B0263
Title: Enhancing long-term survival prediction with multiple short-term events
Authors: Wen Li - The University of Texas (United States) [presenting]
Jing Ning - The University of Texas MD Anderson Cancer Center (United States)
Jing Zhang - The University of Texas Health Science Center (United States)
Zhouxuan Li - The University of Texas Health Science Center (United States)
Sean Savitz - The University of Texas Health Science Center (United States)
Amirali Tahanan - The University of Texas Health Science Center (United States)
Mohammad Rahbar - The University of Texas Health Science Center (United States)
Abstract: Patients with cardiovascular diseases who experience disease-related short-term events, such as hospitalizations, often exhibit diverse long-term survival outcomes compared to others. The aim is to improve the prediction of long-term survival probability by incorporating multiple short-term events using a flexible varying-coefficient landmark model. The objective is to predict the risk of long-term survival $T <= t0 + L$, $(L>0)$ among patients who survived up to a pre-specified landmark time $t_0$ since the initial admission. Inverse probability weighting estimation equations are formed based on the information of the short-term outcomes before the landmark time. The kernel smoothing method with the use of cross-validation for bandwidth selection is employed to estimate the time-varying coefficients. The predictive performance of the proposed model is evaluated and compared using predictive measures: area under the receiver operating characteristic curve and Brier score. Simulation studies confirm that parameters under the landmark models can be estimated accurately and the predictive performance of the proposed method consistently outperforms existing methods that either do not incorporate or only partially incorporate information from multiple short-term events. The practical application of the model is demonstrated using a community-based cohort from the atherosclerosis risk in communities (ARIC) study.
