Skip to main content
ACR Convergence 2025 Main banner
Final Program


Schedule at a Glance
Legend
Presentation Icons
CME
CME
Non-CME
Non-CME
In Person
In Person
On Demand
On Demand
Live Stream
Live Stream
Active Learning
Active Learning
Choose Rheum
Choose Rheum
Emerging Investigator Awardee
Emerging Investigator Awardee

Poster Session

Systemic Lupus Erythematosus (SLE)

Poster Session B

Session: (1467–1516) Systemic Lupus Erythematosus – Diagnosis, Manifestations, & Outcomes Poster II

1478: Construction and Validation of a Prediction Model of Cognitive Dysfunction in Patients with Systemic Lupus Erythematosus

Monday, October 27, 2025
10:30 AM - 12:30 PM Central Time
Location: Hall F1
Binomial deviance vs. log(λ) and Coefficient paths for different variables

Nomogram for predicting cognitive impairment in SLE patients incorporating age, Anti-SSB,SDI,anxiety depression,TG and CK-MB.

ROC curve for cognitive impairment prediction in the training cohort  (AUC: 0.887, cut-off value:0.571, sensitivity:0.821, specificity: 0.841, Youden index: 0.662) and validation cohort (AUC: 0.877, cut-off value: 0.526, sensitivity: 0.810, specificity: 0.846, Youden index: 0.656).

    Abstract Poster Presenter(s)

  • Bz

    Bin zhou, MD

    The First School of Clinical Medicine, Southern Medical University
    Guangzhou, Guangdong, China

    Disclosure(s): No financial relationships with ineligible companies to disclose


Background/Purpose: Systemic lupus erythematosus (SLE) is a chronic autoimmune disease that affects multiple organs. Cognitive dysfunction (CD) is a common but often underestimated complication in SLE patients, seriously affecting their quality of life. The purpose of this study was to analyze the clinical data of SLE patients, screen effective predictors, and construct and validate a prediction model for the early identification of cognitive impairment in SLE patients.

Methods: The training cohort included 100 SLE patients. Baseline characteristics, clinical data, and laboratory and imaging data during hospitalization were screened using least absolute shrinkage and selection operator (LASSO) and logistic regression to construct a predictive risk score. The derived score represents an estimate of the risk of developing cognitive dysfunction in patients with SLE. A nomogram was constructed, and its accuracy and predictive performance were evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and clinical decision curves. For the validation cohort, data were prospectively collected from 47 SLE patients.

Results: Six important predictors were screened out by LASSO regression: age, SDI, anxiety and depression, creatine kinase isoenzymes(CK-MB), triglycerides (TG), and anti-SSB antibodies, and a prediction model nomogram for SLE-CD was constructed. In the training cohort, the AUC of the model was 0.887 (critical value: 0.571, sensitivity: 0.821, specificity: 0.841, Youden index: 0.662). In the validation cohort, the AUC of the model was 0.877 (critical value: 0.526, sensitivity: 0.810, specificity: 0.846, Youden index: 0.656). The calibration curve showed that the predicted probability was highly consistent with the actual observed value, and the clinical decision curve suggested that the model had clinical application value within a wide range of thresholds.

Conclusion: The constructed SLE-CD prediction model showed good predictive efficacy in the training and validation cohorts and has potential clinical application value.