Major National Study Launched to Evaluate AI in Breast Cancer Screening

Landmark Study to Evaluate AI in Breast Cancer Screening

A groundbreaking clinical trial, known as the PRISM Trial (Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography), has been launched to evaluate the effectiveness of artificial intelligence (AI) in supporting radiologists for breast cancer screening. This $16 million study, funded by the Patient-Centered Outcomes Research Institute (PCORI), marks the first large-scale randomized trial of AI in breast cancer screening in the United States 1

1

2

2

.

Collaborative Effort Across Multiple Institutions

The PRISM trial brings together 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 - Fred Hutchinson Cancer Center, and University of Wisconsin-Madison 3

3

4

4

. This collaborative effort will involve hundreds of thousands of mammograms interpreted at various academic medical centers and breast imaging facilities.

Study Objectives and Methodology

The primary goal of the study is to rigorously and objectively assess AI's impact on breast cancer screening. Researchers aim to determine whether AI can help radiologists interpret mammograms more accurately, potentially improving cancer detection rates and reducing unnecessary callbacks and patient anxiety 1

1

.

The trial will employ a randomized approach, where mammograms will be assigned to be interpreted either by a radiologist alone or with assistance from an FDA-cleared AI support tool called Transpara by ScreenPoint Medical. Importantly, in all cases, a radiologist will make the final decision on the interpretation 2

2

.

Patient-Centered Approach

What sets the PRISM trial apart is its emphasis on patient-centered research. The study was developed in close partnership with patient advocates, clinicians, health system leaders, and policymakers. This approach ensures that the patient perspective remains at the forefront of the research 3

3

.

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 4

4

.

Potential Impact and Future Implications

The results of this trial are expected to have far-reaching implications. Dr. Hannah Milch, Co-Principal Investigator and UCLA Site PI, stated, "The results will help inform not just clinical practice, but also insurance coverage, technology adoption, and patient communication" 4

4

.

Researchers emphasize that the goal is not to replace human expertise but to understand how AI might complement it. Dr. Jose Net, co-principal investigator of the study, stated, "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" 1

1

.

As AI continues to advance in healthcare, this study represents a critical step in evaluating its real-world impact and effectiveness in improving breast cancer screening outcomes.