Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.06134 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910968328486912 |
|---|---|
| author | Chen, Liuqing Xiao, Shuhong Ding, Shixian Hu, Shanhai Sun, Lingyun |
| author_facet | Chen, Liuqing Xiao, Shuhong Ding, Shixian Hu, Shanhai Sun, Lingyun |
| contents | Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as sequences or transforming them into image representations for further classification. In this paper, we propose a joint learning framework that incorporates both sequence and image representations. We also design three self-supervised learning strategies to facilitate the fusion of sequence and image representations, capturing a more generalizable joint representation. The results indicate that our approach outperforms seven other state-of-the-art models in three representative real-world clinical datasets. We further validate our approach by simulating two major types of real-world missingness through leave-sensors-out and leave-samples-out techniques. The results demonstrate that our approach is more robust and significantly surpasses other baselines in terms of classification performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_06134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning Chen, Liuqing Xiao, Shuhong Ding, Shixian Hu, Shanhai Sun, Lingyun Computer Vision and Pattern Recognition Artificial Intelligence Medical time series are often irregular and face significant missingness, posing challenges for data analysis and clinical decision-making. Existing methods typically adopt a single modeling perspective, either treating series data as sequences or transforming them into image representations for further classification. In this paper, we propose a joint learning framework that incorporates both sequence and image representations. We also design three self-supervised learning strategies to facilitate the fusion of sequence and image representations, capturing a more generalizable joint representation. The results indicate that our approach outperforms seven other state-of-the-art models in three representative real-world clinical datasets. We further validate our approach by simulating two major types of real-world missingness through leave-sensors-out and leave-samples-out techniques. The results demonstrate that our approach is more robust and significantly surpasses other baselines in terms of classification performance. |
| title | Integrating Sequence and Image Modeling in Irregular Medical Time Series Through Self-Supervised Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.06134 |