Photo Credit: Barb Elkin

The following is a summary of “Machine learning-driven immunophenotypic stratification of mixed connective tissue disease corroborating the clinical heterogeneity,” published in the March 2024 issue of Rheumatology by Izuka et al.

Researchers conducted a retrospective study to categorize individuals diagnosed with mixed connective tissue disease (MCTD) according to their immunophenotypic profiles.

They examined the immunophenotype and transcriptome of 24 immune cell subsets in individuals diagnosed with MCTD, systemic lupus erythematosus (SLE), idiopathic inflammatory myopathy (IIM), and systemic sclerosis (SSc), utilizing data from their functional genome database, ImmuNexUT. Employing machine learning techniques such as Random Forest, MCTD patients were categorized using immunophenotyping data from SLE, IIM, and SSc patients. Transcriptomes were assessed through gene set variation analysis (GSVA), and clinical characteristics among MCTD subgroups were compared.

The results showed that among the 22 MCTD patients analyzed, 16 were classified as having the SLE-immunophenotype and 6 as having the non-SLE-immunophenotype using machine learning models originally constructed for SLE, IIM, and SSc patients based on immunophenotyping. Among MCTD patients, those with the SLE-immunophenotype exhibited higher proportions of Th1 cells [2.85% (IQR 1.54–3.91) vs. 1.33% (IQR 0.99–1.74) P=0.027] and plasmablasts [6.35% (IQR 4.17–17.49) vs 2.00% (IQR 1.20–2.80) P=0.010]. It was notable that patients with the SLE-immunophenotype also had a higher number of SLE-related symptoms [2.0 (IQR 1.0–2.0) vs. 1.0 (IQR1.0–1.0) P=0.038]. GSVA scores indicated that interferon-α and -γ responses were significantly higher in patients with the SLE-immunophenotype in central memory CD8⁺ T cells, while hedgehog signaling was higher in non-SLE-immunophenotype patients across 5 cell subsets.

Investigators concluded that immunophenotype analysis in this study revealed subgroups within MCTD patients, suggesting different underlying immune mechanisms for the disease’s various clinical presentations.

Source: academic.oup.com/rheumatology/advance-article/doi/10.1093/rheumatology/keae158/7628320