Still's Disease Patient Data for Macrophage Activation Syndrome Prediction

A dataset of 737 patients with Still's disease from the GIRRCS AOSD Study Group and AIDA Network Still’s Disease Registry, used to explore machine learning techniques for predicting macrophage activation syndrome. The data includes patient age, sex, ferritin, C-reactive protein, systemic score, and MAS occurrence. The study was authored by Piero Ruscitti and last updated in April 2026.

Use Cases

• Training a binary classifier for macrophage activation syndrome (MAS) risk based on clinical variables like ferritin and CRP.
• Developing a decision tree or random forest model to identify key predictors of MAS in Still's disease.
• Creating a clinician-friendly risk stratification algorithm based on age, ferritin, CRP, and systemic score thresholds.
• Benchmarking imputation methods like random forest on clinical datasets with missing values.

Strengths

• Includes 737 patient records with specific demographic statistics (age: 35.5 ± 17.8, male sex: 44.7%).
• Provides concrete clinical thresholds for high-risk MAS probability (e.g., ferritin ≥ 4,178.10 ng/mL, CRP ≥ 27.15 mg/L).
• Data originates from two established multicenter clinical study groups, suggesting a structured collection process.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The primary data file is a 26.3 KB DOCX, which likely contains a summary or supplementary table rather than the full raw dataset.

Provenance

Source

Gruppo Italiano di Ricerca in Reumatologia Clinica e Sperimentale (GIRRCS) AOSD Study Group and AutoInflammatory Disease Alliance (AIDA) Network Still’s Disease Registry.

Collection Method

Multicenter, observational, prospective study.

Time Range

null

Freshness

Last updated 2026-04-14 05:39:23; freshness should be verified.

Geography

null