To construct an exploratory machine learning-based model for early risk stratification to differentiate pediatric CNSI from FS using single-center retrospective data and to analyze key predictive factors.
Approach:
Study Design: Single-center, retrospective study involving children hospitalized with fever and convulsions between January 2023 and December 2025.
Key Findings:
Support Vector Machine achieved a high AUC of 0.864 (95% CI: 0.625–1.000) in the internal test set.
Interpretation:
The study developed a discriminative model for differentiating pediatric CNSI from FS using initial clinical variables, providing preliminary insights for early risk stratification.
Limitations:
The model's generalizability and clinical utility require further validation through multicenter prospective external studies.
Conclusion:
The model offers a preliminary reference for early risk stratification of CNSI in pediatric patients.
