Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
This work addresses ICU resource management for hospitals, but it is incremental as it combines existing methods (state-space models and GNNs) for a specific domain application.
The paper tackles the challenge of predicting ICU length of stay from heterogeneous EHR data by proposing S$^2$G-Net, a neural architecture that unifies state-space sequence modeling with multi-view GNNs, and it outperforms existing models on the MIMIC-IV dataset across all primary metrics.
Predicting a patient's length of stay (LOS) in the intensive care unit (ICU) is a critical task for hospital resource management, yet remains challenging due to the heterogeneous and irregularly sampled nature of electronic health records (EHRs). In this work, we propose S$^2$G-Net, a novel neural architecture that unifies state-space sequence modeling with multi-view Graph Neural Networks (GNNs) for ICU LOS prediction. The temporal path employs Mamba state-space models (SSMs) to capture patient trajectories, while the graph path leverages an optimized GraphGPS backbone, designed to integrate heterogeneous patient similarity graphs derived from diagnostic, administrative, and semantic features. Experiments on the large-scale MIMIC-IV cohort dataset show that S$^2$G-Net consistently outperforms sequence models (BiLSTM, Mamba, Transformer), graph models (classic GNNs, GraphGPS), and hybrid approaches across all primary metrics. Extensive ablation studies and interpretability analyses highlight the complementary contributions of each component of our architecture and underscore the importance of principled graph construction. These results demonstrate that S$^2$G-Net provides an effective and scalable solution for ICU LOS prediction with multi-modal clinical data. The code can be found at https://github.com/ShuqiZi1/S2G-Net.