(Credit: SEBASTIAN KAULITZKI/SCIENCE PHOTO LIBRARY / Science Photo Library via Getty Images)
Don't miss out on our latest stories. Add PCMag as a preferred source on Google.
Can AI help improve patient outcomes when it comes to breast cancer? Seven major medical centers have partnered on a $16 million study to find out.
Hundreds of thousands of mammogram images will be randomly assigned for interpretation by either a radiologist or a radiologist who's assisted by Transpara, an FDA-approved AI support tool from ScreenPoint Medical. A human radiologist will make the final call on a patient's next steps.
The goal is to determine whether AI systems help or hinder radiologists' ability to detect breast cancer on mammograms. UCLA and UC Davis will co-lead this effort, in partnership with Boston Medical Center, UC San Diego Health, University of Miami, University of Washington – Fred Hutchinson Cancer Center, and the University of Wisconsin–Madison. They've named it the PRISM Trial—Pragmatic Randomized Trial of Artificial Intelligence for Screening Mammography.
"There is a lot of hope that AI will make care better, but very few rigorous trials have actually evaluated its real-world effects,” says Dr. Joann G. Elmore, 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. "This is our opportunity to generate trustworthy evidence, with the patient perspective front and center."
A 2024 Harvard study already found that AI can make it more difficult for some technicians to accurately read images, such as X-rays and CT scans.
Breast cancer is one of the leading causes of cancer death among women in the US, and failure to detect it early can make the situation worse, as can "false positives that can lead to unnecessary testing, anxiety and costs, and missed cancers," UCLA says.
Sometimes radiologists struggle to spot signs of cancer in dense breast tissue, or if the evidence is too small to see, Dr. Christoph Lee, co-principal investigator for the trial and professor and vice chair of research in the Department of Radiology at UW-Madison's School of Medicine and Public Health, tells the Milwaukee Journal Sentinel.
The study will also include focus groups and surveys to see how patients and radiologists perceive and trust AI-assisted care.
"The results will help inform not just clinical practice, but also insurance coverage, technology adoption, and patient communication," says Dr. Hannah Milch, Co-Principal Investigator and UCLA Site PI and assistant professor of radiology at UCLA.