Diabetes Classification Performance with AUC 0.8451 from PIMA Dataset

An AUC of 0.8451 (±0.0270) was achieved for diabetes classification using a CNN and autoencoder ensemble. This 5.5 KB Excel file contains results from a study proposing a unified deep learning framework evaluated on three benchmark clinical datasets. The framework was authored by Vijay U. Rathod and last updated on May 8, 2026.

Use Cases

• Benchmarking diabetes classification models based on the reported AUC performance metrics
• Evaluating deep learning ensemble strategies for clinical prediction tasks based on the described framework
• Studying model performance on heterogeneous biomedical datasets like the PIMA Indians Diabetes dataset mentioned in the description

Strengths

• Specific performance metrics are provided, such as an AUC of 0.8451 (±0.0270) for diabetes classification
• The study framework was evaluated on three distinct benchmark datasets, including the PIMA Indians Diabetes dataset with 768 samples
• Dataset is openly licensed under CC-BY-4.0

Limitations

• Row count is unknown, which may limit suitability assessment
• Column-level documentation is absent; field semantics must be inferred after download
• The 5.5 KB size suggests the file likely contains summary results or metadata, not the full underlying clinical data

Provenance

Source

figshare

Collection Method

Likely contains experimental results from a study proposing a deep learning framework for disease prediction.

Freshness

Last updated 2026-05-08 17:34:31; freshness should be verified