Summary of Proposed Instantiations: Benchmark Clinical Datasets for Disease Prediction

Vijay U. Rathod's study, last updated in May 2026, proposes a unified deep learning framework for disease prediction. The framework is evaluated on three benchmark datasets: the UCI Heart Disease dataset (303 samples, 13 features), the PIMA Indians Diabetes dataset (768 samples, 8 features), and a Parkinson's disease voice dataset (195 recordings, 22 features). The associated data file is a 5.5 KB Excel spreadsheet.

Use Cases

• Benchmarking deep learning models for heart disease prediction based on 13 clinical features.
• Evaluating model performance on diabetes classification using 8 metabolic features.
• Testing audio-based diagnostic models for Parkinson's disease detection using 22 acoustic features.
• Developing dataset-aware model selection strategies based on characteristics like sample size and feature dimensionality mentioned in the description.

Strengths

• Includes three established benchmark datasets with specific sample sizes: 303, 768, and 195.
• Provides concrete performance metrics for proposed models, such as an AUC of 0.8980 for heart disease prediction.
• The framework description incorporates robust evaluation methods like nested cross-validation and fold-safe feature selection.

Limitations

• The dataset is very small at 5.5 KB; the actual data content and row count are unknown.
• 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

Vijay U. Rathod via figshare.

Collection Method

Likely compiled from established public benchmark datasets (UCI, PIMA) for a research study.

Freshness

Last updated 2026-05-08 17:34:26; freshness should be verified.