Crohn's Disease Surgical Risk Stratification with Inflammatory and Coagulation Biomarkers

A clinical dataset of 1,060 patients with Crohn's disease used to develop machine learning models for surgical risk prediction. The gradient boosting machine model achieved a C-index of 0.816 and was used to assess the benefit of biologic therapy across risk strata. The dataset was authored by Kailing Xie and last updated on 2026-05-07.

Use Cases

• Predicting surgery-free survival in Crohn's disease patients based on inflammatory and coagulation biomarkers.
• Assessing the treatment benefit of biologic therapy across different risk strata using inverse probability weighting.
• Interpreting machine learning model decisions for clinical risk factors using SHAP analysis.
• Comparing the performance of different machine learning models (e.g., GBM vs. Cox) for clinical risk stratification.

Strengths

• Includes data from 1,060 patients with Crohn's disease.
• The best-performing gradient boosting machine model achieved a C-index of 0.816 and time-dependent AUC values up to 0.851.
• Model interpretability analysis showed inflammatory and coagulation markers contributed approximately 70% to model explainability.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The dataset is small in scale at 276.0 KB, indicating limited raw data or a summary document.

Provenance

Source

figshare, author Kailing Xie.

Collection Method

Data likely collected from a clinical cohort study of 1,060 patients; candidate predictors were selected using LASSO-Cox regression and the Boruta algorithm.

Freshness

Last updated 2026-05-07 04:45:23; freshness should be verified.