PULSE-ICU用自监督学习统一建模重症患者长期医疗数据，提升预测效果。
PULSE-ICU: A Pretrained Unified Long-Sequence Encoder for Multi-task Prediction in Intensive Care Units
- 通过统一嵌入模块编码事件类型、数值、时间等信息，无需重采样或人工特征工程。
- 在18项任务上微调后表现优异，外部验证显示对不同数据集有强鲁棒性。
- 适合需要高效适应多任务、跨机构的重症监护决策支持系统开发人员。
重症监护室（ICU）数据具有高度不规则、异质性和时间碎片化特点，给通用临床预测带来挑战。我们提出PULSE-ICU，一种从大规模电子健康记录（EHR）序列中无须重采样或人工特征工程即可学习事件级表示的自监督基础模型。统一嵌入模块编码事件身份、连续值、单位和时间属性，长序列编码器基于Longformer实现对长时间轨迹的高效建模。PULSE-ICU在18个预测任务上进行微调，涵盖死亡率预测、干预预判和表型识别，表现强劲。在eICU、HiRID和P12数据集上的外部验证表明，仅需少量微调即实现显著性能提升，证明其对领域偏移和不同约束条件具备强鲁棒性。这些结果表明，基础模型范式可提升数据效率与适应性，为多样化临床环境中的重症监护决策支持提供可扩展框架。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。