Cox回归分析在预后数据中的应用

The analysis of prognostic data is commonly performed using the R package "survival" (version 3.3.1) for testing the proportional hazards assumption and conducting Cox regression analysis. A prerequisite for applying Cox regression is that the covariates must satisfy the proportional hazards assumption (P > 0.05). The Variance Inflation Factor (VIF) can be used to assess multicollinearity among variables in the model; generally, a VIF value between 0 and 10 indicates no significant multicollinearity. Cox regression analysis can be applied to both continuous and ordinal variables, with the reference level in ordinal variables serving as the reference category. Variables are included in the multivariate Cox regression analysis if their P-values meet the threshold (P = 0.1).