Temporal Cascade and Structural Modelling of EHRs for Granular Readmission Prediction
This research provides more granular readmission predictions, which can assist clinicians in making better decisions for patients, especially those with multimorbidity.
This paper introduces MEDCAS, a novel model that combines RNNs and point processes within an attention-based sequence-to-sequence learning framework to predict both the timing and nature of future hospital admissions. The model addresses the limitations of existing methods by capturing temporal cascade relationships and leveraging graph-based structural modeling for patients with short visit sequences. Experiments on three real-world EHR datasets show that MEDCAS outperforms state-of-the-art models in both tasks.
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.