An AI tool developed by New York City-based NYU Langone Health researchers identified gaps in radiology residents’ clinical exposure and recommended targeted teaching cases with more than 90% accuracy.
Researchers used ChatGPT-4o to read summary sections of residents’ daily clinical reports and select three to five teaching cases each night for each resident, according to a Sept. 30 news release. The AI prioritized conditions residents had seldom encountered.
The selected cases appeared on residents’ workstations alongside their regular clinical work and were discussed with supervising physicians. The approach increased the breadth of pathologies residents encountered without reducing their experience with real patient cases.
Before deploying the tool, researchers developed a curriculum of conditions residents should encounter during their first three years of training. Faculty experts across five imaging specialties identified the conditions and established target exposure levels.
Researchers plan to expand the tool to additional subspecialties, including cardiac imaging, nuclear medicine, breast imaging and interventional radiology.
