Deep Learning Model and Physician Signal Classification Scores

Signal classification scores of a deep learning model and physicians. The model scores are measured with 9 scores from 3 validation folds and 3 random seeds. Physician scores are measured with 6 scores from 6 physicians. The dataset was authored by Ilhan Yoo and last updated on 2026-05-19.

Use Cases

• Benchmarking deep learning model performance against physician assessments based on the provided classification scores.
• Analyzing the variability of model outputs based on different validation folds and random seeds.
• Comparing inter-physician agreement on signal classification tasks.
• Conducting meta-analyses on AI vs. human performance in diagnostic tasks.

Strengths

• Provides a direct comparison of 9 deep learning model scores and 6 physician scores.
• Includes scores derived from 3 validation folds and 3 random seeds, suggesting a structured evaluation methodology.
• Dataset is small (5.5 KB), facilitating quick download and inspection.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Ilhan Yoo via figshare

Collection Method

Likely contains experimental results from a model evaluation study.

Freshness

Last updated 2026-05-19 17:38:47; freshness should be verified.