LAUSR

Key Points Question Can machine learning help physicians differentiate patients with Kawasaki disease from other febrile patients in a pediatric emergency department using only objective laboratory tests? Findings In this diagnostic study that included 74 641 children with fever, the prediction model could identify Kawasaki disease with a sensitivity of 93% and a specificity of 97%. Meaning These results suggest that machine learning can help physicians differentiate patients with Kawasaki disease from other febrile patients in a pediatric emergency department without relying on subjective symptoms.