17 February 2026
Prima - an upcoming AI-powered imaging assistant - is making waves for its high reading accuracy and unique approach to identifying and prioritising time sensitive neurological conditions from imaging data.
Developed in the United States by the University of Michigan, Prima is a Vision Language Model that combines data from imagining with the patients’ medical history, along with the physician's rationale, to analyse neurological conditions, identify urgency and assign priority for care.
Aiming to streamline radiology workflows, predictive AI tools that improve turnaround times like Prima could be used in Australia to increase access to medical imaging services in areas with limited resources, such as remote and rural regions.
Senior author and neurosurgeon at University of Michigan, Todd Hollon M.D., described a need for tools like Prima. “As the global demand for MRI rises and places significant strain our physicians and health systems, our AI model has potential to reduce burden by improving diagnosis and treatment with fast, accurate information.”
As reported in Nature Biomedical Engineering, Prima was trained on the University of Michigan's decades long digitized radiology records, comprising over 200,000 MRI studies representing over 5.6 million imaging sequences. Across 52 radiologic diagnoses Prima outperformed competing AI models with a mean area under the curve of 92.0%.
Although not the first attempt to integrate AI into radiology workflows, Hollon has emphasised Prima's predominant role as a co-pilot for radiologists, in a similar vein to other assistive AI writing tools that are already seeing use.
"Like the way AI tools can help draft an email or provide recommendations, Prima aims to be a co-pilot for interpreting medical imagine studies," said Hollon.
"We believe that Prima exemplifies the transformative potential of integrating health systems and AI-driven models to improve health care through innovation."
Currently, the University says the research surrounding Prima is still “in its initial stage of evaluation”, though Hollon describes Prima’s potential to become “ChatGPT for medical imaging”, should its potential be expanded to include other modes of imaging such as X-rays and mammograms.
