Advertisement

Article not rated

Vol. 26 - Num. 102

Evidence based Pediatrics

Machine learning to identify febrile children at risk of Kawasaki disease

Manuel Molina Ariasa, Eduardo Ortega Páezb

aServicio de Gastroenterología. Hospital Infantil Universitario La Paz. Madrid. España.
bPediatra. UGC Góngora. Distrito Granada-Metropolitano. Granada. España.

Correspondence: M Molina. E-mail: mma1961@gmail.com

Reference of this article: Molina Arias M, Ortega Páez E. Machine learning to identify febrile children at risk of Kawasaki disease . Rev Pediatr Aten Primaria. 2024;26:209-12. https://doi.org/10.60147/8be904ad

Published in Internet: 24-06-2024 - Visits: 2336

Abstract

Authors´ conclusions: the study suggests that the results of objective laboratory tests have the potential to predict Kawasaki disease. Machine learning with XGBoost can help clinicians differentiate Kawasaki disease patients from other febrile patients in pediatric emergency departments with excellent sensitivity, specificity, and accuracy.

Reviewers´ commentary: although the model presented has power to identify patients at risk of Kawasaki disease, it must be externally validated in populations more similar to ours before its use can be recommended.

Keywords

Diagnostic techniques and procedures Machine learning Mucocutaneous lymph node syndrome

Note:

Este artículo se publica simultáneamente con la revista electrónica Evidencias en Pediatría (www.evidenciasenpediatria.es).

Comments

This article has no comments yet.