Integrated Local and Global Information for Health Risk Prediction Model

Electronic health record (EHR) data has been widely used in health risk prediction models, and it has an important preventive and intervention role in healthcare. Existing approaches typically regard EHR data in a monolayer observational model, and they assume that visits are monotonically decreasing in importance over time. However, in healthcare practice, clinical experts usually focus on diseases and visits that are closely related to the target disease. In addition, the duration of different categories of diseases has a fixed model, as chronic diseases are usually consistently diagnosed during patient visits. To make full use of this disease category information, a hierarchical self-attentive model is proposed that can model patient representations at both the local and global levels. Specifically, a disease duration matrix with multiple times is constructed for disease clustering. We combine the category information to compute dependencies between diseases and disease embeddings. We further explore the pattern of patient health development from a spatio-temporal perspective. Visit embeddings are updated by learning the effects between different visits via a self-attentive mechanism. In addition, the time interval, a special kind of medical event, is introduced to enhance visit sequence temporal modeling. Extensive experiments on two real-world datasets demonstrate the sota performance of the model. At the same time, we demonstrate the plausibility and interpretability of the model through case studies.

I. Introduction

Electronic Health Records (EHR) encompass a wide range of information, such as demographic details, diagnoses, laboratory tests, and medical procedures. This diverse set of data can be leveraged to identify potential patterns in the evolution of medical events [1] [2]. The health risk prediction for the future health status of patients can be achieved by analyzing historical health records. However, due to the presence of multi-source heterogeneity, high-dimensional sparsity, and irregular time intervals in EHR data, the task of risk prediction remains considerably challenging.