A Classification Tool for Differentiation of Kawasaki Disease from Other Febrile Illnesses - 25/08/16

Doi : 10.1016/j.jpeds.2016.05.060

Shiying Hao, PhD ¹, Bo Jin, MS ¹, Zhou Tan, PhD ¹, Zhen Li, BS ¹, Jun Ji, PhD ¹, Guang Hu, PhD ¹, Yue Wang, BS ¹, Xiaohong Deng, PhD ¹, John T. Kanegaye, MD ^2,³, Adriana H. Tremoulet, MD, MAS ^2,³, Jane C. Burns, MD ^2,³, Harvey J. Cohen, MD, PhD ⁴, Xuefeng B. Ling, PhD ^1,^⁎
on behalf of the
Pediatric Emergency Medicine Kawasaki Disease Research Group^{^∗}
List of additional members of the Pediatric Emergency Medicine Kawasaki Disease Research Group is available at www.jpeds.com (Appendix 1).
Lindsay T. Grubensky, RN, MSN, CPNP-PC, Jim R. Harley, MD, MPH, Paul Ishimine, MD, Jamie Lien, MD, Simon J. Lucio, MD, Seema Shah, MD, Stacey Ulrich, MD

¹ Department of Surgery, Stanford University, Stanford, CA
² Department of Pediatrics, University of California San Diego, La Jolla, CA
³ Rady Children's Hospital San Diego, San Diego, CA
⁴ Department of Pediatrics, Stanford University, Stanford, CA

^∗Reprint requests: Xuefeng B. Ling, PhD, Department of Surgery, Stanford University, Stanford, CA 94305.Department of SurgeryStanford UniversityStanfordCA94305

Abstract

Objective

To develop and validate a novel decision tree-based clinical algorithm to differentiate Kawasaki disease (KD) from other pediatric febrile illnesses that share common clinical characteristics.

Study design

Using clinical and laboratory data from 801 subjects with acute KD (533 for development, and 268 for validation) and 479 febrile control subjects (318 for development, and 161 for validation), we developed a stepwise KD diagnostic algorithm combining our previously developed linear discriminant analysis (LDA)–based model with a newly developed tree-based algorithm.

Results

The primary model (LDA) stratified the 1280 subjects into febrile controls (n = 276), indeterminate (n = 247), and KD (n = 757) subgroups. The subsequent model (decision trees) further classified the indeterminate group into febrile controls (n = 103) and KD (n = 58) subgroups, leaving only 29 of 801 KD (3.6%) and 57 of 479 febrile control (11.9%) subjects indeterminate. The 2-step algorithm had a sensitivity of 96.0% and a specificity of 78.5%, and correctly classified all subjects with KD who later developed coronary artery aneurysms.

Conclusion

The addition of a decision tree step increased sensitivity and specificity in the classification of subject with KD and febrile controls over our previously described LDA model. A multicenter trial is needed to prospectively determine its utility as a point of care diagnostic test for KD.

Le texte complet de cet article est disponible en PDF.

Keywords : incomplete KD, KD diagnosis, LDA, random forest, 2-step algorithm

Abbreviations : AHA, CRP, ED, KD, LAD, LDA, NPV, PPV, RCA

Plan

Multivariate Analysis and 2-Step Analyses of KD and Febrile Controls

Algorithm Performance in Subcohorts Stratified by Age, Illness Day, and CRP

Algorithm Performance for Subjects with Incomplete KD

Classification of KD with Coronary Artery Abnormalities

Erroneously Classified and Indeterminate Subjects

Impact of Variable Reduction in Algorithm Performance

Discussion

Supported by the American Heart Association (to H.C. and X.L.), Stanford University Spark Program (H.C. and X.L.), the David Gordon Louis Daniel Foundation (to J.B.), the Mario Batali Foundation (J.B.), the National Institutes of Health, National Heart, Lung, Blood Institute (HL69413 [to J.B.]), the Hartwell Foundation (to A.T.), and the Harold Amos Medical Faculty Development Program/Robert Wood Johnson Foundation (to A.T.). The authors declare no conflicts of interest.

Export

Vol 176

P. 114 - septembre 2016 Retour au numéro

Article précédent

50 Years Ago in The Journal of Pediatrics : Brain Scanning in Childhood
Paul Graham Fisher

| Article suivant

Sex Differences in Cardiometabolic Risk Factors among Hispanic/Latino Youth
Carmen R. Isasi, Christina M. Parrinello, Guadalupe X. Ayala, Alan M. Delamater, Krista M. Perreira, Martha L. Daviglus, John P. Elder, Ashley N. Marchante, Shrikant I. Bangdiwala, Linda Van Horn, Mercedes R. Carnethon

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 ?

connectez-vous ou créez un compte

A Classification Tool for Differentiation of Kawasaki Disease from Other Febrile Illnesses - 25/08/16

Abstract

Objective

Study design

Results

Conclusion

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL