Data Science Pathway to Advance AI in Radiology
FORMAL training in artificial intelligence (AI) and machine learning is not routine for radiologists, but a recently developed data science pathway for fourth-year radiology residents could better prepare these clinicians for future technology use and advance uptake in the medical imaging field.
Senior radiologists at the Brigham and Women’s Hospital, Boston, Massachusetts, USA recognised the gap in organised curricula and sought to provide a well-rounded introductory experience to fourth-year residents. Practical problem-solving and guided instruction are key elements of the piloted pathway, which was designed to be used in collaboration with data scientists.
Dr Walter Wiggins, Brigham and Women’s Hospital and co-leader of the study, explained the rationale for creating the data science pathway: “Across the nation there are a number of radiology residency programmes that are trying to figure out how to integrate AI into their training. We thought that perhaps our experience would help other programmes figure out ways to integrate this type of training into either their elective pathways or their more general residency curriculum.”
By working directly with data scientists, the radiology residents were able to better understand how they approach image analysis issues by using machine learning tools. Conversely, the data scientists were able to appreciate how a radiologist will approach an issue in a clinical setting.
“An important component of a curriculum like this is to learn the language the data scientists speak and teach them a little bit about the language that we as radiologists speak so that we can have better, more effective collaborations,” Dr Wiggins stated.
During the time that the pathway has been piloted, the residents have been able to feedback and contribute to the model and tool development, which has led to 12 accepted abstracts for presentation at national meetings.