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

Objective: EndoPredict 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. Methods: We 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. Results: MCLAM 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 P < 0.05), and maintained predictive power in HER2-low populations (all P < 0.05). Attention heatmaps and nuclear feature analysis further enabled biological interpretability of recurrence risk. Conclusions: To 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.