An Artificial Intelligence Derived Blood Test to Diagnose Kawasaki Disease

Abstract

OBJECTIVE To develop a highly sensitive and specific blood biomarker panel that identifies febrile children with Kawasaki disease (KD). METHODS We tested blood samples from a single-center cohort of KD (n = 50) and control febrile children (n = 100) to develop a biomarker panel from 11 candidates selected by their assay clinical availability. We used machine learning with least absolute shrinkage and selection operator regression to identify 11 blood markers with values incorporated into a model, which provided a binary predictive risk score for KD determined with Youden’s index. We further reduced the model using least angle regression. RESULTS Using 10-fold cross-validation with least absolute shrinkage and selection operator regression on these 11 readouts plus patient age resulted in an area under the receiver operating characteristic curve of 0.94 (95% confidence interval [CI]: 0.90–0.98; P <.01). Using Youden’s index, which provided an optimal cut off for a binary predictive risk score, 88 of 97 KD-negative patients were diagnosed negative, and 47 of 50 KD-positive patients were positive, yielding a sensitivity of 0.94 (95% CI: 0.87–1.0) and specificity of 0.91 (95% CI: 0.85–0.96). Least angle regression reduced the final panel to 3 biomarkers: C-reactive protein, NT-proB-type natriuretic peptide, and thyroid hormone uptake. The predictive model then provided an area under the receiver operating characteristic curve of 0.92 (95% CI: 0.87–0.96; P <.001) along with sensitivity and specificity at 86% each. CONCLUSIONS Machine learning identified a highly accurate diagnostic model for KD. The reduced model employs 3 biomarkers currently approved by regulatory bodies and performed on platforms commonly used by certified diagnostic laboratories.