GraphMMP: A Graph Neural Network Model with Mutual Information and Global Fusion for Multimodal Medical Prognosis
This addresses multimodal medical data analysis for prognosis tasks, representing an incremental improvement with a novel hybrid approach.
The paper tackles the problem of modeling complex interactions between heterogeneous medical data modalities by proposing GraphMMP, a two-stage graph neural network model that uses mutual information and a global fusion module based on Mamba. The model outperforms existing methods on liver prognosis and METABRIC datasets, demonstrating improved prognosis performance.
In the field of multimodal medical data analysis, leveraging diverse types of data and understanding their hidden relationships continues to be a research focus. The main challenges lie in effectively modeling the complex interactions between heterogeneous data modalities with distinct characteristics while capturing both local and global dependencies across modalities. To address these challenges, this paper presents a two-stage multimodal prognosis model, GraphMMP, which is based on graph neural networks. The proposed model constructs feature graphs using mutual information and features a global fusion module built on Mamba, which significantly boosts prognosis performance. Empirical results show that GraphMMP surpasses existing methods on datasets related to liver prognosis and the METABRIC study, demonstrating its effectiveness in multimodal medical prognosis tasks.