DIAGNOSIS AND MANAGEMENT DECISIONS OF LARGE LANGUAGE MODELS IN PEDIATRIC SUPRACONDYLAR HUMERUS FRACTURES: AN AAOS GUIDELINE-BASED COMPARATIVE STUDY
Öz
Objective: This study aimed to evaluate the diagnostic performance and clinical safety of large language models (ChatGPT 5.2 Thinking, Gemini 3.1 Pro, and Claude Sonnet 4.6) in detecting pediatric supracondylar humerus (SCH) fractures, classifying them according to the Gartland system, and providing treatment recommendations based on American Academy of Orthopedic Surgeons (AAOS) clinical practice guidelines.
Material and Methods: In this retrospective observational study, radiographs and clinical data from 128 pediatric patients presenting with elbow trauma (84 fractures and 44 non-fractures) were analyzed. The reference standard was established through consensus evaluation by orthopedic specialists according to AAOS guidelines. Anonymized AP and lateral elbow radiographs, along with age, sex, and brief clinical history, were provided to each model. Diagnostic performance was assessed using sensitivity, specificity, and overall accuracy. Agreement in Gartland classification was evaluated using Cohen’s kappa (κ). Clinical safety was examined by analyzing under-treatment and over-treatment risks in surgical decision recommendations.
Results: Gemini 3.1 demonstrated the highest sensitivity for fracture detection (96%) but had low specificity (41%). ChatGPT 5.2 showed a more balanced profile with both sensitivity and specificity of 64%, whereas Claude 4.6 demonstrated the lowest overall diagnostic accuracy (55%). In Gartland classification, Gemini 3.1 achieved the highest agreement (κ=0.60), while Claude 4.6 showed the lowest (κ=0.33). Regarding treatment recommendations, Gemini 3.1 avoided under-treatment of surgical cases but produced substantial over-treatment, whereas ChatGPT 5.2 missed 40% of surgically indicated cases.
Conclusion: Although LLMs may offer supportive insights in radiographic interpretation, their current performance demonstrates considerable risks of false-positive and false-negative decisions. These findings indicate that LLMs are not yet sufficiently reliable for independent clinical decision-making in pediatric SCH fractures, and expert oversight remains essential.
Anahtar Kelimeler
Etik Beyan
Kaynakça
- 1. Dave T, Athaluri SA, Singh S. ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front Artif Intell. 2023;6:1169595.
- 2. Omiye JA, Gui H, Rezaei SJ, Zou J, Daneshjou R. Large Language models in medicine: the potentials and pitfalls: a narrative review. Ann Intern Med. 2024;177(2):210-20.
- 3. Giorgino R, Alessandri-Bonetti M, Luca A, Migliorini F, Rossi N, Peretti G, et al. ChatGPT in orthopedics: a narrative review exploring the potential of artificial intelligence in orthopedic practice. Front Surg. 2023;10:1284015.
- 4. Tyrrell Burrus M, Werner BC, Starman JS, Kurkis GM, Pierre JM, Diduch DR, et al. Patient perceptions and current trends in Internet use by orthopedic outpatients. HSS J. 2017;13(3):271-5.
- 5. Kolac UC, Oral M, Sili MV, Ibik S, Aydinoglu HS, Bakircioglu S, et al. Identifying risk factors for open reduction in pediatric supracondylar humerus fractures. J Pediatr Orthop. 2024;44:573-8.
- 6. Yilmaz T, Dur IH, Kabakci T, Bulut MA, Akgok B, Kolac UC, et al. Effect of fracture level on optimal Kirschner wire configuration in pediatric supracondylar humerus fractures: A finite element analysis. Jt Dis Relat Surg. 2025;36(3):648-58.
- 7. Heggeness MH, Sanders JO, Murray J, Pezold R, Sevarino KS. Management of Pediatric Supracondylar Humerus Fractures. J Am Acad Orthop Surg. 2015;23(10):e49-51.
- 8. Wilkins KE. Fractures and dislocations of the elbow region. In: Rockwood CA Jr, Wilkins KE, King RE, eds. Fractures in children. Vol 3, 4th ed. Philadelphia: Lippincott-Raven, 1996. p. 680-1.
Ayrıntılar
Birincil Dil
İngilizce
Konular
Cerrahi (Diğer)
Bölüm
Araştırma Makalesi
Yazarlar
Murat Alparslan
0009-0005-9491-6427
Türkiye
Yayımlanma Tarihi
15 Haziran 2026
Gönderilme Tarihi
13 Mart 2026
Kabul Tarihi
11 Mayıs 2026
Yayımlandığı Sayı
Yıl 2026 Cilt: 16 Sayı: 2