Short-term risk stratification using parallel admission and reassessment features in PICU patients with infection

1

A risk prediction model for short-term major adverse events in pediatric ICU patients with infections was developed using admission and early reassessment data.
2

The study analyzed 684 infection-related PICU admissions, focusing on events occurring within 72 hours post-admission.
3

Random forest modeling demonstrated the best performance, achieving AUC values of 0.724 in the internal test set and 0.718 in the validation cohort.
4

The model utilized features from both initial assessment and early reassessment to enhance risk stratification for critically ill children.
5

Further external validation and recalibration of the model are necessary before it can be widely applied in clinical settings.