Gallstone Disease Prediction Model Results with 38 Features

Model results using CB classifier presents performance metrics for machine learning models predicting gallstone disease from tabular data. The dataset includes results from a CatBoost classifier and a Sea Lion Optimization Algorithm (SLOA)-optimized model, reporting mean accuracy, F1-score, precision, and recall from 5-fold cross-validation. It was authored by Prosenjit Das and last updated on 2026-06-01.

Use Cases

• Benchmarking classification model performance based on reported accuracy and F1-scores.
• Studying feature selection impact based on the reduction from 38 to 19 features mentioned.
• Analyzing model explainability techniques based on the application of SHAP, LIME, and DiCE.
• Investigating the influence of specific biomarkers like C-Reactive Protein (CRP) and Vitamin D on predictions.

Strengths

• Performance metrics are explicitly quantified, including a mean accuracy of 80.42% for the SLOA_CB model.
• Model evaluation includes multiple metrics (accuracy, F1-score, precision, recall) and uses 5-fold cross-validation.
• The dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.

Limitations

• The underlying patient data is not included; the dataset contains only model results and metrics.
• Row count and the specific 38 features are unknown, limiting reproducibility and direct application.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Prosenjit Das via figshare

Collection Method

Results from applying CatBoost and Sea Lion Optimization Algorithm to a publicly available tabular dataset for gallstone prediction.

Freshness

Last updated 2026-06-01 17:51:44; freshness should be verified.