Research Article

Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2

Volume: 2 Number: 3 September 30, 2026
TR EN

Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2

Abstract

Abstract Objectives: Legg–Calvé–Perthes disease is a serious orthopedic condition that can lead to permanent disability. Today, families increasingly turn to artificial intelligence–based chatbots in their online health information search. This study aimed to test the hypothesis that three commonly used chatbots can provide accurate and understandable answers to questions about Perthes disease, and to compare their responses in terms of accuracy, comprehensiveness, readability, and user understandability. Methods: On December 10, 2025, the AI-based chatbots GPT-5.1 (OpenAI), Gemini 3 (Google), and DeepSeek V3.2 (DeepSeek) were asked 11 questions from the “Frequently Asked Questions” section of the Perthes Kids Foundation website. A separate conversation was started for each question, using the standard prompt: “I am a parent of a child diagnosed with Perthes disease and I would like to ask…”. The answers were evaluated by two independent pediatric orthopedic specialists using AIRES, PEMAT-P, Flesch Reading Ease (FRE), and Flesch–Kincaid Grade Level (FKGL) indices and were statistically compared. Results: All chatbots produced excellent-quality answers according to the AIRES evaluation. A moderate and statistically significant agreement was observed between observers for AIRES ([ICC]=0.501, p<0.001). Gemini provided answers with lower understandability according to PEMAT-P scores (p = 0.005). No significant differences were found between the chatbots in readability analyses; most answers were at a high school–level readability. Conclusions: This study shows that current chatbots can provide accurate, comprehensive, up-to-date, and understandable answers to questions about Perthes disease. Their interactive nature may allow them to differ from traditional online health information platforms and to respond more effectively to the multidimensional information needs of patients and families. In the future, integrating chatbots with clinical findings may further enhance personalized information delivery and reshape doctor–patient communication in pediatric orthopedic practice.

Keywords

Ethical Statement

This study does not involve any human or animal participants, and no personal or confidential patient data were utilized. The research was conducted using publicly available, anonymous data generated by artificial intelligence platforms. Therefore, institutional review board (ethics committee) approval was not required.

References

  1. Clark, M., & Bailey, S. (2024). Chatbots in health care: Connecting patients to information (Report No. EH0122). Canadian Agency for Drugs and Technologies in Health.
  2. Feghhi, D. P., Komlos, D., Agarwal, N., & Sabharwal, S. (2014). Quality of online pediatric orthopaedic education materials. The Journal of Bone and Joint Surgery, 96(23), e194.
  3. Gilbert, S. R., Laine, J. C., Martin, B. D., Sankar, W. N., & Kim, H. K. W. (2025). Legg–Calvé–Perthes disease. Journal of the American Academy of Orthopaedic Surgeons. Advance online publication.
  4. Goodman, R. S., Patrinely, J. R., Stone, C. A., Jr., Zimmerman, E., Donald, R. R., Chang, S. S., ... & others. (2023). Accuracy and reliability of chatbot responses to physician questions. JAMA Network Open, 6(10), e2336483.
  5. Jeong, K. Y., Lee, H. J., & Yim, S. Y. (2022). The usefulness, reliability, and quality of YouTube video clips on congenital muscular torticollis: A STROBE-compliant study. Medicine, 101(37), e30502.
  6. Kubb, C., & Foran, H. M. (2020). Online health information seeking by parents for their children: Systematic review and agenda for further research. Journal of Medical Internet Research, 22(8), e19985.
  7. Kusec, S., Brborovic, O., & Schillinger, D. (2003). Diabetes websites accredited by the Health On the Net Foundation Code of Conduct: Readable or not? Studies in Health Technology and Informatics, 95, 655–660.
  8. Leo, D. G., Murphy, R., Gambling, T., Long, A., Jones, H., & Perry, D. C. (2019). Perspectives on the social, physical, and emotional impact of living with Perthes’ disease in children and their family: A mixed methods study. Global Pediatric Health, 6, 2333794X19835235.

Details

Primary Language

English

Subjects

Orthopaedics

Journal Section

Research Article

Publication Date

September 30, 2026

Submission Date

June 11, 2026

Acceptance Date

July 6, 2026

Published in Issue

Year 2026 Volume: 2 Number: 3

APA
Bayraktar, T. O., Erkurt, N., Yüce, A., Yerli, M., Özdemir, B., & Corekci, A. M. (2026). Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2. Journal of Baltalimanı, 2(3), 60-64. https://izlik.org/JA83UW58BH
AMA
1.Bayraktar TO, Erkurt N, Yüce A, Yerli M, Özdemir B, Corekci AM. Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2. JoB. 2026;2(3):60-64. https://izlik.org/JA83UW58BH
Chicago
Bayraktar, Tahsin Olgun, Nazım Erkurt, Ali Yüce, Mustafa Yerli, Baran Özdemir, and Ahmet Murat Corekci. 2026. “Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2”. Journal of Baltalimanı 2 (3): 60-64. https://izlik.org/JA83UW58BH.
EndNote
Bayraktar TO, Erkurt N, Yüce A, Yerli M, Özdemir B, Corekci AM (September 1, 2026) Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2. Journal of Baltalimanı 2 3 60–64.
IEEE
[1]T. O. Bayraktar, N. Erkurt, A. Yüce, M. Yerli, B. Özdemir, and A. M. Corekci, “Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2”, JoB, vol. 2, no. 3, pp. 60–64, Sept. 2026, [Online]. Available: https://izlik.org/JA83UW58BH
ISNAD
Bayraktar, Tahsin Olgun - Erkurt, Nazım - Yüce, Ali - Yerli, Mustafa - Özdemir, Baran - Corekci, Ahmet Murat. “Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2”. Journal of Baltalimanı 2/3 (September 1, 2026): 60-64. https://izlik.org/JA83UW58BH.
JAMA
1.Bayraktar TO, Erkurt N, Yüce A, Yerli M, Özdemir B, Corekci AM. Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2. JoB. 2026;2:60–64.
MLA
Bayraktar, Tahsin Olgun, et al. “Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2”. Journal of Baltalimanı, vol. 2, no. 3, Sept. 2026, pp. 60-64, https://izlik.org/JA83UW58BH.
Vancouver
1.Tahsin Olgun Bayraktar, Nazım Erkurt, Ali Yüce, Mustafa Yerli, Baran Özdemir, Ahmet Murat Corekci. Evaluation of AI-Based Chatbots in Responding to Frequently Asked Online Questions About Perthes Disease: A Comparison of ChatGPT-5.1, Gemini 3, DeepSeek V3.2. JoB [Internet]. 2026 Sep. 1;2(3):60-4. Available from: https://izlik.org/JA83UW58BH