Bal Harbour

or most of medical history, a woman's breast cancer risk was calculated the same crude way: Did her mother have it? Her sister? Did she carry a known genetic mutation? If the answers were no, she was told, essentially, Don't worry. Come back at 40, then see you every year or two. The trouble is that those family-history and genetic models only ever captured about 15 percent of the women who would go on to be diagnosed. The remaining 85 percent were, in medical terms, "sporadic," meaning cancer might appear with no visible warning sign, no glaring red flag on the chart. "We didn't have a way to find those 85 percent in advance," says Dr. Constance Lehman, a professor of radiology at Harvard Medical School and a breast imaging specialist who has spent her career at the bleeding edge of radiology research. "Until now." Dr. Lehman's aha moment occurred in 2016, when she moved to Boston and began collaborating with a colleague at Massachusetts Institute of Technology on imaging and machine learning. Radiologists had spent decades training computers to spot a mass, a calcification, or a lesion, all cancer indicators humans had long been trained to see. Dr. Lehman wondered if, with the rapid advancements in artificial intelligence, a machine could look at a woman's mammogram today and F Researchers have developed an AI-powered tool that can predict a woman's five-year breast cancer risk from a routine mammogram, shifting the focus from detecting disease to preventing it altogether. BY HEIDI MITCHELL before it begins seeing cancer the breakthrough 120 120 BALHAR B O U RSH O P S .CO M

• Cover