ChatGPT-4o in pediatric surgery and urology: current possibilities and limitations in everyday use in Czech hospitals

Czech version

Authors: J. Trachta; L. Poš
Authors‘ workplace: Klinika dětské chirurgie 2. LF UK a FN Motol a Homolka, Praha
Published in: Rozhl. Chir., 2026, roč. 105, č. 1, s. 20-28.
Category: Review
doi: https://doi.org/10.48095/ccrvch2026

Overview

This narrative review article describes the possibilities and limitations of using the ChatGPT-4o language model in pediatric surgery and urology in Czech hospitals. Based on a review of 45 research and media sources published between 2023 and 2025, the article explains the basic principles of how the chatbot works and divides the possibilities of using ChatGPT-4o into those that are realistic in current practice and those that are potential in the near future. The model can serve as a tool in the education of medical students and doctors preparing for specialization or as a useful assistant in writing academic papers. ChatGPT-4o can be used in communication with children and their parents as an understandable source of information and answers to lay questions in preparation for investigations and operations. It can be used as a data collection tool in monitoring long-term complications, quality of life, and subjective perception of the perioperative period. It can help doctors as a consultation tool in the diagnostic and investigation process or when writing outpatient reports and surgical protocols. Potential future uses of the chatbot include the integration of all clinical data about the patient, generating admission and discharge reports or the role of an intraoperative multimodal AI assistant. Ethical risks are discussed, particularly in the areas of authorship, reliability of chatbot outputs, and personal data protection. The introduction of European legislation on the use of AI, not only in healthcare, is mentioned. Based on personal experience, the authors recommend the use of the latest ChatGPT model as a useful support tool in the daily practice of pediatric surgeons and believe that the practical usefulness of chatbots will continue to grow over time.

Keywords:

artificial intelligence – ChatGPT-4o – pediatric surgery and urology – practical application

Sources

Clusmann J, Kolbinger FR, Muti HS et al. The future landscape of large language models in medicine. Commun Med (Lond) 2023; 3(1): 141. doi: 10.1038/s43856-023-00370-1.
Miyake Y, Retrosi G, Keijzer R. Artificial intelligence and pediatric surgery: where are we? Pediatr Surg Int 2024; 41(1): 19. doi: 10.1007/s00383-024-05921-8.
González R, Poenaru D, Woo R et al. ChatGPT: what every pediatric surgeon should know about its potential uses and pitfalls. J Pediatr Surg 2024; 59(5): 941–947. doi: 10.1016/j.jpedsurg.2024.01.007.
Data center map –⁠ colocation, cloud and connectivity. 2025 [online]. Available from: https://www.datacentermap.com/.
Jiřík M, Moulisová V, Hlaváč M et al. Artificial neural networks and computer vision in medicine and surgery. Rozhl Chir 2022; 101(12): 564–570. doi: 10.33699/PIS.2022.101.12.564-570.
Umělá inteligence pomáhá rozpoznat rakovinu. Dostupná je v 60 českých nemocnicích. FocusOn. 2025 [online]. Available from: https://www.focuson.cz/umela-inteligence-pomaha-rozpoznat-rakovinu-dostupna-je-v-60-ceskych-nemocnicich/.
CSAIM –⁠ Česká společnost pro umělou inteligenci a inovativní digitální technologie v medicíně. 2025 [online]. Available from: https://csaim.cz/.
Cottier B, Rahman R, Fattorini L et al. The rising costs of training frontier AI models. 2025 [online]. Available from: https://github.com/epoch-research/.
Tech giants beat quarterly expectations as Trump’s tariffs hit the sector. Technology. The Guardian. 2025 [online]. Available from: https://www.theguardian.com/technology/2025/may/06/techscape-trump-tariffs-ai-musk-meta.
The Most Used AI Chatbots in 2025: Global usage, trends, and platform comparisons of ChatGPT, Gemini, Copilot, and Claude. 2025 [online]. Available from: https://www.datastudios.org/post/the-most-used-ai-chatbots-in-2025-global-usage-trends-and-platform-comparisons-of-chatgpt-gemini?utm_source=chatgpt.com.%20The%20Guiradian:%20.
Uppalapati VK, Nag DS. A comparative analysis of AI models in complex medical decision-making scenarios: evaluating ChatGPT, Claude AI, Bard, and Perplexity. Cureus 2024; 16(1): e52485. doi: 10.7759/cureus.52485.
Gravina AG, Pellegrino R, Palladino G et al. Charting new AI education in gastroenterology: cross-sectional evaluation of ChatGPT and perplexity AI in medical residency exam. Dig Liver Dis 2024; 56(8): 1304–1311. doi: 10.1016/j.dld.2024.02.019.
Best practices for prompt engineering with the OpenAI API. OpenAI Help Center. 2025 [online]. Available from: https://help.openai.com/en/articles/6654000-best-practices-for-prompt-engineering-with-the-openai-api.
Lucas HC, Upperman JS, Robinson JR. A systematic review of large language models and their implications in medical education. Med Educ 2024; 58(11): 1276–1285. doi: 10.1111/medu.15402.
Ishida K, Hanada E. ChatGPT (GPT-4o) performance on the healthcare information technologist examination in Japan. Cureus 2025; 17(1): e76775. doi: 10.7759/cureus.76775.
Seth P, Carretas R, Rudzicz F. The utility and implications of ambient scribe in primary care. JMIR AI 2024; 3: e57673. doi: 10.2196/57673.
Gigola F, Amato T, Del Riccio M et al. Artificial intelligence in clinical practice: a cross-sectional survey of paediatric surgery residents' perspectives. BMJ Health Care Inform 2025; 32(1): e101456. doi: 10.1136/bmjhci-2025-101456.
Cheung BH, Lau GK, Wong GT et al. ChatGPT versus human in generating medical graduate exam multiple choice questions –⁠ a multinational prospective study (Hong Kong S.A.R., Singapore, Ireland, and the United Kingdom). PLoS One 2023; 18(8): e0290691. doi: 10.1371/journal.pone.0290691.
Robinson JR, Stey A, Schneider DF et al. Generative artificial intelligence in academic surgery: ethical implications and transformative potential. J Surg Res 2025; 307 : 212–220. doi: 10.1016/j.jss.2024.12.059.
Xiao D, Meyers P, Upperman JS et al. Revolutionizing healthcare with ChatGPT: an early exploration of an AI language model's impact on medicine at large and its role in pediatric surgery. J Pediatr Surg 2023; 58(12): 2410–2415. doi: 10.1016/j.jpedsurg.2023.07.008.
Chutia T, Baruah N. A review on emotion detection by using deep learning techniques. Artif Intell Rev 2024; 57 : 203. doi: 10.1007/s10462-024-10831-1.
Ayers JW, Poliak A, Dredze M et al. Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum. JAMA Intern Med 2023; 183(6): 589–596. doi: 10.1001/jamainternmed.2023.1838.
van Eerde AM, Teixeira A, Galletti F et al. Risks and benefits of ChatGPT in informing patients and families with rare kidney diseases: an explorative assessment by the European Rare Kidney Disease Reference Network (ERKNet). Pediatr Nephrol 2025; 40(9): 2899–2905. doi: 10.1007/s00467-025-06746-w.
Zeltzer D, Herzog L, Pickman Y et al. Diagnostic accuracy of artificial intelligence in virtual primary care. Mayo Clin Proc Digit Health 2023; 1(4): 480–489. doi: 10.1016/j.mcpdig.2023.08.002.
What is Doximity? –⁠ Help Center. 2025 [online]. Available from: https://support.doximity.com/hc/en-us/articles/360047806713-What-is-Doximity.
Nový startup má lékaře zbavit papírování. Milion dolarů do něj dal bývalý šéf Avastu. Forbes. 2025 [online]. Available from: https://forbes.cz/novy-startup-ma-lekare-zbavit-papirovani-milionem-dolaru-ho-podporil-byvaly-sef-avastu/?bclid=IwY2xjawKoQQ1leHRuA2FlbQIxMABicmlkETExczJCR2tLUTJCMlVKSHNZAR60e_ztiLHw5r0I_d9TIjTQphB1Apq1zISsrGwX9TNGENqz1cp-LUwnctR2hA_aem_wyYsas1VUVk0nmSjIKZXAg.
Pro kliniky. Medevio. 2025 [online]. Available from: https://www.medevio.cz/pro-kliniky.
První dojmy z GPT-5: malý posun ve schopnostech, větší v jednoduchosti použití. AI začíná být pro každého –⁠ Deník N. 2025 [online]. Available from: https://denikn.cz/1805937/prvni-dojmy-z-gpt-5-maly-posun-ve-schopnostech-vetsi-v-jednoduchosti-pouziti-ai-zacina-byt-pro-kazdeho/?ref=list.
Thorp HH. ChatGPT is fun, but not an author. Science 2023; 379(6630): 313. doi: 10.1126/science.adg7879.
Tools such as ChatGPT threaten transparent science; here are our ground rules for their use. Nature 2023; 613(7945): 612. doi: 10.1038/d41586-023-00191-1.
Resnik DB, Hosseini M. The ethics of using artificial intelligence in scientific research: new guidance needed for a new tool. AI Ethics 2025; 5(2): 1499–1521. doi: 10.1007/s43681-024-00493-8.
Leung TI, de Azevedo Cardoso T, Mavragani A et al. Best practices for using AI tools as an author, peer reviewer, or editor. J Med Internet Res 2023; 25: e51584. doi: 10.2196/51584.
Generative AI policies for journals. 2025 [online]. Available from: https://www.elsevier.com/about/policies-and-standards/generative-ai-policies-for-journals.
van Kolfschooten H, van Oirschot J. The EU artificial intelligence act (2024): implications for healthcare. Health Policy 2024; 149 : 105152. doi: 10.1016/j.healthpol.2024.105152.