Journals / Anatolian Journal of Emergency Medicine / 2026 / Cilt: 9 Sayı: 3

Diagnostic Performance of a Generative Artificial Intelligence Model in Pelvic Ring and Acetabular Fractures: A Reliability and Validity Study

Pelvik Halka ve Asetabular Kırıklarda Üretken Yapay Zeka Modelinin Tanısal Performansı: Güvenilirlik ve Geçerlilik Çalışması

Serdar Orhan(Marmara University Pendik Training and Research Hospital, Department of Orthopaedics and Traumatology)0000-0002-1358-5613
Turgut Dinçal(Marmara University Pendik Training and Research Hospital, Department of Orthopaedics and Traumatology)0000-0002-6992-3749
Ufuk Arzu(Marmara University Pendik Training and Research Hospital, Department of Orthopaedics and Traumatology)0000-0002-6371-2211
İhsan Özdamar(Marmara University Pendik Training and Research Hospital, Department of Orthopaedics and Traumatology)0000-0002-0685-9284
Batuhan Gencer(Marmara University Pendik Training and Research Hospital, Department of Orthopaedics and Traumatology)0000-0003-0041-7378
Pages
142–148
Publication Date
2026-09-25
🏛️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)

While the AI has been demonstrated to function as a supplementary tool to facilitate preliminary assessment, particularly in light of its optimal negative predictive value in non-fracture cases, its moderate false-negative rate (17%) necessitates a cautious approach.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Aim: The objective of this study was to evaluate the effectiveness, accuracy, and consistency of an AI-powered chatbot (ChatGPT 4.0) in supporting clinical and radiological suspicions in the preliminary diagnosis of pelvic ring and acetabular fractures in situations where expert consultation or tertiary healthcare resources are unavailable.
📊
Key Findings & Data:Material and Methods: A total of 100 antero-posterior (AP) pelvis X-ray images, 88 exhibiting pelvic or peri-acetabular fractures or instability, and all free from copyright restrictions, were presented to ChatGPT 4.0.
💡
Conclusion & Impact:While the AI has been demonstrated to function as a supplementary tool to facilitate preliminary assessment, particularly in light of its optimal negative predictive value in non-fracture cases, its moderate false-negative rate (17%) necessitates a cautious approach.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:ChatGPT · pelvik halka yaralanmaları · asetabulum kırıkları

Abstract

Aim: The objective of this study was to evaluate the effectiveness, accuracy, and consistency of an AI-powered chatbot (ChatGPT 4.0) in supporting clinical and radiological suspicions in the preliminary diagnosis of pelvic ring and acetabular fractures in situations where expert consultation or tertiary healthcare resources are unavailable. Material and Methods: A total of 100 antero-posterior (AP) pelvis X-ray images, 88 exhibiting pelvic or peri-acetabular fractures or instability, and all free from copyright restrictions, were presented to ChatGPT 4.0. In a scenario posing as a medical practitioner without any specialization, currently working in an emergency department in a rural hospital, and without any trauma or radiology specialist capable of evaluating the radiographic images, ChatGPT was asked to diagnose all x-rays, and then asked to confirm the diagnosis. Results: In only 43 (48.9%) of the 88 direct radiographs with fracture and instability findings, ChatGPT 4.0 was able to make a correct diagnosis, with a weak-to-minimal level of agreement between initial and confirmation answers. Furthermore, in 15 radiographs (17%), the fracture or instability was misdiagnosed as "solid," and in 30 radiographs (33.4%), while the presence of fracture or instability was detected, the definitive diagnosis was inaccurate. The pelvic ring and acetabular fractures that ChatGPT 4.0 correctly diagnosed at the highest rate were multiple fractures of the pelvic ring and acetabulum (80%), fractured dislocations of the acetabulum (72.7%), and isolated pubic ramus fractures (62.5%). ChatGPT 4.0 demonstrated the most inaccurate diagnostic performance for the following pelvic ring and acetabulum fractures, with a rate of 0%: femoral neck fractures, isolated iliac crest fractures, and vertically unstable pelvic ring injuries. Conclusion: In circumstances where there is a shortage of radiologists and orthopaedic specialists, such as in contexts where resources are limited or in rural emergency situations, reliance on AI-assisted chatbots such as ChatGPT 4.0 for fracture screening may result in diagnostic oversights or mismanagement. While the AI has been demonstrated to function as a supplementary tool to facilitate preliminary assessment, particularly in light of its optimal negative predictive value in non-fracture cases, its moderate false-negative rate (17%) necessitates a cautious approach.

Özet

Amaç: Bu çalışmanın amacı, uzman konsültasyonu veya üçüncü basamak sağlık hizmetleri kaynaklarının bulunmadığı durumlarda, pelvik halka ve asetabular kırıkların ön tanısında klinik ve radyolojik şüpheleri desteklemede yapay zeka destekli bir sohbet robotunun (ChatGPT 4.0) etkinliğini, doğruluğunu ve tutarlılığını değerlendirmektir. Gereç ve Yöntemler: Telif hakkı kısıtlamaları olmayan, pelvik veya peri-asetabular kırıklar veya instabilite gösteren 88 adet olmak üzere toplam 100 adet antero-posterior (AP) pelvis röntgen görüntüsü ChatGPT 4.0'a sunuldu. Herhangi bir uzmanlığı olmayan, şu anda kırsal bir hastanenin acil servisinde çalışan ve radyografik görüntüleri değerlendirebilecek herhangi bir travma veya radyoloji uzmanı bulunmayan bir tıp pratisyeni rolünde, ChatGPT'den tüm röntgenleri teşhis etmesi ve ardından teşhisi doğrulaması istendi. Bulgular: Kırık ve instabilite bulguları olan 88 direkt radyografinin sadece 43'ünde (%48,9) ChatGPT 4.0 doğru tanı koyabildi ve ilk yanıt ile onay yanıtı arasında zayıf ila minimal düzeyde bir uyum vardı. Ayrıca, 15 radyografide (%17) kırık veya instabilite “sağlam” olarak yanlış teşhis edildi ve 30 radyografide (%33,4) kırık veya instabilite varlığı tespit edilmesine rağmen kesin tanı yanlış çıktı. ChatGPT 4.0'ın en yüksek oranda doğru tanı koyduğu pelvik halka ve asetabulum kırıkları şunlardı: pelvik halka ve asetabulumda çoklu kırıklar (%80), asetabulumda kırık çıkıklar (%72,7) ve izole pubik ramus kırıkları (%62,5). ChatGPT 4.0, %0 oranıyla aşağıdaki pelvik halka ve asetabulum kırıkları için en yanlış tanı performansını gösterdi: femur boynu kırıkları, izole iliak kret kırıkları ve dikey olarak instabil pelvik halka yaralanmaları. Sonuç: Radyolog ve ortopedi uzmanlarının yetersiz olduğu durumlarda, örneğin kaynakların sınırlı olduğu ortamlarda veya kırsal acil durumlarda, kırık taraması için ChatGPT 4.0 gibi AI destekli sohbet robotlarına güvenmek, tanısal gözden kaçırmalara veya yanlış yönetime neden olabilir. AI'nın, özellikle kırık olmayan vakalarda optimal negatif prediktif değeri göz önüne alındığında, ön değerlendirmeyi kolaylaştırmak için tamamlayıcı bir araç olarak işlev gördüğü kanıtlanmış olsa da, orta düzeydeki yanlış negatif oranı (%17) dikkatli bir yaklaşım gerektirmektedir.

🔖

Cite This Article

Orhan, S., Dinçal, T., Arzu, U., Özdamar, İ., Gencer, B. (2026). Diagnostic Performance of a Generative Artificial Intelligence Model in Pelvic Ring and Acetabular Fractures: A Reliability and Validity Study. Anatolian Journal of Emergency Medicine, Cilt: 9 Sayı: 3, 142–148. https://doi.org/10.54996/anatolianjem.1772154

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (19)

  1. Gan W, Ouyang J, Li H, et al. Integrating ChatGPT in Orthopedic Education for Medical Undergraduates: Randomized Controlled Trial. J Med Internet Res. 2024;26:e57037. doi:10.2196/57037.
  2. Kaarre J, Feldt R, Zsidai B, et al. ChatGPT can yield valuable responses in the context of orthopaedic trauma surgery. J Exp Orthop. 2024;11(3):e12047. doi:10.1002/jeo2.12047.
  3. Gencer B, Arzu U, Orhan SS, Dinçal T, Ekinci M. Evaluation of ChatGPT Responses About Sexual Activity After Total Hip Arthroplasty: A Comparative Study with Observers of Different Experience Levels. J Clin Med. 2025;14(9):2942. doi:10.3390/jcm14092942.
  4. Arzu U, Gencer B. To Self-Treat or Not to Self-Treat: Evaluating the Diagnostic, Advisory and Referral Effectiveness of ChatGPT Responses to the Most Common Musculoskeletal Disorders. Diagnostics (Basel). 2025;15(14):1834. doi:10.3390/diagnostics15141834.
  5. Kalem M, Balaban K, Kocaoğlu H, Kından P, Şahin E. Evaluation of ChatGPT responses to common patient questions on ankle fusion. Foot Ankle Surg. 2025:S1268-7731(25)00117-1. doi:10.1016/j.fas.2025.05.001.
  6. Ayık G, Ercan N, Demirtaş Y, Yıldırım T, Çakmak G. Evaluation of ChatGPT-4o's answers to questions about hip arthroscopy from the patient perspective. Jt Dis Relat Surg. 2025;36(1):193-199. doi:10.52312/jdrs.2025.1961.
  7. Karataş Ö, Demirci S, Pota K, Tuna S. Assessing ChatGPT's Role in Sarcopenia and Nutrition: Insights from a Descriptive Study on AI-Driven Solutions. J Clin Med. 2025;14(5):1747. doi:10.3390/jcm14051747.
  8. Özbek EA, Ertan MB, Kından P, Karaca MO, Gürsoy S, Chahla J. ChatGPT Can Offer At Least Satisfactory Responses to Common Patient Questions Regarding Hip Arthroscopy. Arthroscopy. 2025;41(6):1806-1827. doi:10.1016/j.arthro.2024.08.036.
  9. Tangadulrat P, Sono S, Tangtrakulwanich B. Using ChatGPT for Clinical Practice and Medical Education: Cross-Sectional Survey of Medical Students' and Physicians' Perceptions. JMIR Med Educ. 2023;9:e50658. doi:10.2196/50658.
  10. Mika AP, Martin JR, Engstrom SM, Polkowski GG, Wilson JM. Assessing ChatGPT Responses to Common Patient Questions Regarding Total Hip Arthroplasty. J Bone Joint Surg Am. 2023;105(19):1519-1526. doi:10.2106/JBJS.23.00209.
  11. Giorgino R, Alessandri-Bonetti M, Del Re M, Verdoni F, Peretti GM, Mangiavini L. Google Bard and ChatGPT in Orthopedics: Which Is the Better Doctor in Sports Medicine and Pediatric Orthopedics? The Role of AI in Patient Education. Diagnostics (Basel). 2024;14(12):1253. doi:10.3390/diagnostics14121253.
  12. Horiuchi D, Tatekawa H, Oura T, et al. Comparing the Diagnostic Performance of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and Radiologists in Challenging Neuroradiology Cases. Clin Neuroradiol. 2024;34(4):779-787. doi:10.1007/s00062-024-01426-y.
  13. Arruzza ES, Evangelista CM, Chau M. The performance of ChatGPT-4.0o in medical imaging evaluation: a cross-sectional study. J Educ Eval Health Prof. 2024;21:29. doi:10.3352/jeehp.2024.21.29.
  14. Mohammadi M, Parviz S, Parvaz P, et al. Diagnostic performance of ChatGPT in tibial plateau fracture in knee X-ray. Emerg Radiol. 2025;32(1):59-64. doi:10.1007/s10140-024-02298-y.
  15. Phua JK, Tan TSE. Flexing ChatGPT-4o's Diagnostic Muscle: Detection of Fractures in the Ossifying Pediatric Elbow on Radiographs. Diagnostics (Basel). 2025;15(22):2882. doi:10.3390/diagnostics15222882.
  16. Erdem TE, Kirilmaz A, Kekec AF. Diagnostic Performance of ChatGPT-4o in Detecting Hip Fractures on Pelvic X-rays. Cureus. 2025;17(6):e86654. doi:10.7759/cureus.86654.
  17. Temel MH, Erden Y, Bağcıer F. Evaluating artificial intelligence performance in medical image analysis: Sensitivity, specificity, accuracy, and precision of ChatGPT-4o on Kellgren-Lawrence grading of knee X-ray radiographs. Knee. 2025;55:79-84. doi:10.1016/j.knee.2025.04.008.
  18. Horiuchi D, Tatekawa H, Oura T, et al. ChatGPT's diagnostic performance based on textual vs. visual information compared to radiologists' diagnostic performance in musculoskeletal radiology. Eur Radiol. 2025;35(1):506-516. doi:10.1007/s00330-024-10902-5.
  19. Shan G, Chen X, Wang C, et al. Comparing Diagnostic Accuracy of Clinical Professionals and Large Language Models: Systematic Review and Meta-Analysis. JMIR Med Inform. 2025;13:e64963. doi:10.2196/64963.