@article{article_1738669, title={AI-Assisted Knowledge Assessment: Comparison of ChatGPT and Gemini on Undescended Testicle in Children}, journal={Aksaray Üniversitesi Tıp Bilimleri Dergisi}, volume={5}, pages={93–97}, year={2025}, author={Özdemir Kaçer, Emine and Tuşat, Mustafa and Kılıçaslan, Murat and Memiş, Sebahattin}, keywords={ChatGPT, İnmemiş Testis., Gemini, Çocuklar}, abstract={Aim: This study aimed to evaluate the accuracy and completeness of ChatGPT-4 and Google Gemini in answering questions about undescended testis, as these AI tools can sometimes provide seemingly accurate but incorrect information, raising caution in medical applications. Methods: Researchers created 20 identical questions independently and submitted them to both ChatGPT-4 and Google Gemini.A pediatrician and a pediatric surgeon evaluated the responses for accuracy, using the Johnson et al. scale (accuracy rated from 1 to 6 and completeness from 1 to 3).Responses that lacked content received a score of 0. Statistical analyses were performed using R Software (version 4.3.1) to assess differences in accuracy and consistency between the tools. Results: Both chatbots answered all questions, with ChatGPT achieving a median accuracy score of 5.5 and a mean score of 5.35, while Google Gemini had a median score of 6 and a mean of 5.5. Completeness was similar, with ChatGPT scoring a median of 3 and Google Gemini showing comparable performance. Conclusion: ChatGPT and Google Gemini showed comparable accuracy and completeness; however, inconsistencies between accuracy and completeness suggest these AI tools require refinement.Regular updates are essential to improve the reliability of AI-generated medical information on UDT and ensure up-to-date, accurate responses.}, number={3}, publisher={Aksaray Üniversitesi}