Clinical Data for Autoimmune Comorbidity Analysis in Ankylosing Spondylitis, 2012-2025

A multicenter, retrospective study collected clinical and laboratory data from three tertiary centers between 2012 and 2025. Jichong Zhu authored this dataset, which includes demographic characteristics, systemic inflammatory indices, hematological parameters, and liver and renal function markers. The data underpins an explainable machine learning framework for identifying autoimmune comorbidities in ankylosing spondylitis patients.

Use Cases

• Training ML models to distinguish ankylosing spondylitis alone from cases with autoimmune comorbidities based on demographic and laboratory markers.
• Developing interpretable classifiers for autoimmune diseases alone versus comorbid cases using features like metabolic and inflammatory indices.
• Analyzing the systemic inflammatory-metabolic phenotype associated with autoimmune comorbidity in AS using SHAP explanations.
• Benchmarking machine learning algorithms like LightGBM on clinical classification tasks with real-world, multicenter data.

Strengths

• Data originates from a multicenter study across three independent tertiary centers, potentially enhancing generalizability.
• Includes a range of routinely available clinical variables, such as demographic data, inflammatory indices, and organ function markers.
• The underlying research employed multiple evaluation metrics, including AUC, calibration, and clinical impact curves.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment for large-scale model training.
• The 11.8 KB file size suggests a very limited dataset, likely containing summary or model results rather than raw patient records.

Provenance

Source

figshare, author Jichong Zhu.

Collection Method

Multicenter, retrospective, cross-sectional study collecting clinical and laboratory data.

Time Range

Data collected between 2012 and 2025.

Freshness

Last updated 2026-03-18 07:40:05; freshness should be verified.

Geography

Data from three tertiary centers; specific geographic locations are unknown.