NYU Langone Tests AI Tool to Fill Radiology Training Gaps

NYU Langone Health said in a press release that an AI tool identified gaps in the pathologies seen by radiology residents and selected targeted teaching cases. The study found that the system identified exposure gaps and suggested needed pathologies with more than 90 percent accuracy.

Researchers created a curriculum of important conditions across abdominal, musculoskeletal, brain, pediatric, and chest imaging. They used ChatGPT-4o to read summaries from residents' daily clinical reports and select three to five teaching cases each night, prioritizing conditions each resident had rarely encountered.

The selected cases appeared on residents' workstations alongside their regular clinical work. Residents reviewed the findings with supervising physicians, increasing the range of pathologies they encountered without reducing their work on real patient cases.