Cross-Validation Configurations for Three Clinical Benchmark Datasets

Vijay U. Rathod published a 5.5 KB Excel file on May 8, 2026, detailing cross-validation configurations for a proposed deep learning framework. The framework was evaluated on three benchmark datasets: the UCI Heart Disease dataset (303 samples), the PIMA Indians Diabetes dataset (768 samples), and a Parkinson's disease voice dataset (195 recordings). The study reports model performance metrics, including an AUC of 0.8980 for heart disease prediction.

Use Cases

• Benchmarking cross-validation strategies for clinical prediction models based on the described framework.
• Comparing deep learning model performance (e.g., MLP, CNN, FT-Transformer) on heterogeneous clinical datasets mentioned in the description.
• Reproducing the experimental setup for heart disease, diabetes, or Parkinson's disease prediction tasks detailed in the study.

Strengths

• Provides specific performance metrics for models, such as an AUC of 0.8980 for heart disease prediction.
• Documents the evaluation on three distinct clinical datasets with known sample sizes (303, 768, and 195).
• Released under a permissive CC-BY-4.0 license for open reuse.

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The 5.5 KB file size suggests the dataset contains configuration metadata rather than the primary clinical data itself, limiting its scope.
• Last updated 2026-05-08 17:34:25; freshness should be verified.

Provenance

Source

Vijay U. Rathod via figshare

Collection Method

Likely generated as part of a research study proposing a unified deep learning framework.

Freshness

Last updated 2026-05-08 17:34:25.