Developing novel dynamic prediction methods for survival time to analyze short-term and long-term progression of Alzheimer's disease.

Tracking and monitoring mild cognitive impairment (MCI) patients to intervene promptly at the imminent onset of Alzheimer's disease (AD) are crucial. However, existing dynamic survival prediction models for the conversion from MCI to AD are mostly based on hazard rates, which are less intuitive to interpret and require adherence to the proportional hazards assumption. To address this, we propose a Bayesian joint model (JM) based on the time scale indicator of the restricted mean survival time (RMST), which can capture the trajectories of multiple longitudinal covariates and dynamically predict the patient time to event. Using Monte Carlo simulation, it can be demonstrated that the JM method has a better prediction performance compared with the static model. To predict the dynamic progression of AD in MCI patients at different stages, based on the landmark (LM) method and the JM method for RMST, we developed an LM-based model for short-term dynamic prediction (LM-ST model) and a JM-based model for long-term dynamic prediction (JM-LT model) utilizing the ADNI database. The internal and external validation results indicate that the predictive performance of the LM-ST and JM-LT models surpasses that of the static RMST model. Additionally, an online web tool for the two dynamic prediction models was created for clinical application. In summary, we propose a novel method and combined it with the existing LM method for AD progression, which improves the predictive power and provides a scientific basis for medical decision-making.