Table 1_Identifying the clinical signature of anti-centromere antibody-positive Sjögren’s

Wenlong Zhu's dataset contains clinical data from a multicenter cohort of 616 patients diagnosed with Sjögren's syndrome, including 81 anti-centromere antibody (ACA)-positive and 535 ACA-negative cases. The data was used to develop and validate machine learning models for identifying the clinical signature of ACA-positive Sjögren's syndrome. The dataset was last updated on April 23, 2026.

Use Cases

• Training a binary classifier to predict ACA-positive Sjögren's syndrome based on clinical and serological features.
• Performing feature importance analysis to identify key predictors like anti-SSA/Ro52, age, and Raynaud's phenomenon.
• Investigating non-linear feature interactions, such as the synergy between Raynaud's phenomenon and advancing age, using SHAP analysis.

Strengths

• Data originates from a multicenter study with 616 patient records, providing a substantial clinical cohort.
• Includes a clear target variable with 81 ACA-positive cases for model training and validation.
• The underlying research achieved a robust model AUC of 0.811 in the validation cohort, suggesting predictive utility.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying analysis is known, but the exact number of rows and columns in the provided XLSX file is unknown.
• The dataset is very small at 11.9 KB, indicating limited scope, likely containing summary or model results rather than raw patient data.

Provenance

Source

Wenlong Zhu via figshare.

Collection Method

Clinical data collected from a multicenter cohort study of Sjögren's syndrome patients.

Freshness

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