AI Outperforms Standard Tools in Predicting Breast Cancer Risk.

In a study published in Radiology, AI algorithms outperformed traditional clinical risk models in predicting the five-year risk for breast cancer using mammograms as the single data source. The study used data associated with negative screening mammograms performed at Kaiser Permanente Northern California in 2016, and all five AI algorithms performed better than the Breast Cancer Surveillance Consortium (BCSC) risk model for predicting breast cancer risk at 0 to 5 years. AI for cancer risk prediction offers the opportunity to individualize every woman’s care and provide personalized, precision medicine on a national level.