Subphenotype Identification for Sepsis-Associated Acute Kidney Injury Using Graph Bidirectional Mamba Networks

Sepsis-associated acute kidney injury (SA-AKI) is a heterogeneous clinical syndrome and a leading cause of mortality in intensive care units (ICUs). Identifying subphenotypes of SA-AKI can improve treatment precision, enabling more targeted clinical interventions. Recently, the analysis of sepsis subphenotypes using electronic health records (EHRs) has gained interest among healthcare researchers. However, current methods typically rely on static and aggregated features, overlook intrinsic correlations among patients and struggle with the sparse and high-dimensional nature of EHR data. In this paper, we propose GBMN, a novel Graph Bidirectional Mamba Network for identifying subphenotypes of SA-AKI. First, we develop a multi-modal fusion module that integrates demographic information, laboratory results, vital signs, and diagnostic data. Next, we introduce an adaptive latent graph inference module that captures latent graph structures and co-optimizes them with the identification model to reveal intrinsic patient connections. Inspired by the recent success of state space models (SSMs), such as Mamba, we incorporate a graph learning model that combines graph neural networks with Mambas. Finally, we design a spectral modularity maximization objective function with regularization terms to achieve differentiable patient subphenotype identification. Experiments conducted on the MIMIC-IV dataset demonstrate that our model outperforms baseline models, exhibiting strong performance and interpretability. Following subphenotype identification, the importance of contributing factors can guide precise treatment and intervention strategies.