A heterogeneous multimodal ensemble framework for multi-omics breast cancer prognosis

Abstract

Accurate breast cancer prognosis remains a major challenge in precision oncology due to tumor heterogeneity and the complexity of integrating high-dimensional multi-omics data. Although multimodal learning approaches have improved predictive performance by combining clinical and molecular information, many existing methods rely on a single ensemble strategy that remains susceptible to prediction variance and limited robustness in high-dimensional, low-sample-size biomedical datasets. This study investigated whether integrating complementary ensemble strategies within a unified multimodal framework could improve the robustness and predictive performance of breast cancer prognosis. A heterogeneous multimodal ensemble framework was developed in which stacking was used to integrate complementary information from clinical, gene expression, and copy number variation (CNV) data through meta-learning, while bagging was incorporated to stabilize the meta-learning process via bootstrap aggregation. The outputs of the stacking and bagging branches were combined using weighted probability fusion. The framework was evaluated on the METABRIC breast cancer cohort and compared with unimodal models and a conventional stacking ensemble using an independent test set and stratified tenfold cross-validation. The proposed hybrid framework achieved a ROC-AUC of 0.936, outperforming unimodal clinical and molecular models (ROC-AUC = 0.8140.885) and the conventional stacking ensemble (ROC-AUC = 0.898). Stratified tenfold cross-validation further demonstrated consistent improvements in mean ROC-AUC, recall, F1-score, balanced accuracy, and Matthews correlation coefficient, indicating improved robustness and stable performance across the internal validation folds. On the independent test set, the hybrid framework reduced false-negative predictions and increased sensitivity relative to the stacking ensemble, demonstrating a more favorable balance between identifying high-risk patients and maintaining overall predictive performance. Rather than introducing a new ensemble algorithm, this study demonstrates that assigning complementary roles to stacking multimodal information integration and bagging for prediction stabilization provides an effective and robust framework for multi-omics breast cancer prognosis. The proposed hybrid strategy consistently improved predictive performance and robustness compared with conventional stacking while demonstrating stable performance across internal validation, supporting the use of complementary ensemble paradigms for multimodal prediction in precision oncology.