NCR-EBRB: Diabetes Prediction Data for Clinical Diagnostic Models

Shucheng Feng's dataset supports an Extended Belief Rule Base model for diabetes prediction and diagnosis. The dataset is 5.5 KB in size, stored in XLS format, and was last updated on 2026-05-05. It was created to address challenges in clinical diagnostic processes, including patient heterogeneity and the need for explainable models.

Use Cases

• Training diagnostic models based on key clinical features selected via feature importance evaluation.
• Testing rule reduction and activation strategies for efficient model inference.
• Optimizing rule-based model parameters to improve diagnostic accuracy and robustness.
• Benchmarking predictive performance of models handling complex and diverse patient parameters.

Strengths

• Dataset is licensed under CC-BY-4.0, permitting open sharing and adaptation.
• The associated research methodology is described in detail, including feature selection with XGBoost and model optimization with P-CMA-ES.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Shucheng Feng

Collection Method

Likely contains clinical or simulated data used to construct and validate the NCR-EBRB prediction model.

Freshness

Last updated 2026-05-05 17:30:34; freshness should be verified.