The researchers believe AI can help fix racial disparity in women’s healthcare.
The researchers from MIT have invented a new model, driven by AI that observes mammogram differently, in order to help detect breast cancer in women up to five years in advance. Breast cancer was the second-leading cancer-related cause of death among women in the U.S. However, this deep learning model created by MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital can predict breast cancer in well advance. Moreover, unlike previous methods, it works just as fine on black patients as it does on white patients.
The results of the study were published in the journal called ‘Radiology’. The scientists looked at mammograms of over 60,000 patients who were treated at Massachusetts General Hospital. Thereafter, scientists identified the women that developed breast cancer within five years of their screening. Using that data, scientists created a model that recognizes the pattern of breast cancer development and growth of its tissue. Moreover, the model’s training data included both white and black population, hence it works for absolutely fine for both. The researchers believe AI has the potential to fix the racial disparity in women’s healthcare.
The current guidelines of breast cancer are based on white populations only, it has led to delay in detection among women of other colors. As a result of that black women are 43% more likely to die from breast cancer than white women. Dr. Allison Kurian, associate professor at Medicine and Health Research and Policy at Stanford University to MIT said, “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. If validated and made available for widespread use, this could really improve on our current strategies to estimate risk.”