In clinical medicine, the accuracy of sleep staging directly affects the diagnosis and treatment of sleep disorders. However, existing methods have significant limitations in characterizing dynamic spatiotemporal associations of the brain during sleep, especially in modeling nonlinear interactions across brain regions. To overcome these limitations, we develop STHGNN, a hypergraph-based neural network model that captures spatiotemporal features for automated sleep staging. The model fuses temporal and spatial features extracted from multi-modal data, and thus performs classification task effectively. In our experiments, we compared our method on the ISRUC-S1 and ISRUC-S3 datasets with the latest methods. Experimental results on the ISRUC-S3 dataset show that the overall classification accuracy of this method reaches 82.8%, F1-score and Cohen kappa reach 81.1% and 77.8%, respectively. Compared with existing baseline classification methods, this method has better classification performance.