<p>mas020326.</p>

mas020326 is a dataset containing responses from three AI models (ChatGPT, Gemini, Perplexity) to 18 keywords related to Myofascial Pain Syndrome. The dataset includes scores from six readability indices and four quality/reliability scales, generated for a study comparing AI-generated medical content. The dataset was authored by Yüksel Erkin and last updated in June 2026.

Use Cases

• Benchmarking AI model performance on medical content generation based on readability and quality metrics.
• Analyzing the relationship between content quality and reliability scores (JAMA, DISCERN, GQS, EQIP) mentioned in the description.
• Comparing linguistic complexity across different AI models using the six readability indices (FRES, FKGL, GFOG, CLI, ARI, SMOG).
• Training models to assess or generate medical text that meets specific readability standards.

Strengths

• Includes scores from six established readability indices and four quality/reliability scales, providing a multi-faceted evaluation.
• Compares outputs from three distinct AI models (ChatGPT, Gemini, Perplexity) on a consistent set of 18 medical keywords.
• Data is licensed under CC-BY-4.0, permitting reuse with attribution.

Limitations

• Row count is unknown, which may limit suitability assessment for large-scale analysis.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small (18.0 KB), indicating a limited scope of analysis.

Provenance

Source

Yüksel Erkin via figshare

Collection Method

AI model responses were generated, then scored by two independent observers using standardized indices and scales.

Freshness

Last updated 2026-06-04 17:22:28; freshness should be verified.