Development of Biomarker Models to Predict Outcomes in Lupus Nephritis

Abstract

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.

Mapping urinary chemokines in human lupus nephritis: Potentially redundant pathways recruit CD4+ and CD8+ T cells and macrophages

“…Our own recently published data as well as other studies suggest that urinary CD4 + and CD8 + T‐cell counts outperform all of the examined urinary chemokine markers in discriminating acute proliferative LN from other SLE patients . Other studies found that individual biomarkers lack predictive power and instead suggest the use of combined low abundance biomarkers in panels .…”

Combined utilization of untimed single urine of MCP-1 and TWEAK as a potential indicator for proteinuria in lupus nephritis

“…Consequently, it is very difficult to achieve both high specificity and sensitivity simply using 1 analyte, due to the heterogeneity of the LN at presentation. [ 34 ] In addition, the present study showed that uTWEAK possessed high specificity to proteinuria, while uMCP-1 showed moderate sensitivity and specificity, indicating that the combined model may gather their advantages and enhance the assessment ability of proteinuria. Such hypothesis was verified by the fact that the combination resulted in the elevation of sensitivity to 76.7% and specificity to 88.9%, suggesting that the combination exceeded single utility of them.…”

Involvement of TWEAK and the NF-κB signaling pathway in lupus nephritis

“…In recent years, various studies have focused on the combination of SLE biomarkers and simple clinical indicators for improving the sensitivity and specificity of predictions regarding LN activity and disease progression (28,29). TWEAK is a novel member of the tumor necrosis factor ligand super family that is distributed in a range of organs, including the pancreas, heart, intestine, kidney, brain, ovaries, liver, spleen, lymph nodes and skeletal muscle (30).…”