Time-Guided High-Order Attention Model of Longitudinal Heterogeneous Healthcare Data
This addresses challenges in EHR data analysis for chronic disease management and personalized healthcare, though it appears incremental as an extension of attention models to higher-order dependencies.
The paper tackles modeling longitudinal heterogeneous EHR data by proposing a time-guided high-order attention model that captures 3-order correlations and irregular temporal impacts, showing effectiveness in mortality prediction and disease ranking tasks on real-world datasets.
Due to potential applications in chronic disease management and personalized healthcare, the EHRs data analysis has attracted much attention of both researchers and practitioners. There are three main challenges in modeling longitudinal and heterogeneous EHRs data: heterogeneity, irregular temporality and interpretability. A series of deep learning methods have made remarkable progress in resolving these challenges. Nevertheless, most of existing attention models rely on capturing the 1-order temporal dependencies or 2-order multimodal relationships among feature elements. In this paper, we propose a time-guided high-order attention (TGHOA) model. The proposed method has three major advantages. (1) It can model longitudinal heterogeneous EHRs data via capturing the 3-order correlations of different modalities and the irregular temporal impact of historical events. (2) It can be used to identify the potential concerns of medical features to explain the reasoning process of the healthcare model. (3) It can be easily expanded into cases with more modalities and flexibly applied in different prediction tasks. We evaluate the proposed method in two tasks of mortality prediction and disease ranking on two real world EHRs datasets. Extensive experimental results show the effectiveness of the proposed model.