SOC
Surgery on Children

Surgery on Children Journal aims to publish issues related to Pediatric Surgery, Pediatric Neurosurgery, Pediatric Plastic Surgery, Pediatric Cardiovascular Surgery, Pediatric Orthopedic Surgery, Pediatric Vascular Surgery, Pediatric Gynecology and Obstetrics, Pediatric Ear Nose Throat, Ophthalmology, Pediatric Anesthesiology and Reanimation, Pediatric Urology, Pediatric Surgical Intensive Care Clinic, and other clinical surgery fields on children of the highest scientific and clinical value at an international level and accepts articles on these topics.

eISSN: 3023-7289
Creative Commons CC BY-NC-ND 4.0 International License.
EndNote Style

Online Manuscript System

Index
Original Article
The potential of AI applications to providing clinical counseling to parents: a pilot study
Abstract
Aims: This study aimed to evaluate the responses of current large language model-based AI applications to pediatric surgery and urology clinical scenarios using expert physician-defined criteria, and to investigate their potential for providing clinical guidance to parents.
Methods: Ten clinical questions were submitted to three AI applications (ChatGPT-5.2, DeepSeek-V3.1, Gemini 3). Responses were scored blindly by four specialist physicians using ten criteria across four domains (maximum, 20 points per question). A safety veto criterion (E1) was included as an independent safeguard; any response failing to recognize a clinical emergency or containing potentially harmful information was rendered invalid regardless of other scores.
Results: No safety related veto was applied. The overall mean scores were as follows: ChatGPT-5.2: 19,8/20, Gemini 3: 19,8/20 and DeepSeek-V3.1: 19,6/20. The lowest single-rater scores were observed in DeepSeek-V3.1 responses for varicocele (S6, min: 16/20) and intermittent hernias (S7, min: 16/20), although question-level mean scores for these items remained high (18,3/20 and 18,8/20, respectively).
Conclusion: In this pilot evaluation, current LLM-based AI applications demonstrated promising performance in responding to parental questions in pediatric urology and general pediatrics, though these findings should be interpreted within the scope of the limited number of clinical scenarios evaluated. They may have potential as a source of supplementary information but cannot replace physician consultations.

Keywords : Artificial intelligence, urology, child, pediatrics, chatbots, caregivers

Download Article
Ethical Statement

This study was approved by the Ethics Committee for Scientific Researches at Eskişehir City Hospital (Date: 10.04.2026, Decision No: ESH/BAEK 2026/367).

Informed Consent

As no human participants or patient-level data were included, informed consent was not required.

Author Contributions

Concept: NK, ÖA; Design: NK; Consultation: ÖA, BT; Data Collection and/or Processing: NK, ÖA, EBK, BT; Analysis and/or Interpretation: NK, ÖA; Literature Review: BT, EBK; Manuscript Preparation: NK; Critical Review: All Authors.

Conflict of Interest

The authors declare no conflicts of interest related to this study.

Financial Disclosure

The authors received no financial support for the conduct or publication of this research.


1. Topol EJ. High-performance medicine: the convergence of human and Artificial Intelligence. Nat Med. 2019;25(1):44-56. doi:10.1038/s41591-018-0300-7
2. Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthcare (Basel). 2023;11(6):887. doi:10.3390/healthcare11060887
3. Akbayram HT, Coskun E. Paediatric emergency department visits for non-urgent conditions: can family medicine prevent this? Eur J Gen Pract. 2020;26(1):134-139. doi:10.1080/13814788.2020.1825676
4. Yüksel A. Characteristics of pediatric emergency patients in a Turkish tertiary-level hospital: a 1-year cross-sectional study. SAGE Open Med. 2022;10:20503121221135401. doi:10.1177/20503121221135401
5. Saygili S, Demirbas KC, Bagci B, et al. Underserved and undervalued: the alarming collapse in pediatric residency preference in Türkiye. Turk Arch Pediatr. 2025;60(4):352-354. doi:10.5152/TurkArchPediatr.2025.1112254
6. Frey E, Bonfiglioli C, Brunner M, Frawley J. Parents’ use of social media as a health information source for their children: a scoping review. Acad Pediatr. 2022;22(4):526-539. doi:10.1016/j.acap.2021.12.006
7. Smailhodzic E, Hooijsma W, Boonstra A, Langley DJ. Social media use in healthcare: a systematic review of effects on patients and on their relationship with healthcare professionals. BMC Health Serv Res. 2016; 16(1):442. doi:10.1186/s12913-016-1691-0
8. Suarez-Lledo V, Alvarez-Galvez J. Prevalence of health misinformation on social media: systematic review. J Med Internet Res. 2021;23(1):e17187. doi:10.2196/17187
9. 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
10. Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat Med. 2023;29(8):1930-1940. doi:10.1038/s41591-023-02448-8
11. Koo TK, Li MY. A Guideline of selecting and reporting intraclass correlation coefficients for reliability research. J Chiropr Med. 2016; 15(2):155-163. doi:10.1016/j.jcm.2016.02.012
12. Singhal K, Azizi S, Tu T, et al. Large language models encode clinical knowledge. Nature. 2023;620(7972):172-180. doi:10.1038/s41586-023-06291-2
13. Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit Health. 2023;2(2):e0000198. doi:10.1371/journal.pdig.0000198
14. Çıraklı Ü. 18 OECD ülkesinde 2002-2018 yılları arası kişi başı ortalama hasta muayene sürelerinin karşılaştırılması.Sağlıkta Kalite ve Akreditasyon Derg.2020;3(1):43-54.
15. Crocetti M, Moghbeli N, Serwint J. Fever phobia revisited: have parental misconceptions about fever changed in 20 years? Pediatrics. 2001;107(6):1241-1246. doi:10.1542/peds.107.6.1241
16. Hany M, Zidan MH, Parmar C, et al. Accuracy and knowledge base evaluation of ChatGPT-4o, Gemini-2.0-Flash, and DeepSeek-V3 in metabolic and bariatric surgery: an expert-rated blinded study. Obes Surg. 2026;36(5):2160-2171. doi:10.1007/s11695-026-08562-z
17. Meyer A, Karay Y, Steinbicker AU, Streichert T, Overbeek R. Performance of DeepSeek-R1, ChatGPT (GPT-o3-mini), and Gemini 2.0 Flash on German medical multiple-choice questions: comparative evaluation. JMIR Form Res. 2025;9:e77357. doi:10.2196/77357
18. Tortum F, Kasali K. Exploring the potential of Artificial Intelligence models for triage in the emergency department. Postgrad Med. 2024; 136(8):841-846. doi:10.1080/00325481.2024.2418806
19. Eraybar S, Dal E, Aydin MO, Begenen M. Transforming emergency triage: apreliminary, scenario-based cross-sectional study comparing Artificial Intelligence models and clinical expertise for enhanced accuracy. Bratisl Lek Listy. 2024;125(11):738-743. doi:10.4149/BLL_2024_114
20. Ensari E, Boztas AE. Evaluation of ChatGPT-4o® responses on pediatric urolithiasis: is it useful? Urolithiasis. 2025;53(1):202. doi:10.1007/s00240-025-01880-4
21. Laranjo L, Dunn AG, Tong HL, et al. Conversational agents in healthcare: a systematic review. J Am Med Inform Assoc. 2018;25(9): 1248-1258. doi:10.1093/jamia/ocy072
Article available in :
Volume 3, Issue 4, 2026
Page : 133-138
https://doi.org/10.51271/SOC-0086
Article Information
Received : 08 Eyl 2026
Accepted : 09 Eki 2026
Published : 20 Eki 2026
Corresponding Author :

Nilsun Kuas: Department of Pediatric Urology, Eskişehir City Hospital, Eskişehir, Turkiye

[email protected]
Citation : Kuas N, Aktaş Ö, Karkın EB, Tekkanat B. The potential of AI applications to provide clinical counseling to parents: a pilot study. Surg Child. 2026;3(4):133-138. doi:10.51271/SOC-0086

Read: 6
Download : 5
Cited: 0
_Footer