Temporal Cascade and Structural Modelling of EHRs for Granular Readmission Prediction

TL;DR

This paper introduces MEDCAS, a novel model combining RNNs and point processes with structural graph-based methods to improve granular hospital readmission predictions from EHR data, capturing complex temporal cascades.

Contribution

MEDCAS innovatively integrates point processes with attention-based RNNs and graph structures to model complex cascade relationships in EHR data for readmission prediction.

Findings

MEDCAS outperforms existing models on three real-world datasets.

The model effectively captures temporal cascade relationships.

Structural graph-based features enhance short sequence modeling.

Abstract

Predicting (1) when the next hospital admission occurs and (2) what will happen in the next admission about a patient by mining electronic health record (EHR) data can provide granular readmission predictions to assist clinical decision making. Recurrent neural network (RNN) and point process models are usually employed in modelling temporal sequential data. Simple RNN models assume that sequences of hospital visits follow strict causal dependencies between consecutive visits. However, in the real-world, a patient may have multiple co-existing chronic medical conditions, i.e., multimorbidity, which results in a cascade of visits where a non-immediate historical visit can be most influential to the next visit. Although a point process (e.g., Hawkes process) is able to model a cascade temporal relationship, it strongly relies on a prior generative process assumption. We propose a novel model, MEDCAS, to address these challenges. MEDCAS combines the strengths of RNN-based models and point processes by integrating point processes in modelling visit types and time gaps into an attention-based sequence-to-sequence learning model, which is able to capture the temporal cascade relationships. To supplement the patients with short visit sequences, a structural modelling technique with graph-based methods is used to construct the markers of the point process in MEDCAS. Extensive experiments on three real-world EHR datasets have been performed and the results demonstrate that \texttt{MEDCAS} outperforms state-of-the-art models in both tasks.