Objective: To investigate the potential role of PANoptosis-related genes (PRGs) in the pathogenesis of SCI using bioinformatics approaches. Methods: The GSE151371 dataset from the Gene Expression Omnibus (GEO) database, comprising 38 SCI samples and 10 healthy control samples, was analyzed. Differential expression analysis, weighted gene co-expression network analysis (WGCNA), and machine learning algorithms were integratively applied to identify key genes associated with SCI. Results: A total of 1,138 differentially expressed genes (DEGs) were identified between SCI patients and healthy controls. Among them, 19 overlapping signature genes were obtained from the intersection of PRGs and WGCNA module genes. Functional enrichment analysis indicated that these genes were mainly involved in the regulation of immune and inflammatory responses, inflammatory cell adhesion and differentiation, and protease-related processes. Machine learning-based feature selection identified 8 hub genes, among which only NOL3 was consistently validated in the independent GSE45006 dataset. Immune infiltration analysis further demonstrated that NOL3 expression was positively correlated with neutrophil and macrophage infiltration, and negatively correlated with multiple T cell subsets, with the strongest negative correlation observed in activated CD8? T cells. Conclusion: NOL3 may play an important role in the pathophysiology of SCI and has potential value as a diagnostic biomarker and therapeutic target.