提出可解释的时空图网络，精准预测重症患者多重耐药风险
Explainable Spatio-Temporal GCNNs for Irregular Multivariate Time Series: Architecture and Application to ICU Patient Data
- 构建时空图结构捕捉异构不规则多变量时间序列依赖关系
- 在真实ICU数据上实现81.03±2.43的平均ROC-AUC，优于传统模型
- 揭示关键临床特征与时间点的组合，助力医生理解预测依据
本文提出XST-GCNN（可解释的时空图卷积神经网络），用于处理异构且不规则的多变量时间序列（MTS）数据。通过统一的时空管道，利用基于时空图的图卷积网络捕获时间与特征依赖关系。图结构估计采用广义距离（Gower distance）等方法，提出两种构造方式：一种基于笛卡尔积，对时序点一视同仁；另一种为每时刻独立的时空方法。设计两种GCNN架构：带归一化邻接矩阵的标准模型与高阶多项式模型。在强调预测精度的同时，注重可解释性，通过内在可解释模型与深入分析，识别驱动预测的关键特征-时间组合。在西班牙Fuenlabrada大学医院的真实电子健康记录数据上评估，用于预测重症患者多重耐药（MDR），这是与高死亡率和复杂治疗相关的重大挑战。结果表明，该架构在预测性能上超越传统模型，平均ROC-AUC达81.03±2.43。解释性分析提供了可行动的临床洞察，显著提升模型透明度。本工作为处理异构多变量时间序列的复杂推断任务树立了新基准，提供了一个通用、可解释的现实应用解决方案。
原文摘要 · Abstract (English)
In this paper, we present XST-GCNN (eXplainable Spatio-Temporal Graph Convolutional Neural Network), a novel architecture for processing heterogeneous and irregular Multivariate Time Series (MTS) data. Our approach captures temporal and feature dependencies within a unified spatio-temporal pipeline by leveraging a GCNN that uses a spatio-temporal graph aimed at optimizing predictive accuracy and interoperability. For graph estimation, we introduce techniques, including one based on the (heterogeneous) Gower distance. Once estimated, we propose two methods for graph construction: one based on the Cartesian product, treating temporal instants homogeneously, and another spatio-temporal approach with distinct graphs per time step. We also propose two GCNN architectures: a standard GCNN with a normalized adjacency matrix and a higher-order polynomial GCNN. In addition to accuracy, we emphasize explainability by designing an inherently interpretable model and performing a thorough interpretability analysis, identifying key feature-time combinations that drive predictions. We evaluate XST-GCNN using real-world Electronic Health Record data from University Hospital of Fuenlabrada to predict Multidrug Resistance (MDR) in ICU patients, a critical healthcare challenge linked to high mortality and complex treatments. Our architecture outperforms traditional models, achieving a mean ROC-AUC score of 81.03 +- 2.43. Furthermore, the interpretability analysis provides actionable insights into clinical factors driving MDR predictions, enhancing model transparency. This work sets a benchmark for tackling complex inference tasks with heterogeneous MTS, offering a versatile, interpretable solution for real-world applications.
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。