EClinicalMedicine (Oct 2021)

Data-driven clustering identifies features distinguishing multisystem inflammatory syndrome from acute COVID-19 in children and adolescents

  • Alon Geva,
  • Manish M. Patel,
  • Margaret M. Newhams,
  • Cameron C. Young,
  • Mary Beth F. Son,
  • Michele Kong,
  • Aline B. Maddux,
  • Mark W. Hall,
  • Becky J. Riggs,
  • Aalok R. Singh,
  • John S. Giuliano,
  • Charlotte V. Hobbs,
  • Laura L. Loftis,
  • Gwenn E. McLaughlin,
  • Stephanie P. Schwartz,
  • Jennifer E. Schuster,
  • Christopher J. Babbitt,
  • Natasha B. Halasa,
  • Shira J. Gertz,
  • Sule Doymaz,
  • Janet R. Hume,
  • Tamara T. Bradford,
  • Katherine Irby,
  • Christopher L. Carroll,
  • John K. McGuire,
  • Keiko M. Tarquinio,
  • Courtney M. Rowan,
  • Elizabeth H. Mack,
  • Natalie Z. Cvijanovich,
  • Julie C. Fitzgerald,
  • Philip C. Spinella,
  • Mary A. Staat,
  • Katharine N. Clouser,
  • Vijaya L. Soma,
  • Heda Dapul,
  • Mia Maamari,
  • Cindy Bowens,
  • Kevin M. Havlin,
  • Peter M. Mourani,
  • Sabrina M. Heidemann,
  • Steven M. Horwitz,
  • Leora R. Feldstein,
  • Mark W. Tenforde,
  • Jane W. Newburger,
  • Kenneth D. Mandl,
  • Adrienne G. Randolph

Journal volume & issue
Vol. 40
p. 101112

Abstract

Read online

Background: Multisystem inflammatory syndrome in children (MIS-C) consensus criteria were designed for maximal sensitivity and therefore capture patients with acute COVID-19 pneumonia. Methods: We performed unsupervised clustering on data from 1,526 patients (684 labeled MIS-C by clinicians) <21 years old hospitalized with COVID-19-related illness admitted between 15 March 2020 and 31 December 2020. We compared prevalence of assigned MIS-C labels and clinical features among clusters, followed by recursive feature elimination to identify characteristics of potentially misclassified MIS-C-labeled patients. Findings: Of 94 clinical features tested, 46 were retained for clustering. Cluster 1 patients (N = 498; 92% labeled MIS-C) were mostly previously healthy (71%), with mean age 7·2 ± 0·4 years, predominant cardiovascular (77%) and/or mucocutaneous (82%) involvement, high inflammatory biomarkers, and mostly SARS-CoV-2 PCR negative (60%). Cluster 2 patients (N = 445; 27% labeled MIS-C) frequently had pre-existing conditions (79%, with 39% respiratory), were similarly 7·4 ± 2·1 years old, and commonly had chest radiograph infiltrates (79%) and positive PCR testing (90%). Cluster 3 patients (N = 583; 19% labeled MIS-C) were younger (2·8 ± 2·0 y), PCR positive (86%), with less inflammation. Radiographic findings of pulmonary infiltrates and positive SARS-CoV-2 PCR accurately distinguished cluster 2 MIS-C labeled patients from cluster 1 patients. Interpretation: Using a data driven, unsupervised approach, we identified features that cluster patients into a group with high likelihood of having MIS-C. Other features identified a cluster of patients more likely to have acute severe COVID-19 pulmonary disease, and patients in this cluster labeled by clinicians as MIS-C may be misclassified. These data driven phenotypes may help refine the diagnosis of MIS-C.

Keywords