West Coast Ballroom
WITHDRAWN - Statistical Modeling of Longitudinal Medical Cost Trajectory (307794)
Liang Li, MD Anderson Cancer CenterYu Shen, MD Anderson Cancer Center
Ya-Chen Tina Shih, MD Anderson Cancer Center
*Shikun Wang, MD Anderson Cancer Center
Keywords: Bivariate surface, Joint modeling, Lifetime and survival analysis, Medical cost, SEER Medicare
Projecting cancer care cost is important to policy makers. An indispensable step in cost projection is to estimate the cost trajectory from an incident cohort of cancer patients using longitudinal medical cost data, accounting for terminal events such as death, and right censoring due to loss of follow-up. Since the cancer care cost and survival are correlated, a scientifically meaningful inference in this context is the mean cost trajectory conditional on survival. We propose a two-step semiparametric approach to estimating the cost trajectories from a joint model of longitudinal medical costs and survival. The cost trajectories corresponding to various survival times form a bivariate surface, which is approximated by penalized splines on two-dimensions. The proposed approach balances the practical considerations of model flexibility, statistical efficiency and computational tractability. Asymptotic theory and extensive simulation studies demonstrate that the estimator is unbiased, efficient, and robust to model misspecifications. We estimate the cost trajectories of renal cell cancer patients using the Surveillance, Epidemiology, and End Results-Medicare Linked database.