GARLIC：重症监护环境下多变量时间序列的基于图注意力的关系学习
GARLIC: Graph Attention-based Relational Learning of Multivariate Time Series in Intensive Care
另 2 家 · 查看机构详情
- University of Zürich（苏黎世大学）
- ETH Zürich（苏黎世联邦理工学院）
- SPF
- SCAI Lab（SCAI实验室）
- D-HEST
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
本文提出GARLIC模型，通过可学习指数衰减编码器等模块处理ICU多变量时间序列，在三个ICU基准数据集上实现结局预测最优，兼具可解释性与泛化性。
中文摘要 AI 辅助
医疗数据（如重症监护病房ICU记录）包含以不规则间隔采样且普遍存在缺失值的异构多变量时间序列，但临床应用要求预测模型兼具准确性与可解释性。本文提出GARLIC模型（Graph Attention-based Relational Learning for Intensive Care，即重症监护环境下基于图注意力的关系学习模型），这是一种新型神经网络架构，通过可学习的指数衰减编码器插补缺失数据，通过时滞总结图捕捉传感器间依赖关系，并将全局模式与跨维度序列注意力融合。所有注意力权重和图边均通过端到端学习生成，可作为内置的观测级、信号级和边级解释。为协调辅助重构与主要分类目标，本文开发了一种交替解耦优化方案以稳定训练。在三个ICU基准数据集（PhysioNet 2012、2019，MIMIC-III）上，GARLIC在结局预测方面取得了新的最优性能，在计算成本相当的情况下，较表现最佳的基线显著提升了AUROC和AUPRC。消融研究证实了每个模块的贡献，特征移除试验通过单调性能下降（完整>前50%>随机50%>后50%）验证了重要性归因的保真度。实时案例研究展示了带有透明解释的可操作风险预警，为不规则采样ICU时间序列数据的准确、可解释深度学习带来了重大进展。此外，本文还在ICU领域之外的各类时间序列数据集上验证了所提模型在数据插补和分类任务中的优越性，表明其具有可推广性及更广泛任务的适用性。
英文摘要
Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable exponential-decay encoder, captures inter-sensor dependencies via time-lagged summary graphs, and fuses global patterns with cross-dimensional sequential attention. All attention weights and graph edges are learned end-to-end to serve as built-in observation-, signal-, and edge-level explanations. To reconcile auxiliary reconstruction and primary classification objectives, we developed an alternating decoupled optimization scheme that stabilizes training. On three ICU benchmarks (PhysioNet 2012 & 2019, MIMIC-III), GARLIC sets the new state of the art in outcome prediction, significantly improving AUROC and AUPRC over best-performing baselines at comparable computational cost. Ablation studies confirm the contribution of each module, and feature-removal trials validate the fidelity of importance attribution through a monotonic performance drop (full > top 50% > random 50% > bottom 50%). Real-time case studies demonstrate actionable risk warnings with transparent explanations, marking a significant advance toward accurate, explainable deep learning for irregularly sampled ICU time series data. Moreover, we demonstrated \proposed{}'s superiority in data imputation and classification on various time-series datasets beyond the ICU domain, showing its generalizability and applicability to broader tasks.
