Updated large language models have been trained to process both text- and image-based questions, potentially making them more effective in radiology settings.
When trained with high-fidelity simulation, junior radiology residents can master the discipline of reading whole-body CTs right at the trauma scanner—and doing so with high diagnostic accuracy, work speed and interpretive confidence.
When resident teams included experienced fourth-year trainees, the resident/attending pairs cut overall median report turnaround times by seven minutes versus attending-only efforts.
Out of 10 mock exams, the AI candidate passed two, achieving an overall accuracy of 79.5%, suggesting that the candidate is not quite “ready to graduate.”