A multimodal deep learning model trained in the NSABP B-42 trial and validated in TAILORx predicted late distant recurrence (DR) risk in hormone receptor (HR)-positive early breast cancer, according to results published in Cancer Research Communications. Caris Life Sciences disclosed the findings, developed with the NSABP Foundation/NRG Oncology and the ECOG-ACRIN Cancer Research Group. HR-positive disease accounts for approximately 70% to 80% of breast cancer diagnoses and carries a recurrence risk that can persist beyond the initial 5 years of endocrine therapy (ET). The model was developed using banked tumor specimens from 2271 patients enrolled in the NSABP B-42 trial with 5-fold cross-validation, then externally validated in 4300 banked specimens from patients in the TAILORx trial who remained disease-free 5 years after diagnosis. It generates risk predictions for late DR in both node-positive and node-negative HR-positive breast cancer. In the NSABP B-42 cohort, the model identified a 10-year absolute distant recurrence risk difference of nearly 8% between high- and low-risk groups. External validation in TAILORx confirmed prognostic performance, independently predicting late DR risk after adjusting for established clinical risk factors and the Oncotype DX Recurrence Score. Exploratory analyses suggested high-risk patients experienced greater absolute benefit from extended letrozole therapy than low-risk patients. George W. Sledge, MD, chief medical officer, Caris