Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.07158 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916745663479808 |
|---|---|
| author | Lu, Jiaying Brown, Stephanie R. Liu, Songyuan Zhao, Shifan Dong, Kejun Bold, Del Fundora, Michael Aljiffry, Alaa Fedorov, Alex Grunwell, Jocelyn Hu, Xiao |
| author_facet | Lu, Jiaying Brown, Stephanie R. Liu, Songyuan Zhao, Shifan Dong, Kejun Bold, Del Fundora, Michael Aljiffry, Alaa Fedorov, Alex Grunwell, Jocelyn Hu, Xiao |
| contents | Early prediction of pediatric cardiac arrest (CA) is critical for timely intervention in high-risk intensive care settings. We introduce PedCA-FT, a novel transformer-based framework that fuses tabular view of EHR with the derived textual view of EHR to fully unleash the interactions of high-dimensional risk factors and their dynamics. By employing dedicated transformer modules for each modality view, PedCA-FT captures complex temporal and contextual patterns to produce robust CA risk estimates. Evaluated on a curated pediatric cohort from the CHOA-CICU database, our approach outperforms ten other artificial intelligence models across five key performance metrics and identifies clinically meaningful risk factors. These findings underscore the potential of multimodal fusion techniques to enhance early CA detection and improve patient care. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_07158 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Early Risk Prediction of Pediatric Cardiac Arrest from Electronic Health Records via Multimodal Fused Transformer Lu, Jiaying Brown, Stephanie R. Liu, Songyuan Zhao, Shifan Dong, Kejun Bold, Del Fundora, Michael Aljiffry, Alaa Fedorov, Alex Grunwell, Jocelyn Hu, Xiao Machine Learning Artificial Intelligence Early prediction of pediatric cardiac arrest (CA) is critical for timely intervention in high-risk intensive care settings. We introduce PedCA-FT, a novel transformer-based framework that fuses tabular view of EHR with the derived textual view of EHR to fully unleash the interactions of high-dimensional risk factors and their dynamics. By employing dedicated transformer modules for each modality view, PedCA-FT captures complex temporal and contextual patterns to produce robust CA risk estimates. Evaluated on a curated pediatric cohort from the CHOA-CICU database, our approach outperforms ten other artificial intelligence models across five key performance metrics and identifies clinically meaningful risk factors. These findings underscore the potential of multimodal fusion techniques to enhance early CA detection and improve patient care. |
| title | Early Risk Prediction of Pediatric Cardiac Arrest from Electronic Health Records via Multimodal Fused Transformer |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2502.07158 |