Development and internal validation of a serum ferritin-based prediction model for coronary artery aneurysms in Kawasaki disease

BACKGROUND: Kawasaki disease is the leading cause of acquired heart disease in children, and coronary artery aneurysms represent its most important cardiovascular complication. Identifying children at risk for coronary artery aneurysms at 4 to 8 weeks after disease onset is clinically important. Serum ferritin may reflect systemic inflammation in Kawasaki disease, but its incremental predictive value remains uncertain. This study developed a ferritin-based model for predicting coronary artery aneurysms at 4 to 8 weeks. METHODS: Patients with Kawasaki disease were retrospectively identified at a single centre and randomly divided into training and internal validation cohorts in a 6:4 ratio. Predictors were selected using least absolute shrinkage and selection operator regression and multivariable logistic regression. Model performance was assessed by discrimination, calibration, decision curve analysis, and reclassification metrics. RESULTS: score ≥ 2.5. Adding serum ferritin increased the area under the receiver operating characteristic curve from 0.853 to 0.899 in the training cohort and from 0.842 to 0.868 in the internal validation cohort, with good calibration, greater decision-curve net benefit, and improved risk reclassification. CONCLUSIONS: Serum ferritin provided incremental predictive value for coronary artery aneurysms at 4 to 8 weeks after the onset of Kawasaki disease. The ferritin-based model improved predictive performance in internal validation and warrants multicentre external validation to assess its generalisability and clinical applicability.