A new breakthrough in breast cancer technology could help close the racial disparity in survival rates among women.
While 78% of diagnosed patients survive the disease each year, over 11,000 people die from it– but 23% of these are preventable cases. Early diagnosis has been proven to result in higher success rates, as more than 90% of women diagnosed at the earliest stage survive their disease for at least five years. That is in comparison to around 15% of women diagnosed with the most advanced stage of disease.
Taking a closer look at women’s race when it comes to breast cancer, the statistics are even more alarming.
UK research found that breast cancer is more likely to reoccur in black women than white women. And, over in America, the Centers for Disease Control and Prevention reported that mortality rates in black women are 39% higher than for white women. The centre also said that breast cancer was more likely to be found at an earlier stage among white women than among black women.
Clearly, much more research into this racial disparity in women’s healthcare needs to be done, and there have been calls for even earlier initial screenings for women of colour.
But a new artificial intelligence (AI) breakthrough in screening could mean that all women - regardless of race - can catch the disease at its earliest stage.
Researchers in the US have developed an AI tool for accurately predicting a woman’s future risk of developing breast cancer, and it is particularly effective for African-American women.
The tool is reported to detect the disease in people up to five years in advance. Developed by a team of researchers from MIT’s Computer Science and Artificial Intelligence Laboratory and Massachusetts General Hospital, the deep learning model can use a mammogram to predict cases. The researchers used almost 90,000 screening mammograms from about 40,000 women - of different races - to train, validate and test the deep learning model.
“Unlike traditional models, our model performs equally well across race, age and family histories,” explained Dr Regina Barzilay. “Until now, African-American women were at a distinct disadvantage in having accurate risk assessment of future breast cancer. Our AI model has changed that.”
“It’s particularly striking that the model performs equally as well for black and white people, which has not been the case with prior risk assessment tools”, added Dr. Allison Kurian, associate professor of Medicine and Health Research and Policy at Stanford University. “If validated and made available for widespread use, this could really improve on our current strategies to estimate risk.”
Image: ActionVance via Unsplash