🤖 AI Summary
This study addresses the limited accuracy of future disease diagnosis prediction from electronic health records (EHRs) by proposing a dynamic hypergraph modeling framework tailored to sequential clinical visits. Methodologically, it constructs, for the first time, a disease-discriminative dynamic hypergraph that explicitly captures high-order and temporal evolutionary relationships among acute and chronic conditions. The framework integrates clinical event sequences with temporal embeddings and leverages a domain-adapted medical language model to enhance diagnostic semantic encoding, enabling fine-grained patient representation. Evaluated on MIMIC-III and MIMIC-IV, the proposed Dynamic Hypergraph Neural Network significantly outperforms established baselines—including RNNs and GNNs—in diagnosis sequence prediction accuracy. These results establish a novel paradigm for EHR-driven, prospective clinical decision support through principled modeling of longitudinal, multimodal patient data.
📝 Abstract
This study introduces a pioneering Dynamic Hypergraph Networks (DHCE) model designed to predict future medical diagnoses from electronic health records with enhanced accuracy. The DHCE model innovates by identifying and differentiating acute and chronic diseases within a patient's visit history, constructing dynamic hypergraphs that capture the complex, high-order interactions between diseases. It surpasses traditional recurrent neural networks and graph neural networks by effectively integrating clinical event data, reflected through medical language model-assisted encoding, into a robust patient representation. Through extensive experiments on two benchmark datasets, MIMIC-III and MIMIC-IV, the DHCE model exhibits superior performance, significantly outpacing established baseline models in the precision of sequential diagnosis prediction.