimination for early risk stratification in infection-related PICU admissions, highlighting its clinical relevance.
Limitations:
Need for external validation and recalibration before broader application, emphasizing the impact on clinical applicability.
Conclusion:
The study suggests potential utility for reassessment-oriented early risk stratification in infection-related PICU admissions, underscoring its importance for clinical practice.
