A Risk Prediction Model for the Development of Rheumatoid Arthritis, Sjögren's Syndrome, Systemic Sclerosis in...

Area of Science:

• Rheumatology and Immunology
• Predictive Modeling in Medicine
• Systemic Autoimmune Diseases

Background:

• Systemic lupus erythematosus (SLE) can co-occur with other autoimmune conditions, forming an overlapping syndrome (OS).
• Accurate risk assessment for OS in SLE patients is crucial for timely diagnosis and management.
• Existing methods for OS risk stratification in SLE may require enhancement.

Purpose of the Study:

• To construct and validate a predictive model for evaluating the risk of OS in patients with SLE.
• To identify key clinical and laboratory factors associated with OS development in SLE.
• To develop a risk nomogram for practical clinical application.

Main Methods:

• Development and validation of a predictive model using multicenter data from SLE patients (n=4714 in development, n=2271 in validation).
• Logistic regression modeling to identify predictive factors and construct a risk nomogram.
• Receiver operating characteristic (ROC) and calibration curve analysis to assess model performance.

Main Results:

• Key predictors identified include anti-SSA, anti-SSB antibodies, proteinuria, hematuria, age, eosinophil ratio, hematocrit, platelet count, bilirubin levels, rheumatoid factor, immunoglobulin A, prothrombin time, and ferritin.
• The model achieved an Area Under the Curve (AUC) of 0.874 in the training cohort, 0.877 in internal validation, and 0.760 in external validation.
• The nomogram demonstrated a significant predictive ability for OS risk in SLE patients.

Conclusions:

• The developed predictive model exhibits strong performance in identifying SLE patients at risk of developing overlapping syndromes.
• The model and associated nomogram are clinically valuable tools for risk assessment and management of OS in SLE.
• Further clinical utility studies are warranted to confirm the impact on patient outcomes.