Table 3_Identifying the clinical signature of anti-centromere antibody-positive Sjögren’s

A multicenter cohort of 616 patients diagnosed with Sjögren's syndrome, comprising 81 anti-centromere antibody (ACA)-positive and 535 ACA-negative cases. The dataset was used to develop a machine learning model for identifying the clinical signature of ACA-positive SS, achieving an AUC of 0.811 in validation. It was authored by Wenlong Zhu and last updated in April 2026.

Use Cases

• Training a binary classifier to predict ACA-positive Sjögren's syndrome based on clinical and serological features.
• Analyzing feature importance and non-linear interactions (e.g., age and Raynaud's phenomenon) using SHAP analysis.
• Benchmarking machine learning models (like GBDT) on a clinical tabular dataset with a class imbalance.
• Studying the association between specific serological markers (anti-SSA/Ro52, anti-SSA/Ro60, anti-AMA-M2, anti-SSB, IgM) and a clinical autoimmune profile.

Strengths

• Contains data from 616 patients across multiple clinical centers.
• Includes a clear target variable with 81 positive and 535 negative cases for model development.
• Model performance is validated with a reported AUC of 0.811 (95% CI: 0.699–0.906).
• Key predictive features, such as age and specific antibodies, are identified and quantified via SHAP analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data table is unknown, which may limit suitability assessment.
• The dataset is very small at 11.9 KB, indicating limited scope or a summary of results rather than raw patient records.

Provenance

Source

figshare, author Wenlong Zhu.

Collection Method

Multicenter clinical study analyzing patient data.

Freshness

Last updated 2026-04-23 05:35:10; freshness should be verified.