Researchers have developed an AI test to predict the recurrence of breast cancer, as reported in a paper in the journal *Nature Communications*. The test predicts the risk of breast cancer recurrence more quickly and more inexpensively than current genomic testing methods. Krzysztof J. Geras, a visiting scholar at New York University’s Center for Data Science and an adjunct assistant professor at NYU Grossman School of Medicine, who led the work, stated that the AI test can read the same tumor slides pathologists already examine and, combined with basic clinical details, accurately estimate how likely a patient’s cancer is to return. Yann LeCun, a professor of computer science and data science at New York University and one of the paper’s authors, noted that the model’s accuracy comes from self-supervised pretraining. The authors developed and evaluated the multi-modal AI test by drawing from 15 patient populations across seven countries, building it by considering pathology slides combined with routine clinical data such as tumor stage, patient age, and hormone-receptor status. They evaluated the test’s efficacy using data from more than 3,500 patients. Overall, the AI test reliably separated higher- from lower-risk patients and performed well in evaluating the probability of recurrence in triple-negative and HER2-positive breast cancer, which currently have no reliable genomic test.