Abstract: Many researchers often need to develop appropriate approaches to evaluate the health-care-related expenditure for a specified patient cohort over a specified time horizon. Such medical cost data frequently not only consist of longitudinal data with repeated measurements for a sample of subjects, but also time-to-event data that involve the censoring mechanism such as right censoring and interval censoring. In addition, the covariates information may be also included. In this talk, I proposed an approach for estimating the cumulative function of the mean of history process with time dependent covariates and right censored time-to-event variable. The proposed estimator is based on joint modeling methods. Theoretical analysis and simulation studies indicate that the proposed estimator is quite recommendable to practical applications due to its simplicity and accuracy. A real data set from a multicenter automatic defibrillator implantation trial (MADIT) is used to illustrate the proposed methodology.