The Reading Room Podcast: Emerging Concepts with AI Integration in Radiology

While post-deployment monitoring of AI tools in radiology can be challenging, Joseph Cavallo, MD, MBA, noted key steps they have taken at the Yale University School of Medicine to address this issue.

In a recent Reading Room podcast, Dr. Cavallo said immediate feedback mechanisms the radiology department has in place with AI vendors enable radiologists to provide simple click notification of AI misses with little disruption to imaging workflows. The radiology department also established system macros that help radiologists explain false positives with adjunctive AI in radiology reports, according to Dr. Cavallo.

“This helps clear up confusion if the referring providers see some of the AI-generated notations or alerts within the PACS system themselves, since everybody has access to the PACS images now. It also helps us from a tracking standpoint if we wanted to be able to see within the reports, not just the external AI data, where we're disagreeing with an AI finding,” explained Dr. Cavallo, an assistant professor of radiology and biomedical imaging at the Yale University School of Medicine.

For radiology educators, Dr. Cavallo said there is a balancing act with the increasing advent of AI in radiology. Ensuring an “ironclad” clinical foundation remains essential in the training of residents and fellows. However, Dr. Cavallo says incorporating data literacy concepts is important to show upcoming radiologists how to appropriately leverage AI tools while being wary about potential automation bias and deskilling.

“AI is becoming an integral part of the radiologist workflow, and the onus is on the trainers to make sure that the residents and fellows are well versed with these tools and are in a position to leverage them themselves moving forward. We've made some internal decisions to try and balance those two forces, and I'm sure different institutions are handling it differently,” noted Dr. Cavallo, an assistant director of informatics for clinical artificial intelligence in radiology at the Yale University School of Medicine.

For more insights from Dr. Cavallo, listen below or subscribe on your favorite podcast platform.

(Editor’s note: This podcast was originally published as a video interview at the following link: https://www.diagnosticimaging.com/view/current-perspectives-integrating-ai-radiology .)