融合肺超声与临床数据，提升透析患者液体过载预测准确率
A Multimodal Approach for Fluid Overload Prediction: Integrating Lung Ultrasound and Clinical Data
- 用双模态编码器分别提取超声图像和临床数据特征
- 引入跨域注意力机制，使模型在测试中达到88.31%准确率
- 特别适合需要多源数据融合的医疗诊断场景
维持透析患者的体液平衡至关重要，管理不当可能导致严重并发症。本文提出一种多模态方法，将肺超声图像的视觉特征与临床数据相结合，以增强体液过载的预测能力。该框架采用独立编码器提取各模态特征，并通过跨域注意力机制融合信息，实现互补。将预测任务设为分类后，模型表现显著优于回归方法。结果表明，多模态模型始终优于单模态模型，尤其当注意力机制侧重于表格数据时。伪样本生成有效缓解类别不平衡问题，最高准确率达88.31%。研究证实了多模态学习在透析患者体液管理中的有效性，为改善临床结局提供了重要参考。
原文摘要 · Abstract (English)
Managing fluid balance in dialysis patients is crucial, as improper management can lead to severe complications. In this paper, we propose a multimodal approach that integrates visual features from lung ultrasound images with clinical data to enhance the prediction of excess body fluid. Our framework employs independent encoders to extract features for each modality and combines them through a cross-domain attention mechanism to capture complementary information. By framing the prediction as a classification task, the model achieves significantly better performance than regression. The results demonstrate that multimodal models consistently outperform single-modality models, particularly when attention mechanisms prioritize tabular data. Pseudo-sample generation further contributes to mitigating the imbalanced classification problem, achieving the highest accuracy of 88.31%. This study underscores the effectiveness of multimodal learning for fluid overload management in dialysis patients, offering valuable insights for improved clinical outcomes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。