Longitudinal and time-to-event modeling for prognostic implications of radical surgery in retroperitoneal sarcoma.

Retroperitoneal sarcoma (RPS) is a rare malignancy which can be difficult to manage due to the variety of clinical behaviors. In this study, we aimed to develop a parametric modeling framework to quantify the relationship between postoperative dynamics of several biomarkers and overall/progression-free survival of RPS. One hundred seventy-four patients with RPS who received surgical resection with curative intent at the Peking University Cancer Hospital Sarcoma Center were retrospectively included. Potential prognostic factors were preliminarily identified. Longitudinal analyses of body mass index (BMI), serum total protein (TP), and white blood cells (WBCs) were performed using nonlinear mixed effects models. The impacts of time-varying and time-invariant predictors on survival were investigated by parametric time-to-event (TTE) models. The majority of patients experienced decline in BMI, recovery of TP, as well as transient elevation in WBC counts after surgery, which significantly correlated with survival. An indirect-response model incorporating surgery effect described the fluctuation in percentage BMI. The recovery of TP was captured by a modified Gompertz model, and a semimechanistic model was selected for WBCs. TTE models estimated that the daily cumulative average of predicted BMI and WBC, the seventh-day TP, as well as certain baseline variables, were significant predictors of survival. Model-based simulations were performed to examine the clinical significance of prognostic factors. The current work quantified the individual trajectories of prognostic biomarkers in response to surgery and predicted clinical outcomes, which would constitute an additional strategy for disease monitoring and intervention in postoperative RPS.