Readability Scores for AI-Generated Myofascial Pain Syndrome Content

A dataset comparing the readability, reliability, and quality of medical content on Myofascial Pain Syndrome generated by three AI models. The dataset includes scores from six readability indices, four quality and reliability scales, and was created by Yüksel Erkin in 2026. It contains responses to 18 keywords queried from ChatGPT, Gemini, and Perplexity.

Use Cases

• Benchmark AI model performance on medical text generation based on readability and quality metrics.
• Analyze the correlation between content quality and reliability scores for AI-generated health information.
• Compare linguistic complexity across different AI platforms using six readability indices.
• Assess the suitability of AI chatbot responses for patient comprehension against a sixth-grade reading standard.

Strengths

• Scores derived from six established readability indices (FRES, FKGL, GFOG, CLI, ARI, SMOG).
• Content assessed using four established quality and reliability scales (JAMA, DISCERN, GQS, EQIP).
• Data generated from queries to three distinct AI models (ChatGPT, Gemini, Perplexity).
• Analysis performed by two independent observers, likely improving score reliability.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 9.5 KB, indicating limited scope.

Provenance

Source

figshare

Collection Method

AI-generated responses to 18 keywords derived from Google Trends data, scored by independent observers.

Freshness

Last updated 2026-06-04 17:22:31; freshness should be verified.