Identification of Kidney Clear Cell Carcinoma Mortality Risk-Associated Gene Mutation by Using a Random Survival Forest Approach

Abstract

Kidney clear cell carcinoma is commonly characterized by poor prognosis, which is associated with the function and differential expression of specific genes. The combination of a typical statistical survival model and nonparametric random forest algorithm provides a more precise estimation for the association between gene mutations and all-cause mortality risk. This study identifies mortality risk-associated gene mutations in kidney clear cell carcinoma by using a random survival forest algorithm. Of 22 candidate genes, VHL (variable importance [VIMP] = 0.097), EDIL3 (VIMP = 0.037), PBRM1 (VIMP = 0.027), PTEN (VIMP = 0.012), BAP1 (VIMP = 0.010), and HMGN5 (VIMP = 0.002) were selected and used to develop a dichotomous risk model for all-cause mortality by using the estimated risk threshold. The high-risk group exhibited a relatively poor survival rate than did the low-risk group (95.5% vs. 93.0%). In conclusion, this study provides a simple dichotomous model for mutation risk, according to the gene mutation risk threshold, by using a random survival forest model. For the gene mutation risk model, VHL, EDIL3, PBRM1, PTEN, BAP1, and HMGN5 were selected to effectively determine the effects of gene mutation on all-cause mortality from kidney clear cell carcinoma.