Research Article

Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability

Volume: 19 Number: 4 October 10, 2026
EN TR

Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability

Abstract

Purpose: Artificial intelligence (AI) chatbots are increasingly used in patient education. This study evaluated the responses of AI chatbots to frequently asked questions about osteoporosis in Turkish in terms of accuracy, completeness, and readability. To our knowledge, this is the first study to evaluate AI-generated responses to osteoporosis-related questions in Turkish.
Materials and methods: Thirty-one of the most common frequently asked questions related to osteoporosis were subcategorized into general information, diagnosis, and treatment. The questions were submitted to the publicly accessible platforms ChatGPT-5.3, Gemini, Copilot, and Perplexity. Two physicians evaluated accuracy (six-point Likert scale) and completeness (three-point Likert scale) based on the 2025 Guideline for the Diagnosis and Treatment of Osteoporosis and Metabolic Bone Diseases. Readability was assessed using the Ateşman Readability Formula.
Results: No significant difference was found among the chatbots for accuracy. Accuracy rates ranged 80.5%-82.2% overall, 82.3%-85.2% general information, 58.3%-66.7% diagnosis, and 77.2%-81.7% treatment. Significant differences were found in completeness overall and in the general information (p=0.006, p=0.029; respectively). In pairwise comparisons, ChatGPT-5.3 showed significantly higher completeness than Perplexity (p=0.001, p=0.006; respectively). Completeness rates ranged 47%-64.3% overall, 46%-68.3% general information, 33.3%-50% diagnosis, and 48.3%-60.3% treatment. Readability differed significantly among the chatbots (p<0.001). Based on mean scores, the ranking was ChatGPT-5.3>Gemini=Copilot>Perplexity. ChatGPT-5.3, Gemini, and Copilot were easy, whereas Perplexity was moderately difficult.
Conclusion: All chatbots showed similar accuracy, but ChatGPT-5.3 performed better in completeness and readability. Chatbots may be useful in Turkish patient education. However, their standalone use in osteoporosis management without physician supervision is not appropriate.

Keywords

References

  1. Cosman, F., de Beur, S. J., LeBoff, M. S., Lewiecki, E. M., Tanner, B., Randall, S., Lindsay, R., & National Osteoporosis Foundation (2014). Clinician’s Guide to Prevention and Treatment of Osteoporosis. Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA, 25(10), 2359–2381. https://doi.org/10.1007/s00198-014-2794-2
  2. Zhang, X., Liang, Y., Zhang, F., & Liu, X. (2025). Osteoporosis: molecular pathogenesis and therapeutic interventions. Molecular biomedicine, 6(1), 98. https://doi.org/10.1186/s43556-025-00349-5
  3. GBD 2019 Fracture Collaborators (2021). Global, regional, and national burden of bone fractures in 204 countries and territories, 1990-2019: a systematic analysis from the Global Burden of Disease Study 2019. The lancet. Healthy longevity, 2(9), e580–e592. https://doi.org/10.1016/S2666-7568(21)00172-0
  4. Xiao, P. L., Cui, A. Y., Hsu, C. J., Peng, R., Jiang, N., Xu, X. H., Ma, Y. G., Liu, D., & Lu, H. D. (2022). Global, regional prevalence, and risk factors of osteoporosis according to the World Health Organization diagnostic criteria: a systematic review and meta-analysis. Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA, 33(10), 2137–2153. https://doi.org/10.1007/s00198-022-06454-3
  5. Bartl, R., & Bartl, C. (2016). Epidemiology of osteoporotic fractures. Bone Disorders: Biology, Diagnosis, Prevention, Therapy. Cham: Springer International Publishing, 233-234. https://doi.org/10.1007/978-3-319-29182-6
  6. Aksu, S., & Bakır, F. A. (2025). Yapay zeka sohbet robotlarının ‘diş hekimliğinde flor’ konusu ile ilgili sorulara verdikleri yanıtların değerlendirilmesi. Lokman Hekim Dergisi, 15(3), 1069-1078. https://doi.org/10.31020/mutftd.1746766
  7. Boztaş-Demir, G., & Görgülü, S. (2025). ChatGPT ve Gemini modellerinin ortodonti alanındaki türkçe yeterliliği: hasta sorularına verilen yanıtların doğruluk, eksiksizlik ve okunabilirlik değerlendirilmesi. Yeditepe Üniversitesi Diş Hekimliği Fakültesi Dergisi, 21(3), 151-158. https://doi.org/10.5505/yeditepe.2025.15010
  8. Durmuş-Ece, B. Ş., Hondur, G., & Yüksel, E. (2025). Glokomun Medikal Tedavisi ile İlgili Sorulara ChatGPT Yanıtlarının Doğruluk, Kapsamlılık, Okunabilirlik Açısından Değerlendirilmesi. MN Ophthalmology, 32(4), 239-245.

Details

Primary Language

English

Subjects

Physical Medicine and Rehabilitation

Journal Section

Research Article

Publication Date

October 10, 2026

Submission Date

April 18, 2026

Acceptance Date

July 6, 2026

Published in Issue

Year 2026 Volume: 19 Number: 4

APA
Akıncı, M. G., Atıgan, A., Suskun, C., & Yenidünya, A. (2026). Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability. Pamukkale Medical Journal, 19(4), 725-734. https://doi.org/10.31362/patd.1933335
AMA
1.Akıncı MG, Atıgan A, Suskun C, Yenidünya A. Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability. Pam Med J. 2026;19(4):725-734. doi:10.31362/patd.1933335
Chicago
Akıncı, Meltem Güneş, Alev Atıgan, Ceyda Suskun, and Atakan Yenidünya. 2026. “Evaluation of Turkish Artificial Intelligence-Generated Responses about Osteoporosis in Terms of Accuracy, Completeness, and Readability”. Pamukkale Medical Journal 19 (4): 725-34. https://doi.org/10.31362/patd.1933335.
EndNote
Akıncı MG, Atıgan A, Suskun C, Yenidünya A (October 1, 2026) Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability. Pamukkale Medical Journal 19 4 725–734.
IEEE
[1]M. G. Akıncı, A. Atıgan, C. Suskun, and A. Yenidünya, “Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability”, Pam Med J, vol. 19, no. 4, pp. 725–734, Oct. 2026, doi: 10.31362/patd.1933335.
ISNAD
Akıncı, Meltem Güneş - Atıgan, Alev - Suskun, Ceyda - Yenidünya, Atakan. “Evaluation of Turkish Artificial Intelligence-Generated Responses about Osteoporosis in Terms of Accuracy, Completeness, and Readability”. Pamukkale Medical Journal 19/4 (October 1, 2026): 725-734. https://doi.org/10.31362/patd.1933335.
JAMA
1.Akıncı MG, Atıgan A, Suskun C, Yenidünya A. Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability. Pam Med J. 2026;19:725–734.
MLA
Akıncı, Meltem Güneş, et al. “Evaluation of Turkish Artificial Intelligence-Generated Responses about Osteoporosis in Terms of Accuracy, Completeness, and Readability”. Pamukkale Medical Journal, vol. 19, no. 4, Oct. 2026, pp. 725-34, doi:10.31362/patd.1933335.
Vancouver
1.Meltem Güneş Akıncı, Alev Atıgan, Ceyda Suskun, Atakan Yenidünya. Evaluation of Turkish artificial intelligence-generated responses about osteoporosis in terms of accuracy, completeness, and readability. Pam Med J. 2026 Oct. 1;19(4):725-34. doi:10.31362/patd.1933335

Creative Commons Lisansı

Pamukkale Medical Journal is licensed under the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY NC).