AI shows promise in breast cancer prevention

AI may be able to identify women at elevated risk of breast cancer years before a diagnosis. New research published June 23 in Radiology, a journal of the Radiological Society of North America, finds that AI can generate risk-cancer scores directly from screening mammograms using the entire image. The models have proven more accurate than those that rely on limited, predetermined features such as density in estimating five-year cancer risk. “Having a dynamic risk score opens up a whole new domain of effective preventive therapies,” says lead researcher Constance D. Lehman, MD, PhD, a professor of radiology at Harvard Medical School and CEO of Clairity Inc., a company that recently launched the first FDA-authorized AI platform that predicts breast cancer risk.