Takeuchi M, et al. – The scientists intended to create a new risk assessment tool for intravenous immunoglobulin (IVIG) resistance using advanced statistical techniques. They introduced the random forest (RF) classifier to identify Kawasaki disease (KD) patients at high risk for IVIG resistance.

Methods

• For this study, data were retrospectively accumulated from KD patients receiving IVIG therapy, including demographic characteristics, signs and symptoms of KD and laboratory results.
• To these data, a random forest (RF) classifier, a tree–based machine learning technique was applied.
• The correlation between each variable and risk of IVIG resistance was evaluated.

Results

• From 767 patients with KD data were gathered, including 170 (22.1%) who were refractory to initial IVIG therapy.
• The predictive tool based on the RF algorithm had an area under the receiver operating characteristic curve of 0.916, a sensitivity of 79.7% and a specificity of 87.3%.
• Its misclassification rate in the general patient population was estimated to be 15.5%.
• RF also identified markers related to IVIG resistance such as abnormal liver markers and percentage neutrophils, displaying relationships between these markers and predicted risk.