Algorithm uses age, five signs of Kawasaki disease, and 17 laboratory measures
THURSDAY, Oct. 6, 2022 (HealthDay News) — A deep-learning algorithm called KIDMATCH can distinguish between multisystem inflammatory syndrome in children (MIS-C), Kawasaki disease, and other similar febrile illnesses in children, according to a study published in the October issue of The Lancet Digital Health.
Jonathan Y. Lam, from the University of California in San Diego, and colleagues developed and validated an artificial intelligence algorithm that can distinguish among MIS-C, Kawasaki disease, and other similar febrile illnesses and aid in the diagnosis of patients in the emergency department and acute care setting.
The researchers developed KIDMATCH to include patient age, the five classic clinical Kawasaki disease signs, and 17 laboratory measurements. KIDMATCH achieved a median area under the receiver operating characteristic curve during internal validation of 98.8 percent in the first stage and 96.0 percent in the second stage. During external validation, KIDMATCH correctly classified 76 of 81 patients with MIS-C (94 percent accuracy, two rejected by conformal prediction) from 14 hospitals in the CHARMS Study Group consortium, 47 of 49 patients (96 percent accuracy, one rejected by conformal prediction) from Boston Children’s Hospital, and 36 of 40 patients (90 percent accuracy, two rejected by conformal prediction) from Children’s National Hospital.
“KIDMATCH has the potential to aid front-line clinicians to distinguish between MIS-C, Kawasaki disease, and other similar febrile illnesses to allow prompt treatment and prevent severe complications,” the authors write.
Copyright © 2022 HealthDay. All rights reserved.
