Multivariable Linear Regression of AI Accuracy on Patient Age, Gender, and Clinical Score

5.5 KB of regression analysis results examining the relationship between DeepSeek's accuracy and patient age, gender, Rapid Emergency Medicine Score (REMS), and question type. The dataset, authored by Yang Wang, was last updated on May 8, 2026, and is shared under a CC-BY-4.0 license.

Use Cases

• Assessing AI model bias based on patient demographic variables like age and gender.
• Analyzing the correlation between clinical severity scores (REMS) and AI diagnostic accuracy.
• Investigating how question or task type influences AI performance in medical settings.

Strengths

• Dataset is small (5.5 KB), facilitating quick download and inspection.
• Analysis includes multiple clinical and demographic variables (age, gender, REMS, question type).
• Clear licensing (CC-BY-4.0) supports open reuse and modification.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset's small size suggests it contains summary results rather than raw patient data.

Provenance

Source

Yang Wang via figshare.

Collection Method

Results of a multivariable linear regression analysis.

Time Range

null

Freshness

Last updated 2026-05-08 17:34:57; freshness should be verified.

Geography

null