Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction

TL;DR

This paper introduces S$^2$G-Net, a novel neural network architecture that combines state-space models and graph neural networks to improve ICU length of stay prediction from complex electronic health records.

Contribution

The work presents a unified model integrating state-space and graph neural networks, demonstrating superior performance on large-scale clinical data for ICU LOS prediction.

Findings

S$^2$G-Net outperforms existing models across all metrics.

The architecture effectively captures patient trajectories and similarities.

Interpretability analyses confirm the model's components contribute meaningfully.

Abstract

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.