ACR Meeting Abstracts

ACR Meeting Abstracts

  • Meetings
    • ACR Convergence 2024
    • ACR Convergence 2023
    • 2023 ACR/ARP PRSYM
    • ACR Convergence 2022
    • ACR Convergence 2021
    • ACR Convergence 2020
    • 2020 ACR/ARP PRSYM
    • 2019 ACR/ARP Annual Meeting
    • 2018-2009 Meetings
    • Download Abstracts
  • Keyword Index
  • Advanced Search
  • Your Favorites
    • Favorites
    • Login
    • View and print all favorites
    • Clear all your favorites
  • ACR Meetings

Abstract Number: 1669

Validation of a Machine Learning Lupus Nephritis Decision Support Tool to Predict Complete Response to Therapy

Bethany Wolf1, John Christian Spainhour1, John Arthur2, Michael Janech2, Michelle Petri3, Adnan Kiani4 and Jim Oates5,6, 1Public Health Sciences, Medical University of South Carolina, Charleston, SC, 2Medicine, Medical University of South Carolina, Charleston, SC, 3Johns Hopkins University School of Medicine, Baltimore, MD, 41830 E Monument St, Johns Hopkins University School of Medicine, Baltimore, MD, 5Medicine/Rheumatology & Immunology, Medical University of South Carolina, Charleston, SC, 6Medical Service, Ralph H. Johnson VAMC, Charleston, SC

Meeting: 2014 ACR/ARHP Annual Meeting

Keywords: Bioinformatics, biomarkers and lupus nephritis

  • Tweet
  • Click to email a link to a friend (Opens in new window) Email
  • Click to print (Opens in new window) Print
Session Information

Title: Systemic Lupus Erythematosus - Clinical Aspects and Treatment: Biomarker, Translational and Nephritis Studies

Session Type: Abstract Submissions (ACR)

Background/Purpose .

The American College of Rheumatology treatment guidelines for lupus nephritis (LN) recommend that induction therapy be changed when response to therapy has not occurred within six months. Response is not defined, and renal fibrosis can occur while waiting for this endpoint. Therefore, an early treatment decision support tool is needed. The goal of this project was to create and validate such a tool. Methods .

140 patients with active LN were recruited within 12 months of renal biopsy and prospectively evaluated for one year after start of induction therapy. Patients came from two prospective cohorts (the Hopkins cohort and the Medical University of SC) and two randomized controlled trials (the Lupus Nephritis Assessment of Rituximab (LUNAR) and the abatacept lupus nephritis trial). Renal biopsy International Society of Pathology/Renal Pathology Society (ISN/RPS) class, demographics, serum complement, anti-double stranded DNA antibody (dsDNA), and creatinine values, and urine protein/creatinine (traditional biomarkers, per Dall’Era and Wofsy Arthritis Care & Research 2011;63(3):351–357) and novel biomarker values were determined at 0 & 3 months. Seventeen novel biomarkers measured (see table) were based on those in an initial discovery set of 52 candidate biomarkers that were significantly different between groups or that showed promise in the literature. Patients were randomly assigned to training (n=99) and external validation (n=41) sets, stratifying for ISN/RPS class. Baseline and three-month traditional and novel biomarker, ISN/RPS class, treatment regimen, age, sex, and race were used to train random forest models predictive of one-year complete response (CR) to therapy. External validation sets were used to determine the performance of the trained one-year CR model. The process of randomization into training and validation sets and model training/validation was repeated 1000 times, and the median model results were reported. Results .

Several individual biomarkers were different between the two groups (P< 0.001). The resulting test of the LN Decision Support Tool (LNDST) demonstrated the clinically meaningful performance reported in Table I for both models, but the novel biomarker panel had superior specificity for cutpoints giving equal sensitivity.

Conclusion .

This study demonstrates the ability of the LNDST to predict CR. Implementation of LNDST may assist clinicians in following the ACR guidelines for treatment of LN.


Disclosure:

B. Wolf,
None;

J. C. Spainhour,
None;

J. Arthur,
None;

M. Janech,
None;

M. Petri,
None;

A. Kiani,
None;

J. Oates,
None.

  • Tweet
  • Click to email a link to a friend (Opens in new window) Email
  • Click to print (Opens in new window) Print

« Back to 2014 ACR/ARHP Annual Meeting

ACR Meeting Abstracts - https://acrabstracts.org/abstract/validation-of-a-machine-learning-lupus-nephritis-decision-support-tool-to-predict-complete-response-to-therapy/

Advanced Search

Your Favorites

You can save and print a list of your favorite abstracts during your browser session by clicking the “Favorite” button at the bottom of any abstract. View your favorites »

All abstracts accepted to ACR Convergence are under media embargo once the ACR has notified presenters of their abstract’s acceptance. They may be presented at other meetings or published as manuscripts after this time but should not be discussed in non-scholarly venues or outlets. The following embargo policies are strictly enforced by the ACR.

Accepted abstracts are made available to the public online in advance of the meeting and are published in a special online supplement of our scientific journal, Arthritis & Rheumatology. Information contained in those abstracts may not be released until the abstracts appear online. In an exception to the media embargo, academic institutions, private organizations, and companies with products whose value may be influenced by information contained in an abstract may issue a press release to coincide with the availability of an ACR abstract on the ACR website. However, the ACR continues to require that information that goes beyond that contained in the abstract (e.g., discussion of the abstract done as part of editorial news coverage) is under media embargo until 10:00 AM ET on November 14, 2024. Journalists with access to embargoed information cannot release articles or editorial news coverage before this time. Editorial news coverage is considered original articles/videos developed by employed journalists to report facts, commentary, and subject matter expert quotes in a narrative form using a variety of sources (e.g., research, announcements, press releases, events, etc.).

Violation of this policy may result in the abstract being withdrawn from the meeting and other measures deemed appropriate. Authors are responsible for notifying colleagues, institutions, communications firms, and all other stakeholders related to the development or promotion of the abstract about this policy. If you have questions about the ACR abstract embargo policy, please contact ACR abstracts staff at [email protected].

Wiley

  • Online Journal
  • Privacy Policy
  • Permissions Policies
  • Cookie Preferences

© Copyright 2025 American College of Rheumatology