Wu M, et al. - Via retrospectively evaluating 363 breast cancer cases, researchers developed and validated an interpretable and repeatable machine learning model approach to predict molecular subtypes of breast cancer from clinical metainformation together with mammography and MRI images. Eighty-two features have been visually described as defined in the BI-RADS lexicon. Based on the BI-RADS feature description in a multimodal setting, they used a complete "white box" machine learning method to predict the molecular subtype of breast cancer. The prediction accuracy is boosted and robust by combining BI-RADS features in both mammography and MRI. Due to the applicability and acceptance of the BI-RADS, the proposed method can be easily applied widely regardless of variability of imaging vendors and settings.