Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.11092 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915447331356672 |
|---|---|
| author | Huang, Cindy Shih-Ting Ng, Clarence Boon Liang Rei, Marek |
| author_facet | Huang, Cindy Shih-Ting Ng, Clarence Boon Liang Rei, Marek |
| contents | While the ICD code assignment problem has been widely studied, most works have focused on post-discharge document classification. Models for early forecasting of this information could be used for identifying health risks, suggesting effective treatments, or optimizing resource allocation. To address the challenge of predictive modeling using the limited information at the beginning of a patient stay, we propose a multimodal system to fuse clinical notes and tabular events captured in electronic health records. The model integrates pre-trained encoders, feature pooling, and cross-modal attention to learn optimal representations across modalities and balance their presence at every temporal point. Moreover, we present a weighted temporal loss that adjusts its contribution at each point in time. Experiments show that these strategies enhance the early prediction model, outperforming the current state-of-the-art systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11092 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Predictive Multimodal Modeling of Diagnoses and Treatments in EHR Huang, Cindy Shih-Ting Ng, Clarence Boon Liang Rei, Marek Machine Learning While the ICD code assignment problem has been widely studied, most works have focused on post-discharge document classification. Models for early forecasting of this information could be used for identifying health risks, suggesting effective treatments, or optimizing resource allocation. To address the challenge of predictive modeling using the limited information at the beginning of a patient stay, we propose a multimodal system to fuse clinical notes and tabular events captured in electronic health records. The model integrates pre-trained encoders, feature pooling, and cross-modal attention to learn optimal representations across modalities and balance their presence at every temporal point. Moreover, we present a weighted temporal loss that adjusts its contribution at each point in time. Experiments show that these strategies enhance the early prediction model, outperforming the current state-of-the-art systems. |
| title | Predictive Multimodal Modeling of Diagnoses and Treatments in EHR |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.11092 |