Fifteen mRNA-lncRNA expression-based signature predicted the survival of late-staged head and neck squamous cell carcinoma

Background: Gene expression is necessary for regulation in almost all biological processes, at the same time, it is related to the prognosis for head and neck squamous cell carcinoma (HNSCC). The prognosis of late-staged HNSCC is important because of its guiding significance on the therapy strategies. Methods: In this work, we analyzed the relationship between gene expression and HNSCC in The Cancer Genome Atlas (TCGA) cohort, and optimized the panel with random forest survival analysis. Subsequently, a Cox multivariate regression-based model was developed to predict the clinical outcome of HNSCC. The performance of the model was assayed in the training cohort and validated in another three independent cohorts (GSE41614, E-TABM-302, E-MTAB-1328). The underlying pathways significantly associated with the model were identified. According to the results, patients of low-score group (median survival months: 27.4, 95% CI: 18.2–43) had a significant poor survival than those of high-score group (median survival months: 69.4, 95% CI: 58.7–72.1, P=2.7e-5), and the observation was repeatable in the other validation cohorts. Further analysis revealed that the model performed better than the other clinical indicators and is independent of these indicators. Results: Comparison revealed that the model performed better than existing models for late HNSCC prognosis. Gene set enrichment analysis (GSEA) elucidated that the model was significantly associated with various cell processes and pathways.