Predicting survival of advanced laryngeal squamous cell carcinoma: comparison of machine learning models and Cox regression models.

Laryngeal squamous cell carcinoma (LSCC) is a common tumor type. High recurrence rates remain an important factor affecting the survival and quality of life of advanced LSCC patients. We aimed to build a new nomogram and a random survival forest model using machine learning to predict the risk of LSCC progress. The study included 671 patients with AJCC stages III-IV LSCC. To develop a prognostic model, Cox regression analyses were used to assess the relationship between clinic-pathologic factors and disease-free survival (DFS). RSF analysis was also used to predict the DFS of LSCC patients. The ROC curve revealed that the Cox model exhibited good sensitivity and specificity in predicting DFS in the training and validation cohorts (1 year, validation AUC = 0.679, training AUC = 0.693; 3 years, validation AUC = 0.716, training AUC = 0.655; 5 years, validation AUC = 0.717, training AUC = 0.659). Random survival forest analysis showed that N stage, clinical stage, and postoperative chemoradiotherapy were prognostically significant variables associated with survival. The random forest model exhibited better prediction ability than the Cox regression model in the training cohort; however, the two models showed similar prediction ability in the validation cohort.

Identifying KRT20 as a Potential Key Gene in Lymphatic Metastasis of Head and Neck Squamous Cell Carcinoma.

Background: Head and neck squamous cell carcinoma (HNSCC) was the seventh most common cancer worldwide in 2018. Lymphatic metastasis (LM) is closely related to HNSCC prognosis and recurrence. However, the underlying mechanism of LM remains unclear. Therefore, this study aimed to identify the key genes in the LM of HNSCC. Methods: We used The Cancer Genome Atlas (TCGA) to identify differentially expressed genes (DEGs) between LM and non-LM cases. A random forest model, the Search Tool for the Retrieval of Interacting Genes, Cytoscape, and cytoHubba were used to identify hub genes among DEGs, including KRT20 (Cytokeratins 20). We analyzed the survival of KRT20 in TCGA, and we overexpressed KRT20 in HNSCC cell lines to investigate its effects on migration and invasion. We also correlated the expression of KRT20 in HNSCC tissue microarrays with survival and clinicopathological features. Results: We identified 243 DEGs-143 upregulated genes and 100 downregulated genes. Further analysis revealed that KRT20 is a potential key gene associated with LM and overall survival rates among patients with HNSCC. Overexpression of KRT20 increased the migration and invasion ability of HNSCC cell lines Tu686 and FD-LSC-1. Tissue microarray studies demonstrated an overexpression of KRT20 among N1+ patients (including N1-N3 patients). Survival analysis results and the clinicopathological features of HNSCC tissue microarrays were consistent with our analysis of TCGA. Thus, a high KRT20 expression level might suggest an adverse HNSCC prognosis. Our gene set enrichment analysis showed that KRT20 participates in many metabolic pathways, including those related to tumorigenesis and cancer development. Conclusions: We propose that KRT20 may be a key gene in HNSCC with LM.