Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.23072 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917971791708160 |
|---|---|
| author | Liang, Yuyang Chen, Yankai Fang, Yixiang Lakshmanan, Laks V. S. Ma, Chenhao |
| author_facet | Liang, Yuyang Chen, Yankai Fang, Yixiang Lakshmanan, Laks V. S. Ma, Chenhao |
| contents | Electronic Health Records (EHR) have become a valuable resource for a wide range of predictive tasks in healthcare. However, existing approaches have largely focused on inter-visit event predictions, overlooking the importance of intra-visit nowcasting, which provides prompt clinical insights during an ongoing patient visit. To address this gap, we introduce the task of laboratory measurement prediction within a hospital visit. We study the laboratory data that, however, remained underexplored in previous work. We propose TRACE, a Transformer-based model designed for clinical event nowcasting by encoding patient trajectories. TRACE effectively handles long sequences and captures temporal dependencies through a novel timestamp embedding that integrates decay properties and periodic patterns of data. Additionally, we introduce a smoothed mask for denoising, improving the robustness of the model. Experiments on two large-scale electronic health record datasets demonstrate that the proposed model significantly outperforms previous methods, highlighting its potential for improving patient care through more accurate laboratory measurement nowcasting. The code is available at https://github.com/Amehi/TRACE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23072 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TRACE: Intra-visit Clinical Event Nowcasting via Effective Patient Trajectory Encoding Liang, Yuyang Chen, Yankai Fang, Yixiang Lakshmanan, Laks V. S. Ma, Chenhao Machine Learning Electronic Health Records (EHR) have become a valuable resource for a wide range of predictive tasks in healthcare. However, existing approaches have largely focused on inter-visit event predictions, overlooking the importance of intra-visit nowcasting, which provides prompt clinical insights during an ongoing patient visit. To address this gap, we introduce the task of laboratory measurement prediction within a hospital visit. We study the laboratory data that, however, remained underexplored in previous work. We propose TRACE, a Transformer-based model designed for clinical event nowcasting by encoding patient trajectories. TRACE effectively handles long sequences and captures temporal dependencies through a novel timestamp embedding that integrates decay properties and periodic patterns of data. Additionally, we introduce a smoothed mask for denoising, improving the robustness of the model. Experiments on two large-scale electronic health record datasets demonstrate that the proposed model significantly outperforms previous methods, highlighting its potential for improving patient care through more accurate laboratory measurement nowcasting. The code is available at https://github.com/Amehi/TRACE. |
| title | TRACE: Intra-visit Clinical Event Nowcasting via Effective Patient Trajectory Encoding |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2503.23072 |