用语义对齐时间，提升重症监护风险预测精度
MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction
- 基于事件语义动态调整注意力，更关注因果关系而非时间先后
- 将二分类转为多时域回归，实现全病程风险建模
- 在超50万条标注数据上验证，适合复杂临床序列分析
风险预测依赖于内在病理关联，而非简单的时间接近性。现有方法受限于粗粒度二值监督和物理时间戳。为此，我们提出医学语义感知时间对齐变压器（MATA-Former），利用事件语义动态调节注意力权重，优先考虑因果有效性而非时间延迟。此外，引入平台高斯软标签（PSL），将二分类重构为连续多时域回归，实现全轨迹风险建模。在新构建的SIICU数据集（含超过50.6万条事件，经专家严格验证、细粒度标注）及MIMIC-IV数据集上评估，该框架在捕捉文本密集型、不规则临床时序中的风险方面表现出更优效能与鲁棒泛化能力。
原文摘要 · Abstract (English)
Forecasting evolving clinical risks relies on intrinsic pathological dependencies rather than mere chronological proximity, yet current methods struggle with coarse binary supervision and physical timestamps. To align predictive modeling with clinical logic, we propose the Medical-semantics Aware Time-ALiBi Transformer (MATA-Former), utilizing event semantics to dynamically parameterize attention weights to prioritize causal validity over time lags. Furthermore, we introduce Plateau-Gaussian Soft Labeling (PSL), reformulating binary classification into continuous multi-horizon regression for full-trajectory risk modeling. Evaluated on SIICU -- a newly constructed dataset featuring over 506k events with rigorous expert-verified, fine-grained annotations -- and the MIMIC-IV dataset, our framework demonstrates superior efficacy and robust generalization in capturing risks from text-intensive, irregular clinical time series.
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。