ACR Meeting Abstracts

ACR Meeting Abstracts

  • Meeting Abstracts
    • All Meetings
    • ACR Convergence 2026
    • PRSYM 2026
    • ACR Convergence 2025
    • Download Abstract Supplements
  • Keyword Index
  • My Favorites
    • View & print my favorites
  • Search

Home » Meeting Abstracts » ACR Convergence 2024

Abstract Number: 1876

Automated Case Identification of Patients with End-Stage Renal Disease and Systemic Lupus Erythematosus Using Machine Learning

Mario Felix1 and Lais Osmani2, 1Yale, Hamden, CT, 2Yale, New Haven, CT

Share on X (Twitter) Share on Facebook Share on LinkedIn Share on Email
Print

Meeting: ACR Convergence 2024

Keywords: Lupus nephritis, socioeconomic factors, Systemic lupus erythematosus (SLE)

Session Information

Date: Monday, November 18, 2024

Title: Epidemiology & Public Health Poster III

Session Type: Poster Session C

Session Time: 10:30AM-12:30PM

Background/Purpose: Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease, with 4-28% of patients developing End-Stage Renal Disease (ESRD). Accurate identification of these patients is essential for research and resource allocation. Typically, case identification either involves using administrative claims or diagnostic code data or manual parsing through large datasets, which can be inaccurate and time-consuming. This study aims to develop a machine learning model to efficiently and accurately identify patients with SLE and ESRD from large datasets, and to evaluate the impact of incorporating social determinants of health (SDOH) data on model performance.

Methods: We utilized the NIH “All of Us” dataset, which includes diverse demographic and SDOH data, to create a cohort of patients with SLE. Clinical and SDOH features were used to build and evaluate machine learning models (Random Forest and XGBoost). The dataset was split into training (80%) and test (20%) sets. Model performance was assessed using accuracy, precision, recall, F1-score, and AUC. SHAP values were used to interpret model predictions.

Results: The study cohort included 1101 patients, with 65 having ESRD. XGBoost models outperformed Random Forest models, achieving AUCs of 0.93 (with SDOH) and 0.94 (without SDOH), compared to 0.92 (with SDOH) and 0.89 (without SDOH) for Random Forest. Incorporating SDOH data improved the precision and F1-scores of the XGBoost models. Feature Importance Rankings from XGBoost Model (w/ SDOH) indicated that SDOH variables, particularly those related to healthcare utilization and costs, were among the top 20 features influencing model predictions.

Conclusion: XGBoost models demonstrated superior performance in identifying patients with SLE and ESRD. The inclusion of SDOH data enhanced model precision and real-world interpretability. This study supports the feasibility of using machine learning for automated case identification in large datasets, although addressing class imbalance and model generalizability remains crucial for future work.

Supporting image 1

Classification report demonstrating performance metrics for XgBoost and Random Forest Models with and without incorporation of social determinants of health (SDOH) variables

Supporting image 2

ROC Curves comparing XGBoost and Random Forest models with and without SDOH virables

Supporting image 3

Feature Variable Importance Rankings of the XGBoost Models with and without SDOH variables


Disclosures: M. Felix: None; L. Osmani: None.

To cite this abstract in AMA style:

Felix M, Osmani L. Automated Case Identification of Patients with End-Stage Renal Disease and Systemic Lupus Erythematosus Using Machine Learning [abstract]. Arthritis Rheumatol. 2024; 76 (suppl 9). https://acrabstracts.org/abstract/automated-case-identification-of-patients-with-end-stage-renal-disease-and-systemic-lupus-erythematosus-using-machine-learning/. Accessed .

ACR Meeting Abstracts - https://acrabstracts.org/abstract/automated-case-identification-of-patients-with-end-stage-renal-disease-and-systemic-lupus-erythematosus-using-machine-learning/

My Favorites

Save and print abstracts during your browser session by clicking the “Favorite” button at the bottom of any abstract (must have cookies enabled in browser). See saved favorites.

Abstract Policies

  • ACR Convergence Abstract Embargo Policies
  • ACR Convergence Abstract Permissions & Reprints
  • PRSYM Abstract Policies

ACR Convergence. Where Rheumatology Meets

ACR Convergence 2026

Join us November 6-11 in Orlando, Florida.
See Registration Information

  • Contact ACR
  • Privacy Policy
  • ACR Policies
  • Cookie Preferences

© Copyright 2026 American College of Rheumatology