AI in Breast Cancer Screening: The PRISM Trial Unveiled
The PRISM Trial, led by UCLA, aims to determine if AI can improve breast cancer screening accuracy and reduce unnecessary callbacks. Discover the potential a...
Key Takeaways
- The PRISM Trial is the first large-scale randomized study of AI in breast cancer screening in the U.S.
- The study involves seven leading academic medical centers and hundreds of thousands of mammograms.
- Patient-centered design includes focus groups and surveys to assess AI's impact on trust and perception.
The PRISM Trial: A Pioneering Study in AI and Breast Cancer Screening
The University of California, Los Angeles (UCLA) and the University of California, Davis (UC Davis) are leading a groundbreaking, multi-institutional clinical trial known as the PRISM Trial (Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography). This $16 million study, funded by the Patient-Centered Outcomes Research Institute (PCORI), aims to evaluate the effectiveness of artificial intelligence (AI) in supporting radiologists during mammography interpretation. The ultimate goal is to enhance the accuracy of breast cancer screening and reduce unnecessary callbacks and patient anxiety.
A Pressing Question in Breast Cancer Care
Breast cancer remains one of the leading causes of cancer death among women in the U.S. While routine mammography screening has been shown to reduce mortality through early detection, it also comes with significant drawbacks. False positives lead to unnecessary testing, increased anxiety, and higher costs, while missed cancers can have dire consequences. The PRISM Trial seeks to address these issues by rigorously evaluating the role of AI in breast cancer screening.
Key Objectives:
- Improve Cancer Detection:** Determine whether AI can help radiologists identify more cancers.
- Reduce False Positives:** Assess whether AI can reduce the number of exams that turn out to be normal.
- Evaluate Patient Impact:** Understand how patients perceive and trust AI-assisted care.
Patient-Centered by Design
What sets the PRISM Trial apart is its emphasis on patient-centered research. The trial was developed in close collaboration 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 alone or with assistance from an FDA-cleared AI support tool. In all cases, the final decision will be made by the radiologist.
Collaborative Effort Across Six States
The PRISM Trial brings together seven leading academic medical centers:
- UCLA (Administrative Coordinating Site led by Dr. Joann Elmore; Co-Principal Investigator and Site PI, Dr. Hannah Milch)
- UC Davis (Data Coordinating Center led by 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)
Striking the Right Balance
Dr. Joann Elmore, Dual Principal Investigator and lead of the Administrative Coordinating Site, emphasized that the goal is not to replace human expertise but to understand how AI might complement it. “Our expert radiologists will continue to make the final call. AI may be a useful co-pilot, but it’s the radiologist who holds the wheel,” she said. The trial is expected to inform future policy decisions, best practices in screening, and the effective integration of emerging technologies into patient care.
The Bottom Line
The PRISM Trial represents a significant step forward in the application of AI in healthcare. By providing rigorous, patient-centered evidence, it aims to clarify the role of AI in breast cancer screening, ultimately leading to better outcomes and improved patient experiences.
Frequently Asked Questions
What is the PRISM Trial?
The PRISM Trial (Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography) is a large-scale, multi-institutional clinical trial led by UCLA and UC Davis to evaluate the effectiveness of AI in breast cancer screening.
How does the PRISM Trial differ from other studies?
The PRISM Trial stands out due to its patient-centered design, involving close collaboration with patient advocates, clinicians, health system leaders, and policymakers. It also includes focus groups and surveys to assess patient and radiologist perceptions of AI.
What are the key objectives of the PRISM Trial?
The main objectives are to improve cancer detection, reduce false positives, and evaluate the impact of AI on patient trust and perception.
How many medical centers are involved in the PRISM Trial?
The PRISM Trial involves seven leading academic medical centers across six states, including UCLA, UC Davis, Boston Medical Center, UC San Diego Health, University of Miami, University of Washington, and University of Wisconsin–Madison.
What is the role of radiologists in the PRISM Trial?
Radiologists remain in the driver’s seat for all interpretations, making the final decision on mammograms. The AI support tool is designed to assist, not replace, their expertise.
