Quality and Readability of ChatGPT and Gemini Responses to Patient Questions About Systemic Isotretinoin: Comparative Evaluation Study

The use of AI in health care is rapidly expanding due to its accessibility, with growing reliance among both physicians and patients.

This study evaluated ChatGPT (OpenAI) and Gemini (Google) responses to patient questions on systemic isotretinoin.

A total of 40 commonly anticipated patient questions were developed based on online sources and patient education materials and categorized into 5 groups. Responses were generated using the January 2025 free versions of ChatGPT (GPT-4o) and Gemini 2.0 Flash. A total of 5 experienced dermatologists evaluated the responses in a blinded manner using a 5-point Likert scale assessing accuracy, clarity, completeness, usefulness, and overall quality score (Global Quality Score [GQS]). Readability was measured using Flesch-Kincaid Grade Level (FKGL), Flesch Reading Ease, and Simple Measure of Gobbledygook (SMOG) index scores. Mixed-effects modeling was performed to adjust for reviewer and question variability, and intraclass correlation coefficients (ICCs) were calculated to assess interrater reliability.

ChatGPT achieved significantly higher ratings in accuracy, completeness, usefulness, and GQS, while clarity showed a nonsignificant trend. When questions were analyzed by subtype, no statistically significant differences were observed between models across evaluation parameters. Mixed-effects modeling confirmed higher odds of superior ratings for ChatGPT across domains (odds ratios [ORs] 1.82-5.88; all P<.001). However, interrater reliability was lower for ChatGPT (global ICC 0.401) compared with Gemini (global ICC 0.677). Readability analyses demonstrated that ChatGPT required a higher reading level (FKGL 12.6 vs 11.2; SMOG 11.3 vs 10.0).

ChatGPT outperformed Gemini in terms of data accuracy and quality, while Gemini offered superior readability and consistency. Both models exceeded recommended readability thresholds, highlighting a gap between informational quality and linguistic accessibility in AI-generated health communication.