Answers are grounded in this paper and cite their sources.
Aim This study evaluates the quality, reliability, and readability of Turkish-language information provided by four large language models (LLMs) regarding regenerative medicine modalities in algology practice. Methods Ten standardized queries derived from Google Trends (January 2026) were submitted to ChatGPT 5.2, Gemini, Gemini Pro, and Perplexity. Responses were evaluated by two blinded algologists using the DISCERN instrument, JAMA benchmark criteria, and Global Quality Score (GQS). Readability was assessed using Atesman and Bezirci-Yilmaz indices. Non-parametric repeated-measures comparisons were performed using the Friedman test followed by Bonferroni-corrected Wilcoxon signed-rank tests. Results Regarding content quality (DISCERN), ChatGPT 5.2 (71.2 ± 3.3) and Gemini Pro (70.7 ± 3.2) demonstrated "excellent" performance (≥70), Perplexity (64.2 ± 6.3) was rated as "good" (50–69), and baseline Gemini (49.3 ± 4.2) was classified as "poor" (<50) (Friedman Chi-square = 28.03, p < 0.001). Perplexity achieved significantly higher scientific transparency scores (JAMA: 3.6 ± 0.5, p < 0.001). Readability analyses revealed that all models produced structurally complex texts, approximating associate- and undergraduate-level difficulty on the Atesman index (38.1–41.8). Perplexity exhibited significantly lower Bezirci-Yilmaz scores (6.8 ± 1.5) than non-RAG models (11.4–12.1, p < 0.001), reflecting simpler sentence structures. Conclusions While advanced LLMs achieve favorable scores on structural consumer health information quality metrics, they present a persistent readability barrier. Crucially, favorable scores on structural quality instruments do not equate to independently verified clinical accuracy or procedural safety, underscoring that AI outputs cannot replace specialist medical consultation in regenerative pain medicine.
No takes yet. Share an insight, caveat, or question.
Sari et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: