A Multimodal Approach for Fluid Overload Prediction: Integrating Lung Ultrasound and Clinical Data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917793512816640 |
|---|---|
| author | Yang, Tianqi Anantrasirichai, Nantheera Karakuş, Oktay Allinovi, Marco Achim, Alin |
| author_facet | Yang, Tianqi Anantrasirichai, Nantheera Karakuş, Oktay Allinovi, Marco Achim, Alin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_08790 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Multimodal Approach for Fluid Overload Prediction: Integrating Lung Ultrasound and Clinical Data Yang, Tianqi Anantrasirichai, Nantheera Karakuş, Oktay Allinovi, Marco Achim, Alin Image and Video Processing 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. |
| title | A Multimodal Approach for Fluid Overload Prediction: Integrating Lung Ultrasound and Clinical Data |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2409.08790 |