Developing Dynamic Prediction Methods for Survival Time Lost in Chronic Kidney Disease Progression under Competing Risks.

Abstract

Patients with chronic kidney disease (CKD) may progress to end-stage renal disease (ESRD) or die from other causes during long-term follow-up, making it essential to properly account for competing risks in prognostic modeling. However, most existing CKD prediction models rely on hazard-based measures, which primarily reflect relative effects, lack clinical interpretability, and cannot directly quantify survival time lost due to disease progression or death. To address this limitation, we adopted the restricted mean time lost (RMTL), an absolute and intuitive measure of survival time loss, and developed a dynamic prediction model under competing risks. Given the rich time-dependent covariate information in longitudinal CKD data and the clinical need for patients to understand their disease progression at different stages, we developed a dynamic RMTL prediction model that incorporates the landmark approach. The model captures how covariate effects evolve over time, offering insights into the dynamic impact of clinical variables, and enables individualized prediction of survival time loss over a future window from any given prediction time point. We evaluated its statistical properties through Monte Carlo simulations and demonstrated its practical utility using CKD patient data from the AASK cohort. The results showed that the proposed model yields accurate and robust estimates, captures time-varying covariate effects, and outperforms conventional static models in predictive performance. By quantifying survival time loss under competing risks, the dynamic RMTL model offers clinically interpretable and individualized risk estimates, supporting personalized risk assessment and intervention planning in chronic disease management.