Abstract
OBJECTIVE: Despite the potential of large language models for radiology training, their ability to handle image-based radiological questions remains poorly understood. This study aimed to evaluate the performance of the GPT-4 Turbo and GPT-4o in radiology resident examinations, to analyze differences across question types, and to compare their results with those of residents at different levels. MATERIALS AND METHODS: A total of 776 multiple-choice questions from the Korean Society of Radiology In-Training Examinations were used, forming two question sets: one originally written in Korean and the other translated into English. We evaluated the performance of GPT-4 Turbo (gpt-4-turbo-2024-04-09) and GPT-4o (gpt-4o-2024-11-20) on these questions with the temperature set to zero, determining the accuracy based on the majority vote from five independent trials. We analyzed their results using the question type (text-only vs. image-based) and benchmarked them against nationwide radiology residents' performance. The impact of the input language (Korean or English) on model performance was examined. RESULTS: GPT-4o outperformed GPT-4 Turbo for both image-based (48.2% vs. 41.8%, P = 0.002) and text-only questions (77.9% vs. 69.0%, P = 0.031). On image-based questions, GPT-4 Turbo and GPT-4o showed comparable performance to that of 1st-year residents (41.8% and 48.2%, respectively, vs. 43.3%, P = 0.608 and 0.079, respectively) but lower performance than that of 2nd- to 4th-year residents (vs. 56.0%-63.9%, all P ≤ 0.005). For text-only questions, GPT-4 Turbo and GPT-4o performed better than residents across all years (69.0% and 77.9%, respectively, vs. 44.7%-57.5%, all P ≤ 0.039). Performance on the English- and Korean-version questions showed no significant differences for either model (all P ≥ 0.275). CONCLUSION: GPT-4o outperformed the GPT-4 Turbo in all question types. On image-based questions, both models' performance matched that of 1st-year residents but was lower than that of higher-year residents. Both models demonstrated superior performance compared to residents for text-only questions. The models showed consistent performances across English and Korean inputs.