Systemic lupus erythematosus (SLE) is a known risk factor for endothelial dysfunction. Murine and human lupus studies revealed a role for IFN-α in vascular abnormalities associated with impaired blood vessel dilation. However, the impact of IFN-α on mediators that induce vasodilation and modulate inflammation, including endothelial NO synthase (eNOS) and NO bioavailability, are unknown. The objectives of this study were to determine how IFN-α promotes endothelial dysfunction in SLE, focusing on its regulation of eNOS and NO production in endothelial cells. We demonstrate that IFN-α promotes an endothelial dysfunction signature in HUVECs that is characterized by transcription suppression and mRNA instability of eNOS complemented by upregulation of MCP1 and VCAM1. These changes are associated with IFN-inducible gene expression. IFN-α impairs insulin-mediated NO production, and altered gene expression resulted from eNOS instability, possibly due to enhanced miR-155 expression. IFN-α significantly impaired NO production in insulin-stimulated HUVECs. IFN-α treatment also led to enhanced neutrophil adhesion. Our study introduces a novel pathway by which IFN-α serves as a proatherogenic mediator through repression of eNOS-dependent pathways. This could promote the development of endothelial dysfunction and cardiovascular disease in SLE.

Identifying patients with certain clinical criteria based on manual chart review of doctors’ notes is a daunting task given the massive amounts of text notes in the electronic health records (EHR). This task can be automated using text classifiers based on Natural Language Processing (NLP) techniques along with pattern recognition machine learning (ML) algorithms. The aim of this research is to evaluate the performance of traditional classifiers for identifying patients with Systemic Lupus Erythematosus (SLE) in comparison with a newer Bayesian word vector method. We obtained clinical notes for patients with SLE diagnosis along with controls from the Rheumatology Clinic (662 total patients). Sparse bag-of-words (BOWs) and Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) matrices were produced using NLP pipelines. These matrices were subjected to several different NLP classifiers: neural networks, random forests, naïve Bayes, support vector machines, and Word2Vec inversion, a Bayesian inversion method. Performance was measured by calculating accuracy and area under the Receiver Operating Characteristic (ROC) curve (AUC) of a cross-validated (CV) set and a separate testing set. We calculated the accuracy of the ICD-9 billing codes as a baseline to be 90.00% with an AUC of 0.900, the shallow neural network with CUIs to be 92.10% with an AUC of 0.970, the random forest with BOWs to be 95.25% with an AUC of 0.994, the random forest with CUIs to be 95.00% with an AUC of 0.979, and the Word2Vec inversion to be 90.03% with an AUC of 0.905. Our results suggest that a shallow neural network with CUIs and random forests with both CUIs and BOWs are the best classifiers for this lupus phenotyping task. The Word2Vec inversion method failed to significantly beat the ICD-9 code classification, but yielded promising results. This method does not require explicit features and is more adaptable to non-binary classification tasks. The Word2Vec inversion is hypothesized to become more powerful with access to more data. Therefore, currently, the shallow neural networks and random forests are the desirable classifiers.

Objective: The American College of Rheumatology guidelines for the treatment of lupus nephritis recommend change in induction therapy when response to therapy has not occurred within 6 months. Response is not defined, and renal fibrosis can occur while waiting for this end point. Therefore, a decision support tool to better define response is needed to guide clinicians when starting patients on therapy. This study was undertaken to identify biomarker models with sufficient predictive power to develop such a tool.Methods: Urine samples from 140 patients with biopsy‐proven lupus nephritis who had not yet started induction therapy were analyzed for a panel of urinary biomarkers. Univariate receiver operating characteristic (ROC) curves were generated for each individual biomarker and compared to the ROC area under the curve values from machine learning models developed using random forest algorithms. Biomarker models of outcome developed with novel markers in addition to clinical markers were compared to those developed with traditional clinical markers alone.Results: Models developed with the combined traditional and novel biomarker panels demonstrated clinically meaningful predictive power. Markers most predictive of response were chemokines, cytokines, and markers of cellular damage.Conclusion: This is the first study to demonstrate the power of low‐abundance biomarker panels and machine learning algorithms for predicting lupus nephritis outcomes. This is a critical first step in research to develop clinically meaningful decision support tools.

Objective: Reactive intermediate production is an essential component of the innate immune response that is induced during disease activity in murine lupus. This study was undertaken to determine whether a marker of systemic nitric oxide (NO) production correlates with prospectively studied disease activity in human systemic lupus erythematosus (SLE) and lupus nephritis patients.Methods: Eighty‐three SLE patients and 40 control subjects were studied longitudinally. The SLE group included 23 patients with lupus nephritis documented by renal biopsy and 26 with a history of lupus nephritis. During each visit, following a 24‐hour low‐nitrate diet, traditional markers of disease activity and damage were determined. Serum nitrate plus nitrite (NOx) levels were determined by chemiluminescence detection.Results: NOx levels were higher in SLE patients than in controls during the first visit. In univariate longitudinal analyses, NOx levels were associated with SLE Disease Activity Index scores. In multivariate analyses, NOx levels were associated with serum levels of C3 and creatinine and the urinary protein:creatinine ratio. Among patients with lupus nephritis, those with proliferative lesions had higher NOx levels, and higher NOx levels were associated with accumulation of renal damage and lack of response to therapy.Conclusion: This is the first study to prospectively demonstrate longitudinal associations between serum NOx levels and markers of SLE and lupus nephritis disease activity. The more pronounced association with proliferative lupus nephritis and with longitudinal response to lupus nephritis therapy provides a rationale for the study of reactive intermediates as biomarkers of disease activity and therapeutic targets in proliferative lupus nephritis.