External Validation of a Machine Learning Model to Diagnose Kawasaki Disease
- PMID: 40122277
- DOI: 10.1016/j.jpeds.2025.114543
External Validation of a Machine Learning Model to Diagnose Kawasaki Disease
Abstract
We investigated the generalizability of a machine learning model trained to predict Kawasaki disease using laboratory and clinical data. The algorithm performed with >89% accuracy at 3 children's hospitals across the United States, demonstrating its potential as a physician support tool for diagnosing Kawasaki disease.
Keywords: Kawasaki disease; machine learning.
Copyright © 2025 The Authors. Published by Elsevier Inc. All rights reserved.
Conflict of interest statement
Declaration of Competing Interest This work was funded by a grant from the Gordon and Marilyn Macklin Foundation. All authors declare no conflict of interest.
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Medical
