"Mammogram is an X-ray of the breast used to detect changes in the breasts of women who do not have signs or symptoms of breast cancer. This model is very promising, showing the same accuracy for white and black women. A significant advancement considering the mortality rate from breast cancer in black women is 43% higher."

"This model can predict that patients have a higher risk of developing cancer within two years than within five years. The team trained Mirai on over 200,000 examinations from Massachusetts General Hospital (MGH) and validated it using data from MGH, the Karolinska Institute in Sweden, and Chang Gung Memorial Hospital in Taiwan."

"Mirai, which is currently installed at MGH, shows a much higher accuracy than previous methods in predicting cancer risk and identifying high-risk groups. Mirai outperformed the Tyrer-Cuzick model, identifying almost twice as many future cancer diagnoses. This AI maintains accuracy across different races, age groups, breast density categories, and cancer subtypes."

"The enhanced breast cancer risk model enables targeted screening strategies that achieve early detection and fewer screening harms than existing guidelines," said Adam Yala, a PhD student at CSAIL and the lead author of the paper published in Science Translational Medicine. The team is collaborating with doctors from various global institutions to further validate the model in diverse populations and study its clinical applications."