# A nomogram for predicting the risk of persistent coronary artery aneurysms in children with Kawasaki disease: a retrospective study

## TL;DR

This study created a tool to predict which children with Kawasaki disease are likely to have long-lasting heart artery issues, helping doctors manage their care better.

## Contribution

A novel nomogram was developed using ZM, Age1, and TBA to predict persistent coronary artery aneurysms in Kawasaki disease patients.

## Key findings

- The nomogram achieved an optimism-corrected AUC of 0.933 for predicting persistent CAAs.
- Key predictors included maximum coronary artery Z-score, age under 12 months, and total bile acid levels.
- The model was well-calibrated and showed positive net benefit across a wide probability range.

## Abstract

To develop and validate a nomogram for the individualized prediction of persistent coronary artery aneurysms (CAAs) in children with Kawasaki disease (KD) who have developed CAAs in the acute phase.

This retrospective cohort study enrolled children diagnosed with KD and complicated by CAA between September 2015 and December 2023. The primary outcome was defined as the persistence of CAA 90 days after disease onset. Predictor selection was performed using 1,000 bootstrap resamples combined with LASSO regression for stability. A predictive model was constructed using multivariate logistic regression. The model's discrimination, calibration, and clinical utility were assessed by the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA).

A total of 135 children were included, of whom 80 (59.3%) had persistent CAAs. Stability selection identified the maximum coronary artery Z-score (ZM), age < 12 months (Age1), and total bile acid (TBA) as key predictors. The parsimonious model (Model B) built on these predictors demonstrated excellent performance, with an optimism-corrected AUC of 0.933 (95% CI: 0.905–0.960). It was well-calibrated, and DCA showed a positive net benefit across a wide threshold probability range of 5%–100%.

This study successfully developed a nomogram based on ZM, Age1, and TBA. This tool can effectively identify KD children at risk of persistent CAAs, providing an intuitive and quantitative decision-making aid for precise risk stratification and optimized long-term management in this high-risk population.