Poster 247. Bot vs. Doc – Who is Better at Reading Proximal Humerus Fracture X-Rays? Authors: Kyle K Obana, Mark Ren, Andrew J Luzzi, Matthew R LeVasseur, Hasani W Swindell, William N Levine Published: 2026 ABSTRACT AbstractObjective:Artificial intelligence (AI) is becoming increasingly utilized as a source of convenient, efficient, and cost-effective information. Considering the potential utility of ChatGPT as an adjuvant in clinical decision making, the current study evaluates 1) the accuracy of ChatGPT-5 at evaluating shoulder x-rays containing either normal or proximal humerus fracture (PHFx) diagnoses and 2) interrater reliability between ChatGPT and orthopedic surgeons at different levels of training.Methods:The Stanford University Musculoskeletal Radiographs (MURA) publicly accessible dataset was utilized, and 70 x-rays (35 PHFx, 35 normal) were analyzed after inclusion and exclusion criteria were applied. X-rays were reviewed independently by an orthopedic surgery junior resident, senior resident, shoulder/elbow fellow, and shoulder/elbow fellowship-trained attending. X-rays for each patient were uploaded to ChatGPT-5 (released August 2025, OpenAI, San Francisco, CA) and questions were asked using a response-based algorithm (Figure 1).Results:ChatGPT demonstrated a sensitivity of 61.8% and specificity of 74.3% for PHFx x-rays and an overall accuracy of 67.1%. ChatGPT incorrectly diagnosed 25.7% of normal X-rays with a fracture or dislocation (Table 1). ChatGPT incorrectly diagnosed 22.9% of isolated PHFx X-rays as normal, 8.6% with an isolated dislocation, and 5.7% with a PHFx dislocation. ChatGPT diagnosed 58.1% PHFx involving just the SN and 41.9% involving both the SN and GT. ChatGPT classified PHFx as 90.3% Neer 2-part and 9.7% 3-part fractures (Table 2) Interrater reliability for ChatGPT was slight for displaced parts and poor for fractured part, Neer parts, and located glenohumeral joint (Table 3). Junior and senior residents had moderate to substantial agreement with the attending reads (fractured part, displaced parts, Neer parts), while the fellow had substantial to almost perfect agreement.Conclusions:This study demonstrates that ChatGPT-5 is highly inaccurate at identifying PHFx on shoulder x-rays, characterizing the fracture patterns, and providing accurate interpretations of shoulder x-rays. Overreliance on generative AI to guide clinical decisions risks harm to the patients and should be approached with limited credence.