[ad_1]
Scientists first examined mammograms from more than 60,000 patients treated at Massachusetts General. They then identified women who had developed breast cancer within five years of their screening. With these data, scientists have created a model that recognizes the subtle patterns of breast tissue that are the first signs of cancer. The results of the study can be found in an article published this week in the journal Radiology.
Artificial intelligence could also help address racial disparity in health care for women. Given that current breast cancer recommendations are primarily based on white populations, this may result in delayed detection of women of color, according to a 2018 report published in 2018. JAMA Surgery found. This has had serious consequences. Black women are 43% more likely to die of breast cancer than white women. On average, Hispanic, Black, and Asian women develop breast cancer at an earlier age than their white counterparts.
The scientists found that their AI model worked for both black and white patients for a simple reason; their training data included both populations. "It is particularly striking that the model works as well for blacks as it is for whites, which has not been the case before with risk assessment tools," said Dr. Allison. Kurian, associate professor of medicine and research in medicine and health at Stanford University. . "If validated and made available for widespread use, it could actually improve our current risk assessment strategies."
[ad_2]
Source link