Background <p>Oral squamous cell carcinoma (OSCC) is characterized by poor prognosis and high mortality. Understanding programmed cell death-related genes could provide valuable insights into disease progression and treatment strategies.</p> Methods <p>RNA-sequencing data from 341 OSCC tumor tissues and 31 healthy samples were analyzed from TCGA database, with validation using 76 samples from GSE41613. Single-cell RNA sequencing data was obtained from GSE172577 (6 OSCC samples). Differentially expressed genes (DEGs) were identified and intersected with 1,254 programmed cell death-related genes. A protein–protein interaction network was constructed, and key modules were identified. Univariate Cox, LASSO, and multivariate Cox regression analyses were performed to build a prognostic model. Model performance was evaluated using Kaplan–Meier analysis, ROC curves, and nomogram validation.</p> Results <p>The study identified 200 candidate genes from the intersection of DEGs and programmed cell death-related genes, which were further refined to 57 hub genes through PPI network analysis. A prognostic signature consisting of five genes (MET, GSDMB, KIT, PRKAG3, and CDKN2A) was established and validated. The model demonstrated good predictive performance in both training and validation cohorts (AUC &gt; 0.6 for 1-, 2-, and 3-year survival). Single-cell analysis revealed that prognostic genes were predominantly expressed in stromal and epithelial cells. Cell communication analysis indicated strong interactions between stromal and epithelial cells.</p> Conclusions <p>This study developed and validated a novel five-gene prognostic signature for OSCC based on programmed cell death-related genes. The model shows promising clinical application potential for risk stratification and personalized treatment of OSCC patients.</p>