Fusion-driven multimodal learning for biomedical time series in surgical care
Frontiers in Physiology · 17.09.2025 · 16
DOI: 10.3389/fphys.2025.1605406 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Physiology, online erschienen am 17.09.2025. Verfasst von Jinshan Che und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Anesthesiology and Perioperative Medicine, Fourth Clinical College of Xinxiang Medical College, Xinxiang Central Hospital, Xinxiang, Ch…. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
The 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.
Methods
To 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.
Results
Experimental evaluations on biomedical datasets demonstrate that our method outperforms state-of-the-art techniques in predictive accuracy, robustness, and interpretability.
Discussion
By effectively bridging the gap between heterogeneous biomedical data sources, our framework offers a promising direction for AI-driven disease diagnosis and treatment planning.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Anesthesiology and Perioperative Medicine, Fourth Clinical College of Xinxiang Medical College, Xinxiang Central Hospital, Xinxiang, China.
- Key Laboratory of Rheumatology, Immunological Diseases and Chronic Disease Management in Xinxiang, Xinxiang, China.
Zitieren
APA
Che, J., Sun, M., Wang, Y., & Xu, Z. (2025). Fusion-driven multimodal learning for biomedical time series in surgical care. Frontiers in Physiology, 16. https://doi.org/10.3389/fphys.2025.1605406
Vancouver
Che J, Sun M, Wang Y, Xu Z. Fusion-driven multimodal learning for biomedical time series in surgical care. Frontiers in Physiology. 2025;16. doi:10.3389/fphys.2025.1605406
BibTeX
@article{Che2025,
author = {Che, Jinshan and Sun, Mingming and Wang, Yuhong and Xu, Zhendan},
title = {Fusion-driven multimodal learning for biomedical time series in surgical care},
journal = {Frontiers in Physiology},
year = {2025},
volume = {16},
doi = {10.3389/fphys.2025.1605406}
}
EUVIMED