Patient Classification Scores for a Deep Learning Model and Six Physicians

9 classification scores from a deep learning model, generated from 3 validation folds and 3 random seeds, and 6 scores from 6 physicians. The dataset, authored by Ilhan Yoo and last updated on 2026-05-19, is a 5.5 KB XLS file containing comparative performance metrics.

Use Cases

• Benchmarking AI model performance against human clinicians based on the comparative scores.
• Analyzing variance in model predictions based on the scores from different validation folds and random seeds.
• Studying inter-physician agreement or variability in classification tasks based on the six physician scores.

Strengths

• Provides a direct comparison of 9 AI model scores against 6 human physician scores.
• The 5.5 KB size indicates a focused, easily downloadable dataset for targeted analysis.

Limitations

• Row count and specific column definitions are unknown, requiring manual inspection after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare, authored by Ilhan Yoo.

Collection Method

Likely contains performance scores from a model validation study and physician assessments.

Freshness

Last updated 2026-05-19 17:38:48; freshness should be verified.