Disease-associated and patient-specific immune cell signatures in juvenile-onset systemic lupus erythematosus: patient stratification using a machine-learning approach

Abstract

Background Juvenile-onset systemic lupus erythematosus (SLE) is a rare autoimmune rheumatic disease characterised by more severe disease manifestations, earlier damage accrual, and higher mortality than in adult-onset SLE. We aimed to use machine-learning approaches to characterise the immune cell profile of patients with juvenile-onset SLE and investigate links with the disease trajectory over time. Methods This study included patients who attended the University College London Hospital (London, UK) adolescent rheumatology service, had juvenile-onset SLE according to the 1997 American College of Rheumatology revised classification criteria for lupus or the 2012 Systemic Lupus International Collaborating Clinics criteria, and were diagnosed before 18 years of age. Blood donated by healthy age-matched and sex-matched volunteers who were taking part in educational events in the Centre for Adolescent Rheumatology Versus Arthritis at University College London (London, UK) was used as a control. Immunophenotyping profiles (28 immune cell subsets) of peripheral blood mononuclear cells from patients with juvenile-onset SLE and healthy controls were determined by flow cytometry. We used balanced random forest (BRF) and sparse partial least squares-discriminant analysis (sPLS-DA) to assess classification and parameter selection, and validation was by tenfold cross-validation. We used logistic regression to test the association between immune phenotypes and k-means clustering to determine patient stratification. Retrospective longitudinal clinical data, including disease activity and medication, were related to the immunological features identified. Findings Between Sept 5, 2012, and March 7, 2018, peripheral blood was collected from 67 patients with juvenile-onset SLE and 39 healthy controls. The median age was 19 years (IQR 13-25) for patients with juvenile-onset SLE and 18 years (16-25) for healthy controls. The BRF model discriminated patients with juvenile-onset SLE from healthy controls with 90•9% prediction accuracy. The top-ranked immunological features from the BRF model were confirmed using sPLS-DA and logistic regression, and included total CD4, total CD8, CD8 effector memory, and CD8 naive T cells, Bm1, and unswitched memory B cells, total CD14 monocytes, and invariant natural killer T cells. Using these markers patients were clustered into four distinct groups. Notably, CD8 T-cell subsets were important in driving patient stratification, whereas B-cell markers were similarly expressed across the cohort of patients with juvenile-onset SLE. Patients with juvenile-onset SLE and elevated CD8 effector memory T-cell frequencies had more persistently active disease over time, as assessed by the SLE disease activity index 2000, and this was associated with increased treatment with mycophenolate mofetil and an increased prevalence of lupus nephritis. Finally, network analysis confirmed the strong association between immune phenotype and differential clinical features. Interpretation Machine-learning models can define p...

Ecological and Socio-Economic Determinants of Livestock Animal Leptospirosis in the Russian Arctic

“…As a data-driven method, the Forest-based Classification and Regression tool performs better with large datasets [at least several hundred input analysis units according to the method guidance provided by the software producer (68), while in our study, we used 71 districts for model training and 151 districts for prediction]. However, some studies have reported successful implementation of this approach on relatively small datasets (69,70). Increased number of trees (1,000 in our study) allows reducing out-of-bag errors, which represent portions of data not participating in trees' construction.…”

Patients with Common Variable Immunodeficiency Complicated by Autoimmune Phenomena Have Lymphopenia and Reduced Treg, Th17, and NK Cells

“…In contrast to PID, immunophenotyping of B and T cells in SLE and other autoimmune diseases is mainly used in scientific research and clinical trials [ 27 ]. Therefore, physicians are not familiar with the interpretation and utility of lymphocyte subset counts in clinical practice.…”

The DNA methylation Profile of Undifferentiated Arthritis Patients Anticipates their Subsequent Differentiation to Rheumatoid Arthritis

“…In this sense, the use of high-throughput technologies has enabled the development of computational methods for the processing of patient omic data in search of novel and more precise conclusions [50–52]. For instance, the implementation of machine learning algorithms in high-dimensional data analysis has previously been used to improve stratification of patients [53–55] or to predict disease activity [56,57] in RA and SLE. In our study, we have used DNA methylation in addition to clinical data of UA patients by applying machine learning approaches, fine-tuning the prediction performance of previously existing classifiers [3] in an independent validation cohort.…”