PULSE-ICU: A Pretrained Unified Long-Sequence Encoder for Multi-task Prediction in Intensive Care Units
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911290344079360 |
|---|---|
| author | Jang, Sejeong Yoon, Joo Heung Lee, Hyo Kyung |
| author_facet | Jang, Sejeong Yoon, Joo Heung Lee, Hyo Kyung |
| contents | Intensive care unit (ICU) data are highly irregular, heterogeneous, and temporally fragmented, posing challenges for generalizable clinical prediction. We present PULSE-ICU, a self-supervised foundation model that learns event-level ICU representations from large-scale EHR sequences without resampling or manual feature engineering. A unified embedding module encodes event identity, continuous values, units, and temporal attributes, while a Longformer-based encoder enables efficient modeling of long trajectories. PULSE-ICU was fine-tuned across 18 prediction tasks, including mortality, intervention forecasting, and phenotype identification, achieving strong performance across task types. External validation on eICU, HiRID, and P12 showed substantial improvements with minimal fine-tuning, demonstrating robustness to domain shift and variable constraints. These findings suggest that foundation-style modeling can improve data efficiency and adaptability, providing a scalable framework for ICU decision support across diverse clinical environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PULSE-ICU: A Pretrained Unified Long-Sequence Encoder for Multi-task Prediction in Intensive Care Units Jang, Sejeong Yoon, Joo Heung Lee, Hyo Kyung Machine Learning Artificial Intelligence Intensive care unit (ICU) data are highly irregular, heterogeneous, and temporally fragmented, posing challenges for generalizable clinical prediction. We present PULSE-ICU, a self-supervised foundation model that learns event-level ICU representations from large-scale EHR sequences without resampling or manual feature engineering. A unified embedding module encodes event identity, continuous values, units, and temporal attributes, while a Longformer-based encoder enables efficient modeling of long trajectories. PULSE-ICU was fine-tuned across 18 prediction tasks, including mortality, intervention forecasting, and phenotype identification, achieving strong performance across task types. External validation on eICU, HiRID, and P12 showed substantial improvements with minimal fine-tuning, demonstrating robustness to domain shift and variable constraints. These findings suggest that foundation-style modeling can improve data efficiency and adaptability, providing a scalable framework for ICU decision support across diverse clinical environments. |
| title | PULSE-ICU: A Pretrained Unified Long-Sequence Encoder for Multi-task Prediction in Intensive Care Units |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.22199 |