Staging Femoral Head Osteonecrosis with General-Purpose AI: Lessons from the Ficat-Arlet Classification

This study aimed to conceptually evaluate the diagnostic capacity and limitations of a general-purpose vision-language model (ChatGPT-4o) in the radiographic staging of femoral head avascular necrosis (AVN) according to the Ficat-Arlet (FA) classification. Rather than proposing clinical implementation, this proof-of-concept investigation was designed to delineate the boundaries of general-purpose artificial intelligence (AI) in radiographic reasoning. A total of 240 anteroposterior pelvic X-ray images with corresponding clinical and magnetic resonance imaging (MRI)-based reference staging were retrospectively analyzed. Only plain radiographs were uploaded to ChatGPT-4o; no MRI data were provided. Each image was evaluated in a separate, independent session using a standardized English-language prompt. The model's staging outputs were compared with ground-truth labels using sensitivity, specificity, precision, accuracy, and area under the receiver operating characteristic curve (AUC). ChatGPT-4o achieved a micro-averaged sensitivity of 25.8%, specificity of 79.5%, and mean AUC of 0.55 across all FA stages. The highest sensitivity was observed in Stage 0 (54.2%) and the lowest in Stage 4 (10.4%). Statistical comparison across stages revealed significant variation in diagnostic metrics, indicating stage-dependent inconsistency. While ChatGPT-4o demonstrated partial capacity for radiographic reasoning, its limited sensitivity, low AUC, and inconsistency across stages underscore the conceptual boundaries of general-purpose AI in diagnostic image interpretation. These findings highlight the necessity for task-specific training and balanced datasets to achieve reliable performance in orthopedic imaging.