MCLAM: a cost-effective deep learning model for predicting recurrence risk in HR+/HER2- breast cancer-a multi-center study in a Chinese cohort.

objectiveEndoPredict is a gold-standard for HR+/HER2- breast cancer risk stratification but limited by high cost. We propose Multi-modal Clustering-constrained Attention Multiple Instance Learning (MCLAM), a novel deep learning framework, offering a cost-effective, accurate alternative for recurrence risk prediction.

methodsWe retrospectively analyzed 254 early-stage HR+/HER2- breast cancer patients from multiple centers, supplemented by an external validation cohort of 338 cases. MCLAM innovatively combines histopathological features extracted via ResNet-50, nuclear morphology quantified by HoVer-Net, and clinical variables through a clinical-nuclear feature enhancement module and a multimodal fusion strategy.

resultsMCLAM outperformed all comparison models, achieving an impressive area under the curve (AUC) of 0.83 and 0.82 (independent test set), significantly exceeding traditional deep learning baselines (ResNet50 AUC = 0.61) and MIL variants (DTFD_MIL_CN AUC = 0.78). Clinically, it stratified patients into risk groups with significantly better 5- and 10-year disease-free survival and distant disease-free survival in the low-risk group (all

conclusionsTo our knowledge, this is the first and largest multi-center study validating an EndoPredict-predicting model in a Chinese HR+/HER2- breast cancer cohort, addressing a key population gap. MCLAM provides an accurate, interpretable, and cost-efficient alternative to molecular assays, enabling accessible individualized risk assessment and supporting personalized treatment strategies.