UCLA and UC Davis are co-leading a multi-institutional clinical trial to evaluate whether artificial intelligence can help support radiologists in interpreting mammograms more accurately.

The study, known as the PRISM Trial (Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography), is supported by a $16 million award from the Patient-Centered Outcomes Research Institute (PCORI). It will involve hundreds of thousands of mammograms interpreted at academic medical centers and breast imaging facilities in California, Florida, Massachusetts, Washington and Wisconsin. 

The AI support tool studied will be Transpara by ScreenPoint Medical with clinical workflow integration provided by the Aidoc aiOS platform.

The study’s goal is improving breast cancer screening and reducing unnecessary callbacks and anxiety for patients. 

“This is the first large-scale randomized trial of AI in breast cancer screening in the United States,” said Joann Elmore, M.D., M.P.H.,  in a statement. She is dual principal investigator and lead of the Administrative Coordinating Site, and professor of medicine at the David Geffen School of Medicine at UCLA and of health policy and management at the UCLA Fielding School of Public Health. “We’re looking carefully and objectively at whether AI helps or hinders — and for whom. Expert radiologists remain in the driver’s seat for all interpretations.”

“We’re rigorously evaluating whether AI-assisted interpretation improves screening outcomes,” said Diana Migliorette, M.D., in a statement. She is a professor and division chief of biostatistics at the UC Davis Department of Public Health Sciences and serves as dual principal investigator and lead of the study’s data coordinating center, which will be based at UC Davis Health. “The goal is not to replace radiologists with AI but to see how effective AI could be as a co-pilot in reading mammography.”

In addition to analyzing cancer detection and recall rates, the study will include focus groups and surveys to capture how patients and radiologists perceive and trust AI-assisted care.

The PRISM trial brings together seven academic medical centers:
• UCLA (Administrative Coordinating Site led by Dual-Principal Investigator, Dr. Joann Elmore; Co-Principal Investigator and Site PI, Dr. Hannah Milch)
• UC Davis (Data Coordinating Center led by Dual-Principal Investigator, Dr. Diana Miglioretti)
• Boston Medical Center (Site Principal Investigator, Dr. Clare B. Poynton)
• UC San Diego Health (Site Principal Investigator, Dr. Haydee Ojeda-Fournier)
• University of Miami (Site Principal Investigator, Dr. Jose M. Net)
• University of Washington – Fred Hutchinson Cancer Center (Site Principal Investigator, Dr. Janie M. Lee)
• University of Wisconsin–Madison (Co-Principal Investigator, Dr. Christoph I. Lee; Site Principal Investigators, Dr. Mai Elezaby and Dr. Ryan Woods)

Patient-centered by design 

The researchers say that what makes PRISM different is its emphasis on patient-centered research. The trial was developed in close partnership with patient advocates, clinicians, health system leaders and policymakers.

Each participating facility will continue routine screening as usual, with no changes to the patient experience. Mammograms will be randomly assigned to be interpreted either by a radiologist on their own or with assistance from an FDA-cleared AI support tool. In all cases, a radiologist reads the exam and makes the final decision.