Of Ahero Rice Survival Analysis with Competing Risks: Insights from the Fine and Gray Model and Covariate Adjustments

Competing risk survival analysis is deemed necessary when manifold events, such as recurrence and death, are present to prevent the incidence of the event of interest. The application of the Fine and Gray model for cumulative incidence function (CIF) estimation and competing risk regression in a simulated dataset is explored in this study. Simulated time-to-event data and covariates are used to estimate the Fine and Gray model both with and without covariates, with comparisons being made against the Kaplan-Meier (KM) method, which does not account for competing risks. It is demonstrated that the Fine and Gray method provides a more accurate representation of event-specific incidence in the presence of competing risks. Competing risks being ignored, as in the Kaplan-Meier approach, can lead to an underestimation of the event of interest. Additionally, the inclusion of covariates like age and tumor size into the Fine and Gray model is shown to significantly impact the incidence of recurrence and competing events. This comparative analysis is provided.