Characterization of immune cell profiles of innate and humoral immunity in patients with systemic lupus erythematosus through artificial intelligence

Systemic lupus erythematosus (SLE) features uncontrolled humoral immunity. However, the alterations in innate and humoral immune profiles remain unclear. This study assessed immune cell profile (ICP) changes in patients with SLE versus healthy controls (HCs). Blood samples from 18 patients with SLE and 21 HCs were analyzed. The analysis covered granulocytes, B cells, T lymphocytes, and regulatory cells. An AI model evaluated each subset’s role in distinguishing the groups. Patients with SLE showed increased effector memory and terminal effector CD4 + T cells, marginal zone B cells, and IgM hi B cells, but decreased memory, follicular, and IgM dim B cells, indicating an active primary humoral response. The AI model perfectly distinguished patients with SLE from HCs (precision, recall, AUC = 1.00). It identified five key predictive subsets: follicular, IgM hi , and IgM dim B cells; CTLA4 + PD-1 + in FoxP3 + CD4 + T reg cells; and effector memory CD8 + αβ T cells. This study identified a distinct ICP in patients with SLE, enhancing understanding of ICP dynamics in SLE pathogenesis.