Ensemble Model Hyperparameter Grid for Clinical Disease Prediction

5.5 KB Excel file containing a hyperparameter grid for a unified deep learning framework evaluated on three clinical datasets. The framework, proposed by Vijay U. Rathod, integrates MLP, CNN, FT-Transformer, and autoencoder architectures and was last updated on 2026-05-08. It was tested on the UCI Heart Disease (303 samples), PIMA Diabetes (768 samples), and Parkinson's voice (195 samples) datasets.

Use Cases

• Benchmarking ensemble model performance based on the described framework architecture and nested cross-validation strategy.
• Hyperparameter tuning for clinical prediction models based on the provided grid search configurations.
• Developing dataset-aware model selection pipelines based on characteristics like feature dimensionality and class imbalance mentioned in the description.
• Reproducing the study's experimental results for heart disease, diabetes, and Parkinson's disease classification tasks.

Strengths

• Framework evaluated on three distinct benchmark datasets with specified sample sizes (303, 768, 195).
• Reported specific model performance metrics, such as an AUC of 0.8980 for heart disease prediction.
• Employs robust evaluation methods including fold-safe feature selection and nested cross-validation as described.

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating a limited scope focused on hyperparameter configurations rather than raw clinical data.
• Last updated 2026-05-08; freshness should be verified as it is a future date.

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 17:34:23