External Validation of a Machine Learning Model to Diagnose Kawasaki Disease - 09/06/25
Doi : 10.1016/j.jpeds.2025.114543
Jonathan Y. Lam, PhD 1, Chisato Shimizu, MD 2, Michael A. Gardiner, MD 2, Thomas Giorgio, MS 3, Veronique Wright, BS 3, Annette Baker, MSN 3, Marsha S. Anderson, MD 4, Heather Heizer, PA 5, Sindhu Mohandas, MD 6, Alicia Kazarians, NP 7, Kelli Kaneta, MD 8, Pei-Ni Jone, MD 9, Samuel R. Dominguez, MD, PhD 4, Jacqueline R. Szmuszkovicz, MD 10, Jane W. Newburger, MD 3, Adriana H. Tremoulet, MD 2, Jane C. Burns, MD 2, ⁎ 
1 Department of Biomedical Informatics, University of California San Diego, La Jolla, CA
2 Department of Pediatrics, Rady Children's Hospital and University of California San Diego, San Diego, CA
3 Department of Cardiology, Boston Children's Hospital, Boston, MA
4 Department of Pediatrics, Children's Hospital Colorado and University of Colorado School of Medicine, Aurora, CO
5 Department of Pediatric Infectious Diseases, Oklahoma Children's Hospital and University of Oklahoma Health Science Center, Oklahoma City, OK
6 Division of Infectious Disease, Children's Hospital Los Angeles and Keck School of Medicine of the University of Southern California, Los Angeles, CA
7 Division of Cardiology, Children's Hospital Los Angeles, Los Angeles, CA
8 Division of Nephrology, Children's Hospital Los Angeles, Los Angeles, CA
9 Department of Pediatrics, Ann & Robert H. Lurie Children's Hospital of Chicago, Northwestern University Feinberg School of Medicine, Chicago, IL
10 Division of Cardiology, Children's Hospital Los Angeles and Keck School of Medicine of the University of Southern California, Los Angeles, CA
∗Reprint requests: Jane C. Burns, MD, Department of Pediatrics, University of California San Diego, 9500 Gilman Dr, La Jolla, CA 92093.Department of PediatricsUniversity of California San Diego9500 Gilman DrLa JollaCA92093
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.
Le texte complet de cet article est disponible en PDF.Keywords : Kawasaki disease, machine learning
Abbreviations : AUC, ED, FC, KD, MIS-C
Plan
© 2025
The Authors. Publié par Elsevier Masson SAS. Tous droits réservés.
Vol 282
Article 114543- juillet 2025 Retour au numéro
Article précédent
- Metabolic and Bariatric Surgery Utilization in the Era of Glucagon-Like Peptide-1 Receptor Agonists among Adolescents versus Adults
- Sarah E. Messiah, Deepali K. Ernest, Folefac D. Atem, Faisal G. Qureshi, M. Sunil Mathew, Jackson M. Francis, Alicia Wheelington, Marlyn A. Allicock, Bethany R. Cartwright, Benjamin E. Schneider, Nestor de la Cruz-Muñoz, Steven E. Lipshultz, Ildiko Lingvay, Jaime P. Almandoz, Sarah E. Barlow
- Implementation of Rapid Whole Genome Sequencing in Pediatric Acute Care is Associated with Positive Shifts in Health Care Professionals’ Perspectives Toward Testing
- Andrea Scheurer-Monaghan, Joseph D. Fakhoury, Caleb P. Bupp, Melissa A. Hicks, Danielle Nolan, Jessica Omark O'Shea, Thomas J. Hoffmann, Renée Mehra, Linda S. Franck
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?