Machine learning identifies an immunological pattern associated with multiple juvenile idiopathic arthritis subtypes

• Published in: Annals of the rheumatic diseases Vol. 78; no. 5; pp. 617 - 628
• Main Authors: Van Nieuwenhove, Erika, Lagou, Vasiliki, Van Eyck, Lien, Dooley, James, Bodenhofer, Ulrich, Roca, Carlos, Vandebergh, Marijne, Goris, An, Humblet-Baron, Stéphanie, Wouters, Carine, Liston, Adrian
• Format: Journal Article
• Language: English
• Published: England BMJ Publishing Group Ltd and European League Against Rheumatism 01.05.2019; BMJ Publishing Group LTD
• Subjects: Adaptive Immunity - immunology; Adolescent; Arthritis; Arthritis, Juvenile - immunology; Artificial intelligence; autoimmune diseases; B cells; Case-Control Studies; Child; Child, Preschool; Children; Clinical medicine; Collagen; Cytokines; Data processing; Female; Flow Cytometry; Humans; Immune system; Immunology; Immunophenotyping - methods; Inflammation; Inflammatory diseases; Juvenile arthritis; juvenile idiopathic arthritis; Learning algorithms; Lymphocytes; Machine Learning; Male; Pathogenesis; Patients; Phenotyping; Rheumatic diseases; Rheumatoid arthritis; Rheumatology; T cells; autoimmune diseases; B cells; T cells; juvenile idiopathic arthritis
• ISSN: 0003-4967; 1468-2060
• DOI: 10.1136/annrheumdis-2018-214354

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