Multicentre validation of a computer-based tool for differentiation of acute Kawasaki disease from clinically similar febrile illnesses. Issue 8 (5th March 2020)

• Record Type: Journal Article
• Authors: Hao, Shiying; Ling, Xuefeng B; Kanegaye, John T; Bainto, Emelia; Dominguez, Samuel R; Heizer, Heather; Jone, Pei-Ni; Anderson, Marsha S; Jaggi, Preeti; Baker, Annette; Son, Mary Beth; Newburger, Jane W; Ashouri, Negar; McElhinney, Doff B; Burns, Jane C; Whitin, John C; Cohen, Harvey J; Tremoulet, Adriana H
• Other Names: author non-byline.; Bryl Amy author non-byline.; Joelle Donofrio J. author non-byline.; Edwin-Enyenihi Arit author non-byline.; Gardiner Michael author non-byline.; Harley Jim R. author non-byline.; Lucio Simon J. author non-byline.; Nguyen Margaret author non-byline.; Schwartz Kristy author non-byline.; Shah Seema author non-byline.; Ulrich Stacey author non-byline.
• Is Part Of: Archives of disease in childhood. Volume 105:Issue 8(2020)
• Page Start: 772
• Page End: 777
• Publication Date: 2020-03-05
• Subjects: Kawasaki disease -- febrile controls -- algorithm -- multicenter study; Children -- Diseases -- Periodicals; Infants -- Diseases -- Periodicals; 618.920005
• DOI: 10.1136/archdischild-2019-317980
• Languages: English
• ISSNs: 0003-9888

Abstract

Abstract : Background: The clinical features of Kawasaki disease (KD) overlap with those of other paediatric febrile illnesses. A missed or delayed diagnosis increases the risk of coronary artery damage. Our computer algorithm for KD and febrile illness differentiation had a sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of 94.8%, 70.8%, 93.7% and 98.3%, respectively, in a single-centre validation study. We sought to determine the performance of this algorithm with febrile children from multiple institutions across the USA. Methods: We used our previously published 18-variable panel that includes illness day, the five KD clinical criteria and readily available laboratory values. We applied this two-step algorithm using a linear discriminant analysis-based clinical model followed by a random forest-based algorithm to a cohort of 1059 acute KD and 282 febrile control patients from five children's hospitals across the USA. Results: The algorithm correctly classified 970 of 1059 patients with KD and 163 of 282 febrile controls resulting in a sensitivity of 91.6%, specificity of 57.8% and PPV and NPV of 95.4% and 93.1%, respectively. The algorithm also correctly identified 218 of the 232 KD patients (94.0%) with abnormal echocardiograms. Interpretation: The expectation is that the predictive accuracy of the algorithm will be reduced in a real-world setting in which patients with KD are rare and febrile controls are common. However, the results of the current analysis suggest that this algorithm warrants a prospective, multicentre study to evaluate its potential utility as a physician support tool.