A $16 million trial will investigate how AI tools could help radiologists interpret mammograms more accurately, reducing patient anxiety and unnecessary appointments.
A study led by Sylvester Comprehensive Cancer Center, part of University of Miami Miller School of Medicine (FL, USA) seeks to understand how AI can improve breast cancer screening. The Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography (PRISM) trial will examine hundreds of thousands of mammograms to “assess AI’s true impact”.
Despite huge investments in research, breast cancer remains a leading cause of mortality in US women. Routine mammography has increased the diagnosis of early-stage cancer, but the increased incidence of false positives can lead to unnecessary testing, anxiety and higher costs.
“As the first major randomized trial of AI in breast cancer screening in the US, this study represents a pivotal step,” commented Jose Net, University of Miami Miller School of Medicine and co-principal investigator of the study. “Our goal is to rigorously and objectively assess AI’s impact, identifying who benefits and who may not.”
Bringing transparency to AI in screening
The study brings together experts several health departments across the US. Over the study period, mammograms will either be examined by a radiologist acting on their own, or with the support of Transpare, an AI tool developed by Screenpoint Medical (Netherlands). The patient experience at each treatment center will not be changed in any of the facilities partaking in the study.
“While AI offers substantial promise, it also prompts critical questions,” continued Net. “Our focus is on understanding whether AI genuinely enhances cancer detection by radiologists or simply leads to more false alarms.” However, Net cautions “Our skilled radiologists will always have the final say. While AI can serve as a helpful assistant, it is ultimately the radiologist who is in control.”
Putting patients at the center
PRISM has been supported by Patient-Centered Outcomes Research Institute emphasizing its unique patient-centered approach, Net commented: “This trial presents an opportunity to produce reliable evidence with a strong emphasis on the patient’s perspective.”
Net and the investigating team hope that PRISM will reveal AI’s real-world impact, helping inform future policy decisions and best practices in screening. During the study, they will also conduct focus groups and surveys, to help health centers understand how to most effectively integrate emerging technologies into patient care.
“A trial of this magnitude focusing on AI in breast cancer screening has never been conducted in the US,” concluded Net. “The findings will influence not only clinical practices but also insurance policies, technology integration and patient interactions.”
Click here to sign up to our dedicated breast cancer news round-up