Answers are grounded in this paper and cite their sources.
Aim: Artificial intelligence-based systems are increasingly used for recognizing and assessing skin lesions, yet studies focusing on pregnancy-specific dermatological findings are limited. This study aimed to compare the accuracy of artificial intelligence based large language models in diagnosing pregnancy related dermatological lesions, explaining their etiopathogenesis, and providing clinically appropriate treatment recommendations.Materials and Methods: In this observational study, ten pregnancy-specific dermatological lesions were evaluated using ChatGPT (version 5) and Google Gemini (version 2.5). Each case was presented with an image from Williams Obstetrics, 26th edition, and a standardized patient statement: “I am pregnant. I have a skin lesion like this. What is it, why does it occur, and what should I do for treatment?” Responses were blindly rated by obstetrics and gynecology and dermatology specialists for diagnostic accuracy, etiopathogenesis explanation, and treatment appropriateness, using a five-point Likert scale. Cohen’s kappa was used to assess inter-rater agreement; the Wilcoxon test compared the models; Spearman’s correlation examined score relationships. A p-value of less than 0.05 was considered statistically significant.Results: ChatGPT outperformed Gemini in etiopathogenesis explanation (p = 0.002) and treatment recommendations (p = 0.002), with no significant difference in diagnostic accuracy (p = 0.336). ChatGPT generally provided more detailed, applicable responses, whereas Gemini often gave limited or purely directive information. Correlations between criteria were weak and statistically insignificant for both models.Conclusions: ChatGPT was superior to Gemini in etiopathogenesis and treatment recommendations but comparable in diagnostic accuracy. However, no artificial intelligence system can replace clinical evaluation by a physician.
No takes yet. Share an insight, caveat, or question.
Vuraloğlu et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: