Objective: This study aimed to explore common patient inquiries about Cone-Beam Computed Tomography (CBCT) and systematically assess the accuracy, quality, usefulness, and readability of outputs from four AI-based conversational platforms (ChatGPT-3.5, DeepSeek-V3.1, Gemini 1.5 Flash, and Microsoft Copilot Free).Materials and Methods: Common questions about CBCT were gathered from online sources and expert contributions and submitted to ChatGPT-3.5, DeepSeek, Gemini, and Copilot under standardized conditions. Outputs were independently evaluated by three specialists using CLEAR, mGQS, accuracy, usefulness, DISCERN, and readability metrics (FRE and FKGL).Results: Significant differences were observed among AI platforms regarding CLEAR scores (p < 0.05), with Gemini showing higher values than ChatGPT (p = 0.016). Across all four platforms, strong to a very strong positive correlations were found among CLEAR, mGQS, and Accuracy scores (r ≥ 0.77, p < 0.001), while these measures were strongly to very strongly and inversely correlated with Usefulness (r ≤ −0.77, p < 0.001). Flesch Reading Ease and Flesch-Kincaid Grade Level demonstrated a very strong negative correlations across platforms (r ranging from −0.85 to −0.93, p < 0.05). Within the Gemini group, Flesch-Kincaid Grade Level showed a moderate positive association with DISCERN scores (r = 0.496, p = 0.043).Conclusions: Gemini and DeepSeek produced more accurate and clearer responses. The readability of all AI systems was below the recommended level for patient education. These systems may support patient education but require expert validation.
Savaş Özarslantürk, Seval Ceylan Şen, Özlem Saraç Atagün et al.· Northwestern Medical Journal· 0 citations
OBJECTIVE
To compare the quality and readability of responses from five generative artificial intelligence chatbot platforms to clinician-oriented questions on open temporomandibular joint (TMJ) surgery against guideline-based reference answers.
MATERIAL AND METHODS
Forty questions across eight domains were submitted on 16 July 2026 to ChatGPT (GPT-5.5), Claude (Opus 4.8), Gemini (3.1 Pro), Grok (4) and Perplexity (Pro), each via its paid tier at default settings (200 responses). Two blinded oral and maxillofacial surgeons applied the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool, the Global Quality Score (GQS) and a five-point overall quality rating using a priori key elements and written anchors. Readability was assessed with the Flesch-Kincaid Grade Level (FKGL) and Flesch Reading Ease Score (FRES); platforms were compared with the Friedman test and Bonferroni-corrected Wilcoxon post-hoc tests; inter-rater reliability used intraclass correlation coefficients (ICC).
RESULTS
Inter-rater reliability was good to excellent (average-measure ICC 0.93-0.99). All outcomes except clarity differed among platforms (P < .001). Perplexity achieved the highest QAMAI total (27.5 ± 1.4; Kendall's W = 0.75), largely through retrieval-based source provision; excluding this domain, Claude, Perplexity and Gemini converged. Claude had the highest GQS (4.5 ± 0.6), Gemini the highest overall rating (4.3 ± 0.7); Grok scored lowest. Claude and Gemini were least readable (median FKGL 22.7 and 26.1; FRES -11.6 and -7.5). Length did not explain scores within platforms.
CONCLUSIONS
Performance varied substantially across platforms and dimensions; no platform optimized all outcomes. These findings describe informational quality, not clinical safety or decision-making, and support specialist verification before clinical use.
