Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.27321 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910071619846144 |
|---|---|
| author | Kuo, Yu-Chen Tseng, Yi-Ju |
| author_facet | Kuo, Yu-Chen Tseng, Yi-Ju |
| contents | The inherent multimodality and heterogeneous temporal structures of medical data pose significant challenges for modeling. We propose MedM2T, a time-aware multimodal framework designed to address these complexities. MedM2T integrates: (i) Sparse Time Series Encoder to flexibly handle irregular and sparse time series, (ii) Hierarchical Time-Aware Fusion to capture both micro- and macro-temporal patterns from multiple dense time series, such as ECGs, and (iii) Bi-Modal Attention to extract cross-modal interactions, which can be extended to any number of modalities. To mitigate granularity gaps between modalities, MedM2T uses modality-specific pre-trained encoders and aligns resulting features within a shared encoder. We evaluated MedM2T on MIMIC-IV and MIMIC-IV-ECG datasets for three tasks that encompass chronic and acute disease dynamics: 90-day cardiovascular disease (CVD) prediction, in-hospital mortality prediction, and ICU length-of-stay (LOS) regression. MedM2T achieved superior or comparable performance relative to state-of-the-art multimodal learning frameworks and existing time series models, achieving an AUROC of 0.932 and an AUPRC of 0.670 for CVD prediction; an AUROC of 0.868 and an AUPRC of 0.470 for mortality prediction; and Mean Absolute Error (MAE) of 2.33 for LOS regression. These results highlight the robustness and broad applicability of MedM2T, positioning it as a promising tool in clinical prediction. We provide the implementation of MedM2T at https://github.com/DHLab-TSENG/MedM2T. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_27321 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electrocardiogram Data Kuo, Yu-Chen Tseng, Yi-Ju Machine Learning The inherent multimodality and heterogeneous temporal structures of medical data pose significant challenges for modeling. We propose MedM2T, a time-aware multimodal framework designed to address these complexities. MedM2T integrates: (i) Sparse Time Series Encoder to flexibly handle irregular and sparse time series, (ii) Hierarchical Time-Aware Fusion to capture both micro- and macro-temporal patterns from multiple dense time series, such as ECGs, and (iii) Bi-Modal Attention to extract cross-modal interactions, which can be extended to any number of modalities. To mitigate granularity gaps between modalities, MedM2T uses modality-specific pre-trained encoders and aligns resulting features within a shared encoder. We evaluated MedM2T on MIMIC-IV and MIMIC-IV-ECG datasets for three tasks that encompass chronic and acute disease dynamics: 90-day cardiovascular disease (CVD) prediction, in-hospital mortality prediction, and ICU length-of-stay (LOS) regression. MedM2T achieved superior or comparable performance relative to state-of-the-art multimodal learning frameworks and existing time series models, achieving an AUROC of 0.932 and an AUPRC of 0.670 for CVD prediction; an AUROC of 0.868 and an AUPRC of 0.470 for mortality prediction; and Mean Absolute Error (MAE) of 2.33 for LOS regression. These results highlight the robustness and broad applicability of MedM2T, positioning it as a promising tool in clinical prediction. We provide the implementation of MedM2T at https://github.com/DHLab-TSENG/MedM2T. |
| title | MedM2T: A MultiModal Framework for Time-Aware Modeling with Electronic Health Record and Electrocardiogram Data |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.27321 |