A new decade is here and it’s bringing some exciting advancements in technology. No, we don’t have flying cars or teleportation just yet, but we may have a different approach to diagnosing breast cancer — and it could potentially be more accurate than what doctors are able to do on their own currently.
On Wednesday, the scientific journal Nature published a study that put one of Google’s artificial intelligence systems to the test. This particular AI system can purportedly detect the presence of breast cancer more accurately than its human counterparts, reports CNN Business. It works by analyzing tens of thousands of mammograms from women in the United Kingdom and the United States.
This study concluded that the AI technology resulted in fewer false positives and false negatives, both of which can significantly affect how the disease is detected and, ultimately, treated in the long term.
“The performance of even the best clinicians leaves room for improvement,” the researchers wrote about their findings. “AI may be uniquely poised to help with this challenge.”
Overall, the AI system proved to be more accurate in its findings even though it didn’t have access to information that conventional (i.e. human) radiologists would have, including medical histories and previous mammograms.
“This is one of those transformational discoveries you have in your hand, which could disrupt the way we deliver screening in terms of improving accuracy and productivity,” Ara Darzi, one of the study’s authors and the director of the Cancer Research UK Imperial Center, told CNN.
About one in eight women in Canada will develop breast cancer at some point in their lives. In 2019, the Canadian Cancer Society estimated that on average 75 Canadian women were diagnosed with breast cancer everyday while 14 Canadian women died from breast cancer daily. Generally, deaths from breast cancer have been on the decline since the early 1990s, but the research suggests that the rate has fluctuated since.
“It’s slowing slightly,” Carol DeSantis, lead author of the report, told Refinery29. “It was surprising. This is the first time we’ve noted that happening.”
Although she couldn’t identify what, exactly, was slowing the decline, she offered a hypothesis. It could be the result of a saturation of certain groups of patients who have been steadily benefiting from advances in early detection, treatment, and technology.