MRI Radiomics + Clinical Data Model Predicts MammaPrint Result in Breast Cancer

Retrospective study: an MRI radiomics+clinical model predicted MammaPrint result in HR+/HER2- early breast cancer with AUC 0.86 (training), 0.76–0.79 (external), outperforming clinical-only (0.69,0.66,0.67) and radiomics-only (0.77,0.67,0.68).

• Retrospective multicenter study of 202 women (80 training, 122 external validation across two centers).
• SHAP analysis identified Ki-67 as the most influential predictor in the combined model.
• External validation AUCs were moderate (0.76–0.79); prospective validation is needed before clinical use.

RadPigeon summaries are original and for information only. They are not clinical advice.