JORR
Journal of Orthopedics Research and Rehabilitation

The Journal of Orthopedics Research and Rehabilitation welcomes scholarly papers in orthopaedic surgery, physical therapy and rehabilitation, physiotherapy, neurology and clinic anesthesiology and reanimation.

eISSN: 2980-0560
Creative Commons CC BY-NC-ND 4.0 International License.
EndNote Style

Online Manuscript System

Index
Original Article
Comparison of ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery
Abstract
Aims: To compare ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery in terms of accuracy, informativeness, comprehensibility, and currency.
Methods: A Google search performed with a newly created account without previous search activity was used to identify patient-oriented questions about hallux valgus surgery. Two researchers reviewed 100 questions and consolidated overlapping items into 10 representative questions. On February 1, 2026, the same questions were submitted in English to ChatGPT-5.2 and DeepSeek-V3.2. The first response from each model was recorded without editing. Ten orthopedic specialists with at least five years of professional experience independently and blindly rated each response on a 5-point Likert scale for accuracy, informativeness, comprehensibility, and currency. Paired model scores were compared using the Wilcoxon signed-rank test.
Results: Both models answered all 10 questions. ChatGPT-5.2 had numerically higher mean scores for accuracy (4.7±0.3 vs 4.6±0.4; p=0.214), informativeness (4.6±0.4 vs 4.4±0.5; p=0.081), comprehensibility (4.6±0.4 vs 4.5±0.4; p=0.197), and currency (4.5±0.4 vs 4.3±0.5; p=0.064). None of the between-model differences reached statistical significance.
Conclusion: ChatGPT-5.2 and DeepSeek-V3.2 both generated responses that orthopedic specialists rated highly across the four evaluated domains. Neither model demonstrated statistically significant superiority. These systems may support patient education as supplementary information tools, but their outputs should remain subject to clinical verification and should not replace individualized patient-physician communication.

Keywords : Hallux valgus, patient education as topic, large language models, health literacy, comprehension, generative artificial intelligence

Download Article
Ethical Statement

The study did not involve patients, patient records, identifiable personal data, biological materials, or any clinical intervention. The orthopedic specialists served solely as voluntary professional evaluators of AI-generated responses. No institutional ethics committee approval or formal exemption was obtained.

Informed Consent

Patient informed consent was not applicable because no patients or identifiable patient data were included in the study. The orthopedic specialists participated voluntarily as professional evaluators and provided verbal consent to participate.

Author Contributions

Concept: VEÇ, FÖ, MK; Design: VEÇ, FÖ; Data Collection and/or Processing: VEÇ, FÖ, BK; Analysis and/or Interpretation: VEÇ, BK, AFT, HO; Literature Review: VEÇ, FÖ, MK; Writing the Article: VEÇ, FÖ, AFT; Critical Review: VEÇ, FÖ, MK, BK, AFT, HO.

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. Cai Y, Song Y, He M, et al. Global prevalence and incidence of hallux valgus: a systematic review and meta-analysis. J Foot Ankle Res. 2023; 16(1):63. doi:10.1186/s13047-023-00661-9
2. Lewis TL, See A, Thomas M, et al. The inaugural UK National Hallux Valgus Think Tank: identification of key issues and strategies to improve clinical care for patient benefit. Bone Jt Open. 2025;6(4):432-439. doi:10.1302/2633-1462.64.BJO-2024-0212.R1
3. Cotchett M, Bramston C, Bergin S, Menz HB, Jessup R. Lived experience of people with painful hallux valgus: a descriptive qualitative study. Musculoskeletal Care. 2023;21(4):1421-1428. doi:10.1002/msc.1822
4. Dias CGP, Godoy-Santos AL, Ferrari J, Ferretti M, Lenza M. Surgical interventions for treating hallux valgus and bunions. Cochrane Database Syst Rev. 2024;7(7):CD013726. doi:10.1002/14651858.CD013726.pub2
5. Ji L, Wang K, Ding S, Sun C, Sun S, Zhang M. Minimally invasive vs open surgery for hallux valgus: a meta-analysis. Front Surg. 2022;9: 843410. doi:10.3389/fsurg.2022.843410
6. Tartaglione JP, Rosenbaum AJ, Abousayed M, Hushmendy SF, DiPreta JA. Evaluating the quality, accuracy, and readability of online resources pertaining to hallux valgus. Foot Ankle Spec. 2016;9(1):17-23. doi:10.1177/1938640015592840
7. Hlavinka WJ, Sontam TR, Gupta A, Croen BJ, Abdullah MS, Humbyrd CJ. Are large language models a useful resource to address common patient concerns on hallux valgus? A readability analysis. Foot Ankle Surg. 2025;31(1):15-19. doi:10.1016/j.fas.2024.08.002
8. Yüksel B, Uçar SB, Özdemir E, Ayık G, Kaymakoğlu M, Huri G. Can artificial intelligence provide reliable patient education in minimally invasive bunion surgery? A comparative study of ChatGPT 5.2 and Gemini. Foot Ankle Surg. Published online June 16, 2026. doi:10.1016/j.fas.2026.06.006
9. Karadamar ÖL, Aydilek A. Evaluation of surgical recommendation algorithms in hallux valgus cases using ChatGPT models: an artificial intelligence approach based on 50 simulated scenarios. Acta Orthop Traumatol Turc. 2026;60:e25580. doi:10.5152/j.aott.2026.25580
10. 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
11. Lee P, Bubeck S, Petro J. Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N Engl J Med. 2023;388(13):1233-1239. doi:10.1056/NEJMsr2214184
12. Marcaccini G, Seth I, Xie Y, et al. Breaking bones, breaking barriers: ChatGPT, DeepSeek, and Gemini in hand fracture management. J Clin Med. 2025;14(6):1983. doi:10.3390/jcm14061983
13. Gültekin O, Inoue J, Yilmaz B, et al. Evaluating DeepResearch and DeepThink in anterior cruciate ligament surgery patient education: ChatGPT-4o excels in comprehensiveness, DeepSeek R1 leads in clarity and readability of orthopaedic information. Knee Surg Sports Traumatol Arthrosc. 2025;33(8):3025-3031. doi:10.1002/ksa.12711
14. Bozgeyik B, Öğümsöğütlü E. Can artificial intelligence educate patients? Comparative analysis of ChatGPT and DeepSeek models in meniscus injuries. Healthcare (Basel). 2025;13(22):2980. doi:10.3390/healthcare13222980
15. Bozgeyik B, Öğümsöğütlü E, Huri G. artificial intelligence-based patient information in rotator cuff injuries: a cross-sectional comparative study of ChatGPT and DeepSeek models. Medicine (Baltimore). 2026;105(27):e49658. doi:10.1097/MD.0000000000049658
16. Zhou M, Pan Y, Zhang Y, Song X, Zhou Y. Evaluating AI-generated patient education materials for spinal surgeries: comparative analysis of readability and DISCERN quality across ChatGPT and DeepSeek models. Int J Med Inform. 2025;198:105871. doi:10.1016/j.ijmedinf.2025.105871
17. Öner SK, Demirkiran ND, Canlı EA, Bilir A. Gonarthrosis Advisor vs ChatGPT-5: quality and readability of artificial intelligence-generated patient education for knee osteoarthritis. Acta Orthop Traumatol Turc. 2026;60(2):e25618. doi:10.5152/j.aott.2026.25618
18. Romoff M, Brunette M, Peterson MK, Hashmi SZ, Kim MS. The role of large language models in improving the readability of orthopaedic spine patient educational material. J Orthop Surg Res. 2025;20(1):531. doi:10.1186/s13018-025-05955-1
19. Nian PP, Williams CJ, Baidya J, Marsh IG, Senthilnathan IS, Maheshwari AV. Evaluation of commonly utilized artificial intelligence large language models in optimizing readability, accuracy, and comprehension of orthopaedic oncology patient educational materials. J Am Acad Orthop Surg. Published online May 26, 2026. doi:10.5435/JAAOS-D-25-00883
20. Pamuk Ç, Uyanık AF, Kuyucu E, Uğurlar M. Can ChatGPT pass the Turkish Orthopedics and Traumatology Board Examination? Turkish orthopedic surgeons versus artificial intelligence. Ulus Travma Acil Cerrahi Derg. 2025;31(3):310-315. doi:10.14744/tjtes.2025.07724
21. Gravel J, D’Amours-Gravel M, Osmanlliu E. Learning to fake it: limited responses and fabricated references provided by ChatGPT for medical questions. Mayo Clin Proc Digit Health. 2023;1(3):226-234. doi:10.1016/j.mcpdig.2023.05.004
22. Keshavarz P, Bagherieh S, Nabipoorashrafi SA, et al. ChatGPT in radiology: a systematic review of performance, pitfalls, and future perspectives. Diagn Interv Imaging. 2024;105(7-8):251-265. doi:10.1016/j.diii.2024.04.003
23. Charnock D, Shepperd S, Needham G, Gann R. DISCERN: an instrument for judging the quality of written consumer health information on treatment choices. J Epidemiol Community Health. 1999;53(2):105-111. doi:10.1136/jech.53.2.105
24. Shoemaker SJ, Wolf MS, Brach C. Development of the Patient Education Materials Assessment Tool (PEMAT): a new measure of understandability and actionability for print and audiovisual patient information. Patient Educ Couns. 2014;96(3):395-403. doi:10.1016/j.pec.2014.05.027
Article available in :
Volume 4, Issue 4, 2026
Page : 101-105
https://doi.org/10.51271/JORR-0080
Article Information
Received : 11 Eyl 2026
Accepted : 26 Eki 2026
Published : 28 Eki 2026
Corresponding Author :

Veysel Emre Çelik: Department of Orthopedics and Traumatology, Kocaeli City Hospital, Kocaeli, Turkiye

[email protected]
Citation : Çelik VE, Öktem F, Karahan M, Kırcal B, Taşkın AF, Olgun H. Comparison of ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery. J Orthop Res Rehabil. 2026;4(4):101-105. doi:10.51271/JORR-0080

Read: 3
Download : 1
Cited: 0
_Footer