Search

BackgroundThe aim of this study is to develop survival analysis models of hospitalized systemic lupus erythematosus (h-SLE) patients in Jiangsu province using data mining techniques to predict patient survival outcomes and survival status.MethodsIn this study, based on 1999–2009 survival data of 2453 hospitalized SLE (h-SLE) patients in Jiangsu Province, we not only used the Cox proportional hazards model to analyze patients’ survival factors, but also used neural network models to predict survival outcomes. We used semi-supervised learning to label the censored data and introduced cost-sensitivity to achieve data augmentation, addressing category imbalance and pseudo label credibility. In addition, the risk score model was developed by logistic regression.ResultsThe overall accuracy of the survival outcome prediction model exceeded 0.7, and the sensitivity was close to 0.8, and through the comparative analysis of multiple indicators, our model outperformed traditional classifiers. The developed survival risk assessment model based on logistic regression found that there was a clear threshold, i.e., a survival threshold indicating the survival risk of patients, and cardiopulmonary and neuropsychiatric involvement, abnormal blood urea nitrogen levels and alanine aminotransferase level had the greatest impact on patient survival time. In addition, the study developed a graphical user interface (GUI) integrating survival analysis models to assist physicians in diagnosis and treatment.ConclusionsThe proposed survival analysis scheme identifies disease-related pathogenic and prognosis factors, and has the potential to improve the effectiveness of clinical interventions.

Systemic lupus erythematosus (SLE) is characterized by the production of pathogenic autoantibodies. Ribonuclease A family member 2 (RNase2) is known to have antiviral activity and immunomodulatory function. Although RNASE2 level has been reported to be elevated in SLE patients based on mRNA microarray detection, its pathologic mechanism remains unclear. Here, we confirmed that RNASE2 was highly expressed in PBMCs from SLE patients and associated with the proportion of CD11c+T-bet+ B cells, a class of autoreactive B cells also known as age-associated B cells (ABCs). We showed that reduction of RNASE2 expression by small interfering RNA led to the decrease of ABCs in vitro, accompanied by total IgG and IL-10 reduction. In addition, we demonstrated that both RNASE2 and IL-10 in peripheral blood of lupus patients were mainly derived from monocytes. RNASE2 silencing in monocytes down-regulated IL-10 production and consequently reduced ABCs numbers in monocyte-B cell co-cultures, which could be restored by the addition of recombinant IL-10. Based on above findings, we concluded that RNASE2 might induce the production of ABCs via IL-10 secreted from monocytes, thus contributing to the pathogenesis of SLE.

Systemic lupus erythematosus (SLE) patients exist an imbalance between regulatory T (Treg) and T helper 17 cells (Th17), which might be contributed by defective immune regulation of bone marrow derived mesenchymal stem cells (BM-MSCs) from SLE patients. Our microRNA array analysis showed markedly down-regulated expression levels of microRNA let-7f in BM-MSCs from SLE patients compared to those from normal controls (NOR). To explore the role of let-7f in the disease pathogenesis, we showed that expression levels of let-7f in SLE BM-MSCs were negatively associated with SLE disease activity, and the predicted let-7 family targeted gene expression of interlukin-6 (IL-6) was significantly higher in BM-MSCs from SLE patients compared to normal controls (NOR). Transient transfection of BM-MSCs with let-7f mimics or inhibitors showed reduced levels of let-7f impaired the proliferation rate of BM-MSCs, BM-MSC-mediated downregulation of Th17 cells and upregulation of Treg cells, increased the apoptosis rate of BM-MSCs through targeting IL-6 and activating signal transducers and activators of transcription-3 (STAT3) pathway, but had no significant effect on the differentiation of Th1 and Th2. Our findings showed a key role of let-7f in the imbalance of Treg/Th17 mediated by SLE BM-MSCs, suggesting the potential of manipulating let-7f expression in BM-MSCs for treating SLE patients.