Robust Prediction of Prognosis and Immunotherapy Response for Bladder Cancer through Machine Learning Algorithm.

ABSTRACT: The important roles of machine learning and ferroptosis in bladder cancer (BCa) are still poorly understood. In this study, a comprehensive analysis of 19 ferroptosis-related genes (FRGs) was performed in 1322 patients with BCa from four independent patient cohorts and a pan-cancer cohort of 9824 patients. Twelve FRGs were selected through machine learning algorithm to construct the prognosis model. Significantly differential survival outcomes (hazard ratio (HR) = 2.09, 95% confidence interval (CI): 1.55−2.82, p < 0.0001) were observed between patients with high and low ferroptosis scores in the TCGA cohort, which was also verified in the E-MTAB-4321 cohort (HR = 4.71, 95% CI: 1.58−14.03, p < 0.0001), the GSE31684 cohort (HR = 1.76, 95% CI: 1.08−2.87, p = 0.02), and the pan-cancer cohort (

SUBMITTER: Hu S 

PROVIDER: S-EPMC9223035 | biostudies-literature | 2022 Jun

REPOSITORIES: biostudies-literature