Article Text

Download PDFPDF
Machine learning identifies an immunological pattern associated with multiple juvenile idiopathic arthritis subtypes
  1. Erika Van Nieuwenhove1,2,3,
  2. Vasiliki Lagou2,3,4,
  3. Lien Van Eyck1,2,3,
  4. James Dooley2,3,
  5. Ulrich Bodenhofer5,6,7,
  6. Carlos Roca2,3,
  7. Marijne Vandebergh4,
  8. An Goris4,
  9. Stéphanie Humblet-Baron2,3,
  10. Carine Wouters1,3,
  11. Adrian Liston2,3,8
  1. 1 UZ Leuven, Leuven, Belgium
  2. 2 VIB Center for Brain and Disease Research, Leuven, Belgium
  3. 3 Department of Microbiology and Immunology, KU Leuven - University of Leuven, Leuven, Belgium
  4. 4 Department of Neurosciences, KU Leuven - University of Leuven, Leuven, Belgium
  5. 5 Institute of Bioinformatics, Linz, Austria
  6. 6 LIT AI Lab, Linz Institute of Technology, Johannes Kepler University, Linz, Austria
  7. 7 QUOMATIC.AI, Linz, Austria
  8. 8 The Babraham Institute, Cambridge, United Kingdom
  1. Correspondence to Dr Adrian Liston, Microbiology and Immunology, KU Leuven, Leuven 3000, Belgium; adrian.liston{at}babraham.ac.uk

Abstract

Objectives Juvenile idiopathic arthritis (JIA) is the most common class of childhood rheumatic diseases, with distinct disease subsets that may have diverging pathophysiological origins. Both adaptive and innate immune processes have been proposed as primary drivers, which may account for the observed clinical heterogeneity, but few high-depth studies have been performed.

Methods Here we profiled the adaptive immune system of 85 patients with JIA and 43 age-matched controls with indepth flow cytometry and machine learning approaches.

Results Immune profiling identified immunological changes in patients with JIA. This immune signature was shared across a broad spectrum of childhood inflammatory diseases. The immune signature was identified in clinically distinct subsets of JIA, but was accentuated in patients with systemic JIA and those patients with active disease. Despite the extensive overlap in the immunological spectrum exhibited by healthy children and patients with JIA, machine learning analysis of the data set proved capable of discriminating patients with JIA from healthy controls with ~90% accuracy.

Conclusions These results pave the way for large-scale immune phenotyping longitudinal studies of JIA. The ability to discriminate between patients with JIA and healthy individuals provides proof of principle for the use of machine learning to identify immune signatures that are predictive to treatment response group.

  • juvenile idiopathic arthritis
  • T cells
  • B cells
  • autoimmune diseases

Statistics from Altmetric.com

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Footnotes

  • CW and AL are joint senior authors.

  • EVN and VL contributed equally.

  • Handling editor Josef S Smolen

  • Contributors EVN, LVE and JD collected the data. VL, UB, CR, MV and AG analysed the data. SH-B, CW and AL supervised the study.

  • Funding This work was supported by the ERC Starting Grant IMMUNO. EVN, VL, LVE, MV and SH-B were supported by fellowships from the FWO.

  • Competing interests None declared.

  • Patient consent for publication Not required.

  • Ethics approval All individuals or their legal guardians gave written informed consent, and the study was approved by the Ethics Committee of the University Hospitals Leuven.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data sharing statement All data are included as an online supplementary data set.