PULSE-ICU: A Pretrained Unified Long-Sequence Encoder for Multi-task Prediction in Intensive Care Units
This work addresses the problem of scalable and generalizable clinical prediction for ICU decision support across diverse environments, representing a novel method for a known bottleneck rather than an incremental improvement.
The authors tackled the challenge of predicting clinical outcomes from irregular and heterogeneous ICU data by developing PULSE-ICU, a self-supervised foundation model that achieved strong performance across 18 prediction tasks and showed substantial improvements in external validation on datasets like eICU, HiRID, and P12 with minimal fine-tuning.
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.