AUTHOR=Che Jinshan , Sun Mingming , Wang Yuhong , Xu Zhendan 

TITLE=Fusion-driven multimodal learning for biomedical time series in surgical care

JOURNAL=Frontiers in Physiology

VOLUME=Volume 16 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/physiology/articles/10.3389/fphys.2025.1605406

DOI=10.3389/fphys.2025.1605406

ISSN=1664-042X

ABSTRACT=IntroductionThe integration of multimodal data has become a crucial aspect of biomedical time series prediction, offering improved accuracy and robustness in clinical decision-making. Traditional approaches often rely on unimodal learning paradigms, which fail to fully exploit the complementary information across heterogeneous data sources such as physiological signals, imaging, and electronic health records. These methods suffer from modality misalignment, suboptimal feature fusion, and lack of adaptive learning mechanisms, leading to performance degradation in complex biomedical scenarios.MethodsTo address these challenges, we propose a novel multimodal Deep Learning framework that dynamically captures inter-modal dependencies and optimizes cross-modal interactions for time series prediction. Our approach introduces an Adaptive Multimodal Fusion Network (AMFN), which leverages attention-based alignment, graph-based representation learning, and a modality-adaptive fusion mechanism to enhance information integration. Furthermore, we develop a Dynamic Cross-Modal Learning Strategy (DCMLS) that optimally selects relevant features, mitigates modality-specific noise, and incorporates uncertainty-aware learning to improve model generalization.ResultsExperimental evaluations on biomedical datasets demonstrate that our method outperforms state-of-the-art techniques in predictive accuracy, robustness, and interpretability.DiscussionBy effectively bridging the gap between heterogeneous biomedical data sources, our framework offers a promising direction for AI-driven disease diagnosis and treatment planning.