Table 2_Identifying the clinical signature of anti-centromere antibody-positive Sjögren’s

616 patient records from a multicenter study, comprising 81 anti-centromere antibody (ACA)-positive and 535 ACA-negative cases of Sjögren’s syndrome. The dataset was created by Wenlong Zhu and last updated in April 2026, and was used to develop a machine learning model for identifying the clinical signature of ACA-positive patients. The model achieved an AUC of 0.811 in the validation cohort.

Use Cases

• Training a classifier to predict anti-centromere antibody positivity in Sjögren's syndrome patients based on clinical and serological features.
• Analyzing the non-linear predictive contributions of features like age, Raynaud's phenomenon, and serological markers using SHAP analysis.
• Benchmarking machine learning models (e.g., GBDT, LASSO) on a clinical tabular dataset with a class imbalance.
• Investigating feature interactions, such as how the predictive value of Raynaud's phenomenon changes with patient age.

Strengths

• Includes data from 616 patients across multiple clinical centers.
• Provides a clear class split with 81 ACA-positive and 535 ACA-negative cases for model development.
• Model performance is validated with an AUC of 0.811 (95% CI: 0.699–0.906) on a hold-out set.
• Dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.

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 10.0 KB, indicating limited scope and likely a summary or model results rather than raw patient-level data.

Provenance

Source

Wenlong Zhu via figshare.

Collection Method

Multicenter clinical study analyzing patient data.

Freshness

Last updated 2026-04-23 05:35:07; freshness should be verified.