Nomogram for predicting coronary artery lesions in patients with Kawasaki disease.

BACKGROUND

Coronary artery lesions are the most important complications of Kawasaki disease. Approximately 25-30% of untreated patients develop coronary artery disease, which can lead to long-term cardiovascular sequelae.

AIM

The aim of this study is to evaluate the risk factors for coronary artery lesions in Kawasaki disease and to construct a nomogram for predicting the likelihood of developing such lesions.

METHODS

Data from 599 patients between January 2012 and June 2020 were reviewed retrospectively. Patients were randomly assigned to the training set (n = 450) and the validation set (n = 149). A comparison of clinical features and laboratory data was performed, followed by multivariate logistic regression analysis to identify independent risk factors and develop the nomogram. The predictive efficiency of the nomogram was evaluated using the calibration curve, area under the receiver operating characteristic curve (AUC), C-index, and decision curve analysis (DCA).

RESULTS

Intravenous immunoglobulin (IVIG) resistance, delayed IVIG treatment, C-reactive protein, and neutrophil/lymphocyte ratio were identified as independent risk factors for the development of coronary artery lesions. The nomogram was constructed based on these four variables. The calibration curve of the nomogram showed a high degree of agreement between the predicted probability and the actual probability. The AUC of the nomogram in the training and validation set was 0.790 and 0.711, respectively. In addition, DCA revealed that the nomogram provided a significant net benefit, further supporting its clinical utility.

CONCLUSIONS

The constructed nomogram demonstrates a strong and reliable performance in predicting coronary artery lesions, which enables clinicians to make timely and tailored clinical decisions.