AI-Assisted knowledge assessment: comparison of ChatGPT and Gemini on undescended testicle in children
dc.contributor.author | Özdemir Kaçer, Emine | |
dc.contributor.author | Tuşat, Mustafa | |
dc.contributor.author | Kılıçaslan, Murat | |
dc.contributor.author | Memiş, Sebahattin | |
dc.date.accessioned | 2025-10-01T11:41:15Z | |
dc.date.available | 2025-10-01T11:41:15Z | |
dc.date.issued | 2025 | |
dc.department | Tıp Fakültesi | |
dc.description.abstract | 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. | |
dc.identifier.endpage | 97 | |
dc.identifier.issue | 3 | |
dc.identifier.startpage | 93 | |
dc.identifier.uri | https://hdl.handle.net/20.500.12451/14581 | |
dc.identifier.volume | 5 | |
dc.institutionauthor | Özdemir Kaçer, Emine | |
dc.institutionauthor | Tuşat, Mustafa | |
dc.institutionauthor | Kılıçaslan, Murat | |
dc.institutionauthor | Memiş, Sebahattin | |
dc.institutionauthor | Emine, Özdemir Kaçer | |
dc.institutionauthorid | 0000-0002-0111-1672 | |
dc.institutionauthorid | 0000-0003-2327-4250 | |
dc.institutionauthorid | 0000-0003-1243-9830 | |
dc.institutionauthorid | 0000-0002-3829-9218 | |
dc.language.iso | en | |
dc.publisher | Aksaray Üniversitesi | |
dc.relation.ispartof | Aksaray Üniversitesi Tıp Bilimleri Dergisi | |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | |
dc.rights | info:eu-repo/semantics/openAccess | |
dc.subject | ChatGPT | |
dc.subject | Gemini | |
dc.subject | Children | |
dc.subject | Undescended Testicle | |
dc.title | AI-Assisted knowledge assessment: comparison of ChatGPT and Gemini on undescended testicle in children | |
dc.type | Article |