HoT-SSM:Higher-order Temporal Knowledge Graph Reasoning with State Space Models for Health Care
Researchers have developed HoT-SSM, a novel approach for analyzing medical knowledge graphs that incorporates higher-order temporal reasoning. This method constructs hypergraphs to capture complex relationships between clinical concepts within a single visit and uses a dynamic hypergraph-based state space model to track patient state evolution over time. Experiments on the MIMIC-III and MIMIC-IV datasets demonstrated significant performance improvements in clinical prediction tasks compared to existing state-of-the-art models. AI
IMPACT Introduces a new method for clinical prediction by improving temporal reasoning in medical knowledge graphs.