Readability Scores for AI-Generated Myofascial Pain Syndrome Content

Yüksel Erkin's dataset contains readability, quality, and reliability scores for AI-generated medical content. The data compares responses from ChatGPT, Gemini, and Perplexity models on 18 keywords related to Myofascial Pain Syndrome, assessed using six readability indices and four quality/reliability scales. The dataset was last updated on June 4, 2026.

Use Cases

• Benchmarking AI model readability for medical content based on six different indices (FRES, FKGL, GFOG, CLI, ARI, SMOG).
• Comparing content quality and reliability across AI models using GQS, EQIP, DISCERN, and JAMA scales.
• Analyzing the correlation between quality and reliability parameters in AI-generated health information.
• Assessing the linguistic complexity of AI outputs against a sixth-grade reading level standard.

Strengths

• Data is derived from a systematic study comparing three major AI models (ChatGPT, Gemini, Perplexity).
• Content was assessed using six established readability indices and four quality/reliability scales.
• Evaluations were performed by two independent observers, which may enhance reliability.
• Dataset is openly available under a CC-BY-4.0 license.

Limitations

• The dataset is very small at 9.5 KB, indicating limited scope.
• Row count and column-level documentation are unknown; field semantics must be inferred after download.
• Data may reflect temporal bias inherent to the specific AI model versions tested in the study.

Provenance

Source

Yüksel Erkin via figshare.

Collection Method

AI model responses to 18 keywords were scored for readability, quality, and reliability by independent observers.

Freshness

Last updated 2026-06-04 17:22:30; freshness should be verified as it is a future date.