SavedAdd your journal

Journals / Eskisehir Medical Journal / 2026 / Volume: 7 Issue: 1

Is Artificial Intelligence Our Ally in Post-Earthquake Rehabilitation? Utilization and Accuracy of AI-Derived Large Language Models for Crush Injuries

Deprem Sonrası Rehabilitasyon Sürecinde Yapay Zeka Dostumuz mudur? Yapay Zekadan Türetilmiş Geniş Dil Modellerinin Crush Yaralanmalarında Kullanımı ve Doğruluğu

Onur Engin(Izmir Democracy University, School of Medicine, Department of Physical Medicine and Rehabilitation)0000-0001-7490-9418
Kadir Songür(Hatay Dörtyol State Hospital, Department of Physical Medicine and Rehabilitation)0000-0002-8797-4195
Bekir Tetik(3 Manisa Turgutlu State Hospital, Department of Physical Medicine and Rehabilitation)0000-0002-4888-578X
Pages
—
Publication Date
2026-02-24
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Conclusion: These findings suggest that LLMs can be valuable tools in managing crush injuries in disaster situations, though caution is needed due to occasional inaccuracies and hallucinated references.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Introduction: Crush injuries are a significant concern in disaster scenarios such as earthquakes.
📊
Key Findings & Data:This study aims to evaluate the performance of four AI-derived LLMs, ChatGPT-3.5, ChatGPT-4, Bing AI, and Google Gemini, in providing accurate and reliable information about crush injuries.
💡
Conclusion & Impact:Conclusion: These findings suggest that LLMs can be valuable tools in managing crush injuries in disaster situations, though caution is needed due to occasional inaccuracies and hallucinated references.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:crush injury · crush syndrome · artificial intelligence

Abstract

Introduction: Crush injuries are a significant concern in disaster scenarios such as earthquakes. These injuries may lead to serious complications such as crush syndrome and compartment syndrome. Large language models, which enable rapid access to information, are anticipated to serve as valuable information sources for both patients and physicians, particularly in the management of these injuries that are frequently encountered during disaster periods. This study aims to evaluate the performance of four AI-derived LLMs, ChatGPT-3.5, ChatGPT-4, Bing AI, and Google Gemini, in providing accurate and reliable information about crush injuries. Methods: A total of 34 questions related to crush injuries were formulated, 17 of which were designed to simulate inquiries from healthcare professionals and 17 from patients directed toward LLMs. The responses were evaluated by three physiatrists using a 3-point Likert scale as follows: (1) accurate and sufficient, (2) partially accurate but sufficient, and (3) inaccurate and insufficient. In addition, the references provided by the models were analyzed in terms of their accuracy and relevance. Categorical variables were compared using the chi-squared test with Bonferroni correction, and group differences in non-parametric data were analyzed using the Kruskal–Wallis test. Results: When all 34 questions were analyzed together, ChatGPT-3.5 and Google Gemini each provided accurate and sufficient answers to 88.23% (n=30) of the questions, while ChatGPT-4 provided such answers to 82.35% (n=28), and Bing AI to only 55.88% (n=19). Bing AI had the highest mean Likert score among the models, indicating the lowest performance (p=0.002). The number of correct references was higher for ChatGPT-4 and ChatGPT-3.5 than the others (p<0.001), whereas ChatGPT-3.5 and Bing AI provided significantly more hallucinated references compared to Google Gemini (p=0.01 and p=0.03). Conclusion: These findings suggest that LLMs can be valuable tools in managing crush injuries in disaster situations, though caution is needed due to occasional inaccuracies and hallucinated references.

Özet

Giriş: Yüksek basınç veya darbeye bağlı olarak vücut uzuvlarında meydana gelen crush yaralanmaları, deprem gibi afet senaryolarında önemli bir endişe kaynağıdır. Bu yaralanmalar crush sendromu ve kompartman sendromu gibi ciddi komplikasyonlara yol açabilir. Bu çalışma, ChatGPT-3.5, ChatGPT-4, Bing AI ve Google Gemini olmak üzere dört yapay zeka türevi geniş dil modellerinin crush yaralanmaları hakkında doğru ve güvenilir bilgi sağlamadaki performansını değerlendirmeyi amaçlamaktadır. Metod: Crush yaralanmaları ile ilgili 17'si sağlık çalışanları ve 17'si hastalar için olmak üzere toplam 34 soru formüle edilmiştir. Yanıtlar üç fiziyatrist tarafından 3'lü Likert ölçeği kullanılarakderecelendirilmiştir. Ayrıca, modeller tarafından sağlanan referanslar doğruluk ve uygunluk açısından analiz edilmiştir. Modellerin performansını karşılaştırmak için istatistiksel analizler yapılmıştır. Bulgular: Modeller arasında ChatGPT-3.5, ChatGPT-4 ve Google Gemini’nin yanıtlarının %80'inden fazlası bu kriterleri karşılayarak en doğru ve yeterli yanıtları vermiştir. Buna karşın Bing AI, yanıtların yalnızca %55,88'inin doğru ve yeterli olarak sınıflandırılmasıyla daha düşük bir performans göstermiştir. Bing AI, diğer modellere kıyasla en yüksek ortalama Likert puanlarını göstermiştir (ChatGPT-4 ile p=0.039, ChatGPT-3.5 ile p=0.019 ve Google Gemini ile p=0.034). ChatGPT-3.5 ve Bing AI, Google Gemini'den daha fazla halüsinasyonlu referans örneğine sahip olmuştur (ChatGPT-3.5 için p=0.01 ve Bing Al için p=0.03). Sonuç: Bu bulgular, modellerin afet durumlarında crush yaralanmalarının yönetiminde değerli araçlar olabileceğini, ancak zaman zaman ortaya çıkan yanlış ve/veya halüsinasyonlu referanslar nedeniyle dikkatli olunması gerektiğini göstermektedir.

🔖

Cite This Article

Engin, O., Songür, K., Tetik, B. (2026). Is Artificial Intelligence Our Ally in Post-Earthquake Rehabilitation? Utilization and Accuracy of AI-Derived Large Language Models for Crush Injuries. Eskisehir Medical Journal, Volume: 7 Issue: 1. https://doi.org/10.48176/esmj.2026.239

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. Michaelson M. Crush injury and crush syndrome. World J Surg. 1992;16(5):899-903.
  2. Yazici R, İlçin C, Özsu T, Demirtakan T, Kalafat UM, Dogan S. A Comprehensive Review for Refreshing the Crush Syndrome Knowledge After the Devastating Earthquake in Türkiye. Comprehensive Medicine, 2023;15(2):165-70.
  3. Garner MR, Taylor SA, Gausden E, et al. Compartment syndrome: diagnosis, management, and unique concerns in the twenty-first century. HSS J. 2014;10(2):143-152.
  4. Thirunavukarasu AJ, Ting DSJ, Elangovan K, et al. Large language models in medicine. Nat Med. 2023;29(8):1930-40.
  5. Demirkiran O, Dikmen Y, Utku T, et al. Crush syndrome patients after the Marmara earthquake. Emerg Med J. 2003;20(3):247-50.
  6. Chen Y, Zhang S, Tang N, et al. Using Google web search to analyze and evaluate the application of ChatGPT in femoroacetabular impingement syndrome. Front Public Health. 2024;12:1412063.
  7. Zhang L, Tashiro S, Mukaino M, Yamada S. Use of artificial intelligence large language models as a clinical tool in rehabilitation medicine: a comparative test case. J Rehabil Med. 2023;55:jrm13373.
  8. Seth I, Lim B, Xie Y, et al. Comparing the Efficacy of Large Language Models ChatGPT, BARD, and Bing AI in Providing Information on Rhinoplasty: An Observational Study. Aesthet Surg J Open Forum. 2023;5:ojad084.
  9. Ferber D, Kather JN. Large Language Models in Uro-oncology. Eur Urol Oncol. 2024;7(1):157-9.
  10. Abbas A, Rehman MS, Rehman SS. Comparing the Performance of Popular Large Language Models on the National Board of Medical Examiners Sample Questions. Cureus. 2024;16(3):e55991.
  11. Kung TH, Cheatham M, Medenilla A, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digital Health. 2023;2(2): e0000198.
  12. Binkley JM, Kemp KM. Mobilization of Resources and Emergency Response on the National Scale. Surg Clin North Am. 2022;102(1):169-80.
  13. Preiksaitis C, Ashenburg N, Bunney G, et al. The Role of Large Language Models in Transforming Emergency Medicine: Scoping Review. JMIR Med Inform. 2024;12:e53787.
  14. Nguyen TP, Carvalho B, Sukhdeo H, et al. Comparison of artificial intelligence large language model chatbots in answering frequently asked questions in anaesthesia. BJA Open. 2024;10:100280.
  15. Durmaz Engin C, Karatas E, Ozturk T. Exploring the Role of ChatGPT-4, BingAI, and Gemini as Virtual Consultants to Educate Families about Retinopathy of Prematurity. Children (Basel). 2024;11(6):750.
  16. Ferro Desideri L, Roth J, Zinkernagel M, Anguita R. Application and accuracy of artificial intelligence-derived large language models in patients with age related macular degeneration. Int J Retina Vitreous. 2023;9(1):71.
  17. Dhanvijay AKD, Pinjar MJ, Dhokane N, et al. Performance of Large Language Models (ChatGPT, Bing Search, and Google Bard) in Solving Case Vignettes in Physiology. Cureus. 2023;15(8):e42972.
  18. Giannakopoulos K, Kavadella A, Aaqel Salim A, et al. Evaluation of the Performance of Generative AI Large Language Models ChatGPT, Google Bard, and Microsoft Bing Chat in Supporting Evidence-Based Dentistry: Comparative Mixed Methods Study. J Med Internet Res. 2023;25:e51580.
  19. Zúñiga Salazar G, Zúñiga D, Vindel CL, et al. Efficacy of AI Chats to Determine an Emergency: A Comparison Between OpenAI's ChatGPT, Google Bard, and Microsoft Bing AI Chat. Cureus. 2023;15(9):e45473.
  20. Thirunavukarasu AJ, Hassan R, Mahmood S, et al. Trialling a Large Language Model (ChatGPT) in General Practice With the Applied Knowledge Test: Observational Study Demonstrating Opportunities and Limitations in Primary Care. JMIR Med Educ. 2023;9:e46599.
  21. Eysenbach G. The Role of ChatGPT, Generative Language Models, and Artificial Intelligence in Medical Education: A Conversation With ChatGPT and a Call for Papers. JMIR Med Educ. 2023;9:e46885.
  22. 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.